Responses
responses.connect()
**** ``
Connect to a persistent Responses API WebSocket. Send response.create events and receive response stream events over the socket.
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
client.responses.connect()
Create a model response
responses.create(ResponseCreateParams**kwargs) -> Response
post /responses
Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.
Parameters
-
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
context_management: Optional[Iterable[ContextManagement]]Context management configuration for this request.
-
type: strThe context management entry type. Currently only 'compaction' is supported.
-
compact_threshold: Optional[int]Token threshold at which compaction should be triggered for this entry.
-
-
conversation: Optional[Conversation]The conversation that this response belongs to. Items from this conversation are prepended to
input_itemsfor this response request. Input items and output items from this response are automatically added to this conversation after this response completes.-
strThe unique ID of the conversation.
-
class ResponseConversationParam: …The conversation that this response belongs to.
-
id: strThe unique ID of the conversation.
-
-
-
include: Optional[List[ResponseIncludable]]Specify additional output data to include in the model response. Currently supported values are:
-
web_search_call.action.sources: Include the sources of the web search tool call. -
code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items. -
computer_call_output.output.image_url: Include image urls from the computer call output. -
file_search_call.results: Include the search results of the file search tool call. -
message.input_image.image_url: Include image urls from the input message. -
message.output_text.logprobs: Include logprobs with assistant messages. -
reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when thestoreparameter is set tofalse, or when an organization is enrolled in the zero data retention program). -
"file_search_call.results" -
"web_search_call.results" -
"web_search_call.action.sources" -
"message.input_image.image_url" -
"computer_call_output.output.image_url" -
"code_interpreter_call.outputs" -
"reasoning.encrypted_content" -
"message.output_text.logprobs"
-
-
input: Optional[Union[str, ResponseInputParam]]Text, image, or file inputs to the model, used to generate a response.
Learn more:
-
strA text input to the model, equivalent to a text input with the
userrole. -
Iterable[ResponseInputItemParam]-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
instructions: Optional[str]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: Optional[ResponsesModel]Model ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
moderation: Optional[Moderation]Configuration for running moderation on the input and output of this response.
-
model: strThe moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.
-
-
parallel_tool_calls: Optional[bool]Whether to allow the model to run tool calls in parallel.
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePromptParam]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
store: Optional[bool]Whether to store the generated model response for later retrieval via API.
-
stream: Optional[Literal[false]]If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
false
-
stream_options: Optional[StreamOptions]Options for streaming responses. Only set this when you set
stream: true.-
include_obfuscation: Optional[bool]When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an
obfuscationfield on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can setinclude_obfuscationto false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
-
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
text: Optional[ResponseTextConfigParam]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
tool_choice: Optional[ToolChoice]How the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: Optional[Iterable[ToolParam]]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
Returns
-
class Response: …-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
for response in client.responses.create():
print(response)
Response
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"phase": "commentary"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"defer_loading": true,
"description": "description"
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"moderation": {
"input": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
},
"output": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
}
},
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in_memory",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}
Text input
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input="Tell me a three sentence bedtime story about a unicorn."
)
print(response)
Response
{
"id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
"object": "response",
"created_at": 1741476542,
"status": "completed",
"completed_at": 1741476543,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 36,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 87,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 123
},
"user": null,
"metadata": {}
}
Image input
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input=[
{
"role": "user",
"content": [
{ "type": "input_text", "text": "what is in this image?" },
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
]
}
]
)
print(response)
Response
{
"id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
"object": "response",
"created_at": 1741476777,
"status": "completed",
"completed_at": 1741476778,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 52,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 380
},
"user": null,
"metadata": {}
}
File input
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input=[
{
"role": "user",
"content": [
{ "type": "input_text", "text": "what is in this file?" },
{
"type": "input_file",
"file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf"
}
]
}
]
)
print(response)
Response
{
"id": "resp_686eef60237881a2bd1180bb8b13de430e34c516d176ff86",
"object": "response",
"created_at": 1752100704,
"status": "completed",
"completed_at": 1752100705,
"background": false,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"max_tool_calls": null,
"model": "gpt-5.4",
"output": [
{
"id": "msg_686eef60d3e081a29283bdcbc4322fd90e34c516d176ff86",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "The file seems to contain excerpts from a letter to the shareholders of Berkshire Hathaway Inc., likely written by Warren Buffett. It covers several topics:\n\n1. **Communication Philosophy**: Buffett emphasizes the importance of transparency and candidness in reporting mistakes and successes to shareholders.\n\n2. **Mistakes and Learnings**: The letter acknowledges past mistakes in business assessments and management hires, highlighting the importance of correcting errors promptly.\n\n3. **CEO Succession**: Mention of Greg Abel stepping in as the new CEO and continuing the tradition of honest communication.\n\n4. **Pete Liegl Story**: A detailed account of acquiring Forest River and the relationship with its founder, highlighting trust and effective business decisions.\n\n5. **2024 Performance**: Overview of business performance, particularly in insurance and investment activities, with a focus on GEICO's improvement.\n\n6. **Tax Contributions**: Discussion of significant tax payments to the U.S. Treasury, credited to shareholders' reinvestments.\n\n7. **Investment Strategy**: A breakdown of Berkshire\u2019s investments in both controlled subsidiaries and marketable equities, along with a focus on long-term holding strategies.\n\n8. **American Capitalism**: Reflections on America\u2019s economic development and Berkshire\u2019s role within it.\n\n9. **Property-Casualty Insurance**: Insights into the P/C insurance business model and its challenges and benefits.\n\n10. **Japanese Investments**: Information about Berkshire\u2019s investments in Japanese companies and future plans.\n\n11. **Annual Meeting**: Details about the upcoming annual gathering in Omaha, including schedule changes and new book releases.\n\n12. **Personal Anecdotes**: Light-hearted stories about family and interactions, conveying Buffett's personable approach.\n\n13. **Financial Performance Data**: Tables comparing Berkshire\u2019s annual performance to the S&P 500, showing impressive long-term gains.\n\nOverall, the letter reinforces Berkshire Hathaway's commitment to transparency, investment in both its businesses and the wider economy, and emphasizes strong leadership and prudent financial management."
}
],
"role": "assistant"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"service_tier": "default",
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 8438,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 398,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 8836
},
"user": null,
"metadata": {}
}
Web search
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
tools=[{ "type": "web_search_preview" }],
input="What was a positive news story from today?",
)
print(response)
Response
{
"id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c",
"object": "response",
"created_at": 1741484430,
"status": "completed",
"completed_at": 1741484431,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "web_search_call",
"id": "ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c",
"status": "completed"
},
{
"type": "message",
"id": "msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "As of today, March 9, 2025, one notable positive news story...",
"annotations": [
{
"type": "url_citation",
"start_index": 442,
"end_index": 557,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 962,
"end_index": 1077,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 1336,
"end_index": 1451,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "web_search_preview",
"domains": [],
"search_context_size": "medium",
"user_location": {
"type": "approximate",
"city": null,
"country": "US",
"region": null,
"timezone": null
}
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 356,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 684
},
"user": null,
"metadata": {}
}
File search
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
tools=[{
"type": "file_search",
"vector_store_ids": ["vs_1234567890"],
"max_num_results": 20
}],
input="What are the attributes of an ancient brown dragon?",
)
print(response)
Response
{
"id": "resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7",
"object": "response",
"created_at": 1741485253,
"status": "completed",
"completed_at": 1741485254,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "file_search_call",
"id": "fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7",
"status": "completed",
"queries": [
"attributes of an ancient brown dragon"
],
"results": null
},
{
"type": "message",
"id": "msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The attributes of an ancient brown dragon include...",
"annotations": [
{
"type": "file_citation",
"index": 320,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 576,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1156,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1225,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "file_search",
"filters": null,
"max_num_results": 20,
"ranking_options": {
"ranker": "auto",
"score_threshold": 0.0
},
"vector_store_ids": [
"vs_1234567890"
]
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 18307,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 348,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 18655
},
"user": null,
"metadata": {}
}
Streaming
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
instructions="You are a helpful assistant.",
input="Hello!",
stream=True
)
for event in response:
print(event)
Response
event: response.created
data: {"type":"response.created","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.in_progress
data: {"type":"response.in_progress","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"in_progress","role":"assistant","content":[]}}
event: response.content_part.added
data: {"type":"response.content_part.added","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"","annotations":[]}}
event: response.output_text.delta
data: {"type":"response.output_text.delta","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"delta":"Hi"}
...
event: response.output_text.done
data: {"type":"response.output_text.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"text":"Hi there! How can I assist you today?"}
event: response.content_part.done
data: {"type":"response.content_part.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}}
event: response.output_item.done
data: {"type":"response.output_item.done","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}}
event: response.completed
data: {"type":"response.completed","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"completed","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":{"input_tokens":37,"output_tokens":11,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":48},"user":null,"metadata":{}}}
Functions
from openai import OpenAI
client = OpenAI()
tools = [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location", "unit"],
}
}
]
response = client.responses.create(
model="gpt-5.4",
tools=tools,
input="What is the weather like in Boston today?",
tool_choice="auto"
)
print(response)
Response
{
"id": "resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0",
"object": "response",
"created_at": 1741294021,
"status": "completed",
"completed_at": 1741294022,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "function_call",
"id": "fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0",
"call_id": "call_unLAR8MvFNptuiZK6K6HCy5k",
"name": "get_current_weather",
"arguments": "{\"location\":\"Boston, MA\",\"unit\":\"celsius\"}",
"status": "completed"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "function",
"description": "Get the current weather in a given location",
"name": "get_current_weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
},
"strict": true
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 291,
"output_tokens": 23,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 314
},
"user": null,
"metadata": {}
}
Reasoning
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="o3-mini",
input="How much wood would a woodchuck chuck?",
reasoning={
"effort": "high"
}
)
print(response)
Response
{
"id": "resp_67ccd7eca01881908ff0b5146584e408072912b2993db808",
"object": "response",
"created_at": 1741477868,
"status": "completed",
"completed_at": 1741477869,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "o1-2024-12-17",
"output": [
{
"type": "message",
"id": "msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The classic tongue twister...",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": "high",
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 81,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 1035,
"output_tokens_details": {
"reasoning_tokens": 832
},
"total_tokens": 1116
},
"user": null,
"metadata": {}
}
Get a model response
responses.retrieve(strresponse_id, ResponseRetrieveParams**kwargs) -> Response
get /responses/{response_id}
Retrieves a model response with the given ID.
Parameters
-
response_id: str -
include: Optional[List[ResponseIncludable]]Additional fields to include in the response. See the
includeparameter for Response creation above for more information.-
"file_search_call.results" -
"web_search_call.results" -
"web_search_call.action.sources" -
"message.input_image.image_url" -
"computer_call_output.output.image_url" -
"code_interpreter_call.outputs" -
"reasoning.encrypted_content" -
"message.output_text.logprobs"
-
-
include_obfuscation: Optional[bool]When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an
obfuscationfield on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can setinclude_obfuscationto false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. -
starting_after: Optional[int]The sequence number of the event after which to start streaming.
-
stream: Optional[Literal[false]]If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
false
Returns
-
class Response: …-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
for response in client.responses.retrieve(
response_id="resp_677efb5139a88190b512bc3fef8e535d",
):
print(response)
Response
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"phase": "commentary"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"defer_loading": true,
"description": "description"
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"moderation": {
"input": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
},
"output": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
}
},
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in_memory",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}
Example
from openai import OpenAI
client = OpenAI()
response = client.responses.retrieve("resp_123")
print(response)
Response
{
"id": "resp_67cb71b351908190a308f3859487620d06981a8637e6bc44",
"object": "response",
"created_at": 1741386163,
"status": "completed",
"completed_at": 1741386164,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-4o-2024-08-06",
"output": [
{
"type": "message",
"id": "msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Silent circuits hum, \nThoughts emerge in data streams— \nDigital dawn breaks.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 32,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 18,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 50
},
"user": null,
"metadata": {}
}
Delete a model response
responses.delete(strresponse_id)
delete /responses/{response_id}
Deletes a model response with the given ID.
Parameters
response_id: str
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
client.responses.delete(
"resp_677efb5139a88190b512bc3fef8e535d",
)
Example
from openai import OpenAI
client = OpenAI()
response = client.responses.delete("resp_123")
print(response)
Response
{
"id": "resp_6786a1bec27481909a17d673315b29f6",
"object": "response",
"deleted": true
}
Cancel a response
responses.cancel(strresponse_id) -> Response
post /responses/{response_id}/cancel
Cancels a model response with the given ID. Only responses created with
the background parameter set to true can be cancelled.
Learn more.
Parameters
response_id: str
Returns
-
class Response: …-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
response = client.responses.cancel(
"resp_677efb5139a88190b512bc3fef8e535d",
)
print(response.id)
Response
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"phase": "commentary"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"defer_loading": true,
"description": "description"
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"moderation": {
"input": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
},
"output": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
}
},
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in_memory",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}
Example
from openai import OpenAI
client = OpenAI()
response = client.responses.cancel("resp_123")
print(response)
Response
{
"id": "resp_67cb71b351908190a308f3859487620d06981a8637e6bc44",
"object": "response",
"created_at": 1741386163,
"status": "cancelled",
"background": true,
"completed_at": null,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-4o-2024-08-06",
"output": [
{
"type": "message",
"id": "msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44",
"status": "in_progress",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Silent circuits hum, \nThoughts emerge in data streams— \nDigital dawn breaks.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": null,
"user": null,
"metadata": {}
}
Compact a response
responses.compact(ResponseCompactParams**kwargs) -> CompactedResponse
post /responses/compact
Compact a conversation. Returns a compacted response object.
Learn when and how to compact long-running conversations in the conversation state guide. For ZDR-compatible compaction details, see Compaction (advanced).
Parameters
-
model: Union[Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 89 more], str, null]Model ID used to generate the response, like
gpt-5oro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 89 more]Model ID used to generate the response, like
gpt-5oro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613" -
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
str
-
-
input: Optional[Union[str, Iterable[ResponseInputItemParam], null]]Text, image, or file inputs to the model, used to generate a response
-
strA text input to the model, equivalent to a text input with the
userrole. -
Iterable[ResponseInputItemParam]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
instructions: Optional[str]A system (or developer) message inserted into the model's context. When used along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt_cache_key: Optional[str]A key to use when reading from or writing to the prompt cache.
-
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]How long to retain a prompt cache entry created by this request.
-
"in_memory" -
"24h"
-
-
service_tier: Optional[Literal["auto", "default", "flex", "priority"]]The service tier to use for this request.
-
"auto" -
"default" -
"flex" -
"priority"
-
Returns
-
class CompactedResponse: …-
id: strThe unique identifier for the compacted response.
-
created_at: intUnix timestamp (in seconds) when the compacted conversation was created.
-
object: Literal["response.compaction"]The object type. Always
response.compaction."response.compaction"
-
output: List[ResponseOutputItem]The compacted list of output items. This is a list of all user messages, followed by a single compaction item.
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
usage: ResponseUsageToken accounting for the compaction pass, including cached, reasoning, and total tokens.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
compacted_response = client.responses.compact(
model="gpt-5.4",
)
print(compacted_response.id)
Response
{
"id": "id",
"created_at": 0,
"object": "response.compaction",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"phase": "commentary"
}
],
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
}
}
Example
from openai import OpenAI
client = OpenAI()
compacted_response = client.responses.compact(
model="gpt-5.1-codex-max",
input=[
{
"role": "user",
"content": "Create a simple landing page for a dog petting cafe.",
},
# All items returned from previous requests are included here, like reasoning, message, function call, etc.
{
"id": "msg_001",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "Below is a single file, ready-to-use landing page for a dog petting café:...",
},
],
"role": "assistant",
},
]
)
# Pass the compacted_response.output as input to the next request
print(compacted_response)
Response
{
"id": "resp_001",
"object": "response.compaction",
"created_at": 1764967971,
"output": [
{
"id": "msg_000",
"type": "message",
"status": "completed",
"content": [
{
"type": "input_text",
"text": "Create a simple landing page for a dog petting cafe."
}
],
"role": "user"
},
{
"id": "cmp_001",
"type": "compaction",
"encrypted_content": "gAAAAABpM0Yj-...="
}
],
"usage": {
"input_tokens": 139,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 438,
"output_tokens_details": {
"reasoning_tokens": 64
},
"total_tokens": 577
}
}
Domain Types
Apply Patch Tool
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
Compacted Response
-
class CompactedResponse: …-
id: strThe unique identifier for the compacted response.
-
created_at: intUnix timestamp (in seconds) when the compacted conversation was created.
-
object: Literal["response.compaction"]The object type. Always
response.compaction."response.compaction"
-
output: List[ResponseOutputItem]The compacted list of output items. This is a list of all user messages, followed by a single compaction item.
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
usage: ResponseUsageToken accounting for the compaction pass, including cached, reasoning, and total tokens.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
Computer Action
-
ComputerActionA click action.
-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
Computer Action List
-
List[ComputerAction]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
Computer Tool
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
Computer Use Preview Tool
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
Container Auto
-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
Container Network Policy Allowlist
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
Container Network Policy Disabled
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
Container Network Policy Domain Secret
-
class ContainerNetworkPolicyDomainSecret: …-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
Container Reference
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
Custom Tool
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
Easy Input Message
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
File Search Tool
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
Function Shell Tool
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
Function Tool
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
Inline Skill
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
Inline Skill Source
-
class InlineSkillSource: …Inline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
Local Environment
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
Local Skill
-
class LocalSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
Namespace Tool
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
Response
-
class Response: …-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
Response Apply Patch Tool Call
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
Response Apply Patch Tool Call Output
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
Response Audio Delta Event
-
class ResponseAudioDeltaEvent: …Emitted when there is a partial audio response.
-
delta: strA chunk of Base64 encoded response audio bytes.
-
sequence_number: intA sequence number for this chunk of the stream response.
-
type: Literal["response.audio.delta"]The type of the event. Always
response.audio.delta."response.audio.delta"
-
Response Audio Done Event
-
class ResponseAudioDoneEvent: …Emitted when the audio response is complete.
-
sequence_number: intThe sequence number of the delta.
-
type: Literal["response.audio.done"]The type of the event. Always
response.audio.done."response.audio.done"
-
Response Audio Transcript Delta Event
-
class ResponseAudioTranscriptDeltaEvent: …Emitted when there is a partial transcript of audio.
-
delta: strThe partial transcript of the audio response.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.delta"]The type of the event. Always
response.audio.transcript.delta."response.audio.transcript.delta"
-
Response Audio Transcript Done Event
-
class ResponseAudioTranscriptDoneEvent: …Emitted when the full audio transcript is completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.done"]The type of the event. Always
response.audio.transcript.done."response.audio.transcript.done"
-
Response Code Interpreter Call Code Delta Event
-
class ResponseCodeInterpreterCallCodeDeltaEvent: …Emitted when a partial code snippet is streamed by the code interpreter.
-
delta: strThe partial code snippet being streamed by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is being streamed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.delta"]The type of the event. Always
response.code_interpreter_call_code.delta."response.code_interpreter_call_code.delta"
-
Response Code Interpreter Call Code Done Event
-
class ResponseCodeInterpreterCallCodeDoneEvent: …Emitted when the code snippet is finalized by the code interpreter.
-
code: strThe final code snippet output by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is finalized.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.done"]The type of the event. Always
response.code_interpreter_call_code.done."response.code_interpreter_call_code.done"
-
Response Code Interpreter Call Completed Event
-
class ResponseCodeInterpreterCallCompletedEvent: …Emitted when the code interpreter call is completed.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is completed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.completed"]The type of the event. Always
response.code_interpreter_call.completed."response.code_interpreter_call.completed"
-
Response Code Interpreter Call In Progress Event
-
class ResponseCodeInterpreterCallInProgressEvent: …Emitted when a code interpreter call is in progress.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is in progress.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.in_progress"]The type of the event. Always
response.code_interpreter_call.in_progress."response.code_interpreter_call.in_progress"
-
Response Code Interpreter Call Interpreting Event
-
class ResponseCodeInterpreterCallInterpretingEvent: …Emitted when the code interpreter is actively interpreting the code snippet.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter is interpreting code.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.interpreting"]The type of the event. Always
response.code_interpreter_call.interpreting."response.code_interpreter_call.interpreting"
-
Response Code Interpreter Tool Call
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
Response Compaction Item
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Compaction Item Param
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
Response Completed Event
-
class ResponseCompletedEvent: …Emitted when the model response is complete.
-
response: ResponseProperties of the completed response.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.completed"]The type of the event. Always
response.completed."response.completed"
-
Response Computer Tool Call
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
Response Computer Tool Call Output Item
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Computer Tool Call Output Screenshot
-
class ResponseComputerToolCallOutputScreenshot: …A computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
Response Container Reference
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
Response Content
-
ResponseContentMulti-modal input and output contents.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
class ReasoningTextContent: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
Response Content Part Added Event
-
class ResponseContentPartAddedEvent: …Emitted when a new content part is added.
-
content_index: intThe index of the content part that was added.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that was added.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.added"]The type of the event. Always
response.content_part.added."response.content_part.added"
-
Response Content Part Done Event
-
class ResponseContentPartDoneEvent: …Emitted when a content part is done.
-
content_index: intThe index of the content part that is done.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that is done.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.done"]The type of the event. Always
response.content_part.done."response.content_part.done"
-
Response Conversation Param
-
class ResponseConversationParam: …The conversation that this response belongs to.
-
id: strThe unique ID of the conversation.
-
Response Created Event
-
class ResponseCreatedEvent: …An event that is emitted when a response is created.
-
response: ResponseThe response that was created.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.created"]The type of the event. Always
response.created."response.created"
-
Response Custom Tool Call
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
Response Custom Tool Call Input Delta Event
-
class ResponseCustomToolCallInputDeltaEvent: …Event representing a delta (partial update) to the input of a custom tool call.
-
delta: strThe incremental input data (delta) for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this delta applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.delta"]The event type identifier.
"response.custom_tool_call_input.delta"
-
Response Custom Tool Call Input Done Event
-
class ResponseCustomToolCallInputDoneEvent: …Event indicating that input for a custom tool call is complete.
-
input: strThe complete input data for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this event applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.done"]The event type identifier.
"response.custom_tool_call_input.done"
-
Response Custom Tool Call Item
-
class ResponseCustomToolCallItem: …A call to a custom tool created by the model.
-
id: strThe unique ID of the custom tool call item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Custom Tool Call Output
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
Response Custom Tool Call Output Item
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Error
-
class ResponseError: …An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
Response Error Event
-
class ResponseErrorEvent: …Emitted when an error occurs.
-
code: Optional[str]The error code.
-
message: strThe error message.
-
param: Optional[str]The error parameter.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["error"]The type of the event. Always
error."error"
-
Response Failed Event
-
class ResponseFailedEvent: …An event that is emitted when a response fails.
-
response: ResponseThe response that failed.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.failed"]The type of the event. Always
response.failed."response.failed"
-
Response File Search Call Completed Event
-
class ResponseFileSearchCallCompletedEvent: …Emitted when a file search call is completed (results found).
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.completed"]The type of the event. Always
response.file_search_call.completed."response.file_search_call.completed"
-
Response File Search Call In Progress Event
-
class ResponseFileSearchCallInProgressEvent: …Emitted when a file search call is initiated.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.in_progress"]The type of the event. Always
response.file_search_call.in_progress."response.file_search_call.in_progress"
-
Response File Search Call Searching Event
-
class ResponseFileSearchCallSearchingEvent: …Emitted when a file search is currently searching.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is searching.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.searching"]The type of the event. Always
response.file_search_call.searching."response.file_search_call.searching"
-
Response File Search Tool Call
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
Response Format Text Config
-
ResponseFormatTextConfigAn object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
Response Format Text JSON Schema Config
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
Response Function Call Arguments Delta Event
-
class ResponseFunctionCallArgumentsDeltaEvent: …Emitted when there is a partial function-call arguments delta.
-
delta: strThe function-call arguments delta that is added.
-
item_id: strThe ID of the output item that the function-call arguments delta is added to.
-
output_index: intThe index of the output item that the function-call arguments delta is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.delta"]The type of the event. Always
response.function_call_arguments.delta."response.function_call_arguments.delta"
-
Response Function Call Arguments Done Event
-
class ResponseFunctionCallArgumentsDoneEvent: …Emitted when function-call arguments are finalized.
-
arguments: strThe function-call arguments.
-
item_id: strThe ID of the item.
-
name: strThe name of the function that was called.
-
output_index: intThe index of the output item.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.done"]"response.function_call_arguments.done"
-
Response Function Call Output Item
-
ResponseFunctionCallOutputItemA piece of message content, such as text, an image, or a file.
-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
Response Function Call Output Item List
-
List[ResponseFunctionCallOutputItem]An array of content outputs (text, image, file) for the function tool call.
-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
Response Function Shell Call Output Content
-
class ResponseFunctionShellCallOutputContent: …Captured stdout and stderr for a portion of a shell tool call output.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
Response Function Shell Tool Call
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
Response Function Shell Tool Call Output
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Function Tool Call
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
Response Function Tool Call Item
-
class ResponseFunctionToolCallItem: …A tool call to run a function. See the function calling guide for more information.
-
id: strThe unique ID of the function tool call.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Function Tool Call Output Item
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Function Web Search
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
Response Image Gen Call Completed Event
-
class ResponseImageGenCallCompletedEvent: …Emitted when an image generation tool call has completed and the final image is available.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.image_generation_call.completed"]The type of the event. Always 'response.image_generation_call.completed'.
"response.image_generation_call.completed"
-
Response Image Gen Call Generating Event
-
class ResponseImageGenCallGeneratingEvent: …Emitted when an image generation tool call is actively generating an image (intermediate state).
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.generating"]The type of the event. Always 'response.image_generation_call.generating'.
"response.image_generation_call.generating"
-
Response Image Gen Call In Progress Event
-
class ResponseImageGenCallInProgressEvent: …Emitted when an image generation tool call is in progress.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.in_progress"]The type of the event. Always 'response.image_generation_call.in_progress'.
"response.image_generation_call.in_progress"
-
Response Image Gen Call Partial Image Event
-
class ResponseImageGenCallPartialImageEvent: …Emitted when a partial image is available during image generation streaming.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
partial_image_b64: strBase64-encoded partial image data, suitable for rendering as an image.
-
partial_image_index: int0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.partial_image"]The type of the event. Always 'response.image_generation_call.partial_image'.
"response.image_generation_call.partial_image"
-
Response In Progress Event
-
class ResponseInProgressEvent: …Emitted when the response is in progress.
-
response: ResponseThe response that is in progress.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.in_progress"]The type of the event. Always
response.in_progress."response.in_progress"
-
Response Includable
-
Literal["file_search_call.results", "web_search_call.results", "web_search_call.action.sources", 5 more]Specify additional output data to include in the model response. Currently supported values are:
-
web_search_call.results: Include the search results of the web search tool call. -
web_search_call.action.sources: Include the sources of the web search tool call. -
code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items. -
computer_call_output.output.image_url: Include image urls from the computer call output. -
file_search_call.results: Include the search results of the file search tool call. -
message.input_image.image_url: Include image urls from the input message. -
message.output_text.logprobs: Include logprobs with assistant messages. -
reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when thestoreparameter is set tofalse, or when an organization is enrolled in the zero data retention program). -
"file_search_call.results" -
"web_search_call.results" -
"web_search_call.action.sources" -
"message.input_image.image_url" -
"computer_call_output.output.image_url" -
"code_interpreter_call.outputs" -
"reasoning.encrypted_content" -
"message.output_text.logprobs"
-
Response Incomplete Event
-
class ResponseIncompleteEvent: …An event that is emitted when a response finishes as incomplete.
-
response: ResponseThe response that was incomplete.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.incomplete"]The type of the event. Always
response.incomplete."response.incomplete"
-
Response Input
-
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
Response Input Audio
-
class ResponseInputAudio: …An audio input to the model.
-
input_audio: InputAudio-
data: strBase64-encoded audio data.
-
format: Literal["mp3", "wav"]The format of the audio data. Currently supported formats are
mp3andwav.-
"mp3" -
"wav"
-
-
-
type: Literal["input_audio"]The type of the input item. Always
input_audio."input_audio"
-
Response Input Content
-
ResponseInputContentA text input to the model.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
Response Input File
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
Response Input File Content
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
Response Input Image
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
Response Input Image Content
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
Response Input Item
-
ResponseInputItemA message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
Response Input Message Content List
-
List[ResponseInputContent]A list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
Response Input Message Item
-
class ResponseInputMessageItem: …-
id: strThe unique ID of the message input.
-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
type: Literal["message"]The type of the message input. Always set to
message."message"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
Response Input Text
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
Response Input Text Content
-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
Response Item
-
ResponseItemContent item used to generate a response.
-
class ResponseInputMessageItem: …-
id: strThe unique ID of the message input.
-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
type: Literal["message"]The type of the message input. Always set to
message."message"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCallItem: …A tool call to run a function. See the function calling guide for more information.
-
id: strThe unique ID of the function tool call.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallItem: …A call to a custom tool created by the model.
-
id: strThe unique ID of the custom tool call item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
Response Local Environment
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
Response Mcp Call Arguments Delta Event
-
class ResponseMcpCallArgumentsDeltaEvent: …Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
-
delta: strA JSON string containing the partial update to the arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.delta"]The type of the event. Always 'response.mcp_call_arguments.delta'.
"response.mcp_call_arguments.delta"
-
Response Mcp Call Arguments Done Event
-
class ResponseMcpCallArgumentsDoneEvent: …Emitted when the arguments for an MCP tool call are finalized.
-
arguments: strA JSON string containing the finalized arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.done"]The type of the event. Always 'response.mcp_call_arguments.done'.
"response.mcp_call_arguments.done"
-
Response Mcp Call Completed Event
-
class ResponseMcpCallCompletedEvent: …Emitted when an MCP tool call has completed successfully.
-
item_id: strThe ID of the MCP tool call item that completed.
-
output_index: intThe index of the output item that completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.completed"]The type of the event. Always 'response.mcp_call.completed'.
"response.mcp_call.completed"
-
Response Mcp Call Failed Event
-
class ResponseMcpCallFailedEvent: …Emitted when an MCP tool call has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.failed"]The type of the event. Always 'response.mcp_call.failed'.
"response.mcp_call.failed"
-
Response Mcp Call In Progress Event
-
class ResponseMcpCallInProgressEvent: …Emitted when an MCP tool call is in progress.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.in_progress"]The type of the event. Always 'response.mcp_call.in_progress'.
"response.mcp_call.in_progress"
-
Response Mcp List Tools Completed Event
-
class ResponseMcpListToolsCompletedEvent: …Emitted when the list of available MCP tools has been successfully retrieved.
-
item_id: strThe ID of the MCP tool call item that produced this output.
-
output_index: intThe index of the output item that was processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.completed"]The type of the event. Always 'response.mcp_list_tools.completed'.
"response.mcp_list_tools.completed"
-
Response Mcp List Tools Failed Event
-
class ResponseMcpListToolsFailedEvent: …Emitted when the attempt to list available MCP tools has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.failed"]The type of the event. Always 'response.mcp_list_tools.failed'.
"response.mcp_list_tools.failed"
-
Response Mcp List Tools In Progress Event
-
class ResponseMcpListToolsInProgressEvent: …Emitted when the system is in the process of retrieving the list of available MCP tools.
-
item_id: strThe ID of the MCP tool call item that is being processed.
-
output_index: intThe index of the output item that is being processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.in_progress"]The type of the event. Always 'response.mcp_list_tools.in_progress'.
"response.mcp_list_tools.in_progress"
-
Response Output Audio
-
class ResponseOutputAudio: …An audio output from the model.
-
data: strBase64-encoded audio data from the model.
-
transcript: strThe transcript of the audio data from the model.
-
type: Literal["output_audio"]The type of the output audio. Always
output_audio."output_audio"
-
Response Output Item
-
ResponseOutputItemAn output message from the model.
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
Response Output Item Added Event
-
class ResponseOutputItemAddedEvent: …Emitted when a new output item is added.
-
item: ResponseOutputItemThe output item that was added.
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
output_index: intThe index of the output item that was added.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.added"]The type of the event. Always
response.output_item.added."response.output_item.added"
-
Response Output Item Done Event
-
class ResponseOutputItemDoneEvent: …Emitted when an output item is marked done.
-
item: ResponseOutputItemThe output item that was marked done.
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
output_index: intThe index of the output item that was marked done.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.done"]The type of the event. Always
response.output_item.done."response.output_item.done"
-
Response Output Message
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
Response Output Refusal
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
Response Output Text
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
Response Output Text Annotation Added Event
-
class ResponseOutputTextAnnotationAddedEvent: …Emitted when an annotation is added to output text content.
-
annotation: objectThe annotation object being added. (See annotation schema for details.)
-
annotation_index: intThe index of the annotation within the content part.
-
content_index: intThe index of the content part within the output item.
-
item_id: strThe unique identifier of the item to which the annotation is being added.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_text.annotation.added"]The type of the event. Always 'response.output_text.annotation.added'.
"response.output_text.annotation.added"
-
Response Prompt
-
class ResponsePrompt: …Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
version: Optional[str]Optional version of the prompt template.
-
Response Queued Event
-
class ResponseQueuedEvent: …Emitted when a response is queued and waiting to be processed.
-
response: ResponseThe full response object that is queued.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.queued"]The type of the event. Always 'response.queued'.
"response.queued"
-
Response Reasoning Item
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
Response Reasoning Summary Part Added Event
-
class ResponseReasoningSummaryPartAddedEvent: …Emitted when a new reasoning summary part is added.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe summary part that was added.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.added"]The type of the event. Always
response.reasoning_summary_part.added."response.reasoning_summary_part.added"
-
Response Reasoning Summary Part Done Event
-
class ResponseReasoningSummaryPartDoneEvent: …Emitted when a reasoning summary part is completed.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe completed summary part.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.done"]The type of the event. Always
response.reasoning_summary_part.done."response.reasoning_summary_part.done"
-
Response Reasoning Summary Text Delta Event
-
class ResponseReasoningSummaryTextDeltaEvent: …Emitted when a delta is added to a reasoning summary text.
-
delta: strThe text delta that was added to the summary.
-
item_id: strThe ID of the item this summary text delta is associated with.
-
output_index: intThe index of the output item this summary text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_text.delta"]The type of the event. Always
response.reasoning_summary_text.delta."response.reasoning_summary_text.delta"
-
Response Reasoning Summary Text Done Event
-
class ResponseReasoningSummaryTextDoneEvent: …Emitted when a reasoning summary text is completed.
-
item_id: strThe ID of the item this summary text is associated with.
-
output_index: intThe index of the output item this summary text is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
text: strThe full text of the completed reasoning summary.
-
type: Literal["response.reasoning_summary_text.done"]The type of the event. Always
response.reasoning_summary_text.done."response.reasoning_summary_text.done"
-
Response Reasoning Text Delta Event
-
class ResponseReasoningTextDeltaEvent: …Emitted when a delta is added to a reasoning text.
-
content_index: intThe index of the reasoning content part this delta is associated with.
-
delta: strThe text delta that was added to the reasoning content.
-
item_id: strThe ID of the item this reasoning text delta is associated with.
-
output_index: intThe index of the output item this reasoning text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.reasoning_text.delta"]The type of the event. Always
response.reasoning_text.delta."response.reasoning_text.delta"
-
Response Reasoning Text Done Event
-
class ResponseReasoningTextDoneEvent: …Emitted when a reasoning text is completed.
-
content_index: intThe index of the reasoning content part.
-
item_id: strThe ID of the item this reasoning text is associated with.
-
output_index: intThe index of the output item this reasoning text is associated with.
-
sequence_number: intThe sequence number of this event.
-
text: strThe full text of the completed reasoning content.
-
type: Literal["response.reasoning_text.done"]The type of the event. Always
response.reasoning_text.done."response.reasoning_text.done"
-
Response Refusal Delta Event
-
class ResponseRefusalDeltaEvent: …Emitted when there is a partial refusal text.
-
content_index: intThe index of the content part that the refusal text is added to.
-
delta: strThe refusal text that is added.
-
item_id: strThe ID of the output item that the refusal text is added to.
-
output_index: intThe index of the output item that the refusal text is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.delta"]The type of the event. Always
response.refusal.delta."response.refusal.delta"
-
Response Refusal Done Event
-
class ResponseRefusalDoneEvent: …Emitted when refusal text is finalized.
-
content_index: intThe index of the content part that the refusal text is finalized.
-
item_id: strThe ID of the output item that the refusal text is finalized.
-
output_index: intThe index of the output item that the refusal text is finalized.
-
refusal: strThe refusal text that is finalized.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.done"]The type of the event. Always
response.refusal.done."response.refusal.done"
-
Response Status
-
Literal["completed", "failed", "in_progress", 3 more]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
Response Stream Event
-
ResponseStreamEventEmitted when there is a partial audio response.
-
class ResponseAudioDeltaEvent: …Emitted when there is a partial audio response.
-
delta: strA chunk of Base64 encoded response audio bytes.
-
sequence_number: intA sequence number for this chunk of the stream response.
-
type: Literal["response.audio.delta"]The type of the event. Always
response.audio.delta."response.audio.delta"
-
-
class ResponseAudioDoneEvent: …Emitted when the audio response is complete.
-
sequence_number: intThe sequence number of the delta.
-
type: Literal["response.audio.done"]The type of the event. Always
response.audio.done."response.audio.done"
-
-
class ResponseAudioTranscriptDeltaEvent: …Emitted when there is a partial transcript of audio.
-
delta: strThe partial transcript of the audio response.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.delta"]The type of the event. Always
response.audio.transcript.delta."response.audio.transcript.delta"
-
-
class ResponseAudioTranscriptDoneEvent: …Emitted when the full audio transcript is completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.done"]The type of the event. Always
response.audio.transcript.done."response.audio.transcript.done"
-
-
class ResponseCodeInterpreterCallCodeDeltaEvent: …Emitted when a partial code snippet is streamed by the code interpreter.
-
delta: strThe partial code snippet being streamed by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is being streamed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.delta"]The type of the event. Always
response.code_interpreter_call_code.delta."response.code_interpreter_call_code.delta"
-
-
class ResponseCodeInterpreterCallCodeDoneEvent: …Emitted when the code snippet is finalized by the code interpreter.
-
code: strThe final code snippet output by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is finalized.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.done"]The type of the event. Always
response.code_interpreter_call_code.done."response.code_interpreter_call_code.done"
-
-
class ResponseCodeInterpreterCallCompletedEvent: …Emitted when the code interpreter call is completed.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is completed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.completed"]The type of the event. Always
response.code_interpreter_call.completed."response.code_interpreter_call.completed"
-
-
class ResponseCodeInterpreterCallInProgressEvent: …Emitted when a code interpreter call is in progress.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is in progress.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.in_progress"]The type of the event. Always
response.code_interpreter_call.in_progress."response.code_interpreter_call.in_progress"
-
-
class ResponseCodeInterpreterCallInterpretingEvent: …Emitted when the code interpreter is actively interpreting the code snippet.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter is interpreting code.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.interpreting"]The type of the event. Always
response.code_interpreter_call.interpreting."response.code_interpreter_call.interpreting"
-
-
class ResponseCompletedEvent: …Emitted when the model response is complete.
-
response: ResponseProperties of the completed response.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.completed"]The type of the event. Always
response.completed."response.completed"
-
-
class ResponseContentPartAddedEvent: …Emitted when a new content part is added.
-
content_index: intThe index of the content part that was added.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that was added.
-
class ResponseOutputText: …A text output from the model.
-
class ResponseOutputRefusal: …A refusal from the model.
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.added"]The type of the event. Always
response.content_part.added."response.content_part.added"
-
-
class ResponseContentPartDoneEvent: …Emitted when a content part is done.
-
content_index: intThe index of the content part that is done.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that is done.
-
class ResponseOutputText: …A text output from the model.
-
class ResponseOutputRefusal: …A refusal from the model.
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.done"]The type of the event. Always
response.content_part.done."response.content_part.done"
-
-
class ResponseCreatedEvent: …An event that is emitted when a response is created.
-
response: ResponseThe response that was created.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.created"]The type of the event. Always
response.created."response.created"
-
-
class ResponseErrorEvent: …Emitted when an error occurs.
-
code: Optional[str]The error code.
-
message: strThe error message.
-
param: Optional[str]The error parameter.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["error"]The type of the event. Always
error."error"
-
-
class ResponseFileSearchCallCompletedEvent: …Emitted when a file search call is completed (results found).
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.completed"]The type of the event. Always
response.file_search_call.completed."response.file_search_call.completed"
-
-
class ResponseFileSearchCallInProgressEvent: …Emitted when a file search call is initiated.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.in_progress"]The type of the event. Always
response.file_search_call.in_progress."response.file_search_call.in_progress"
-
-
class ResponseFileSearchCallSearchingEvent: …Emitted when a file search is currently searching.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is searching.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.searching"]The type of the event. Always
response.file_search_call.searching."response.file_search_call.searching"
-
-
class ResponseFunctionCallArgumentsDeltaEvent: …Emitted when there is a partial function-call arguments delta.
-
delta: strThe function-call arguments delta that is added.
-
item_id: strThe ID of the output item that the function-call arguments delta is added to.
-
output_index: intThe index of the output item that the function-call arguments delta is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.delta"]The type of the event. Always
response.function_call_arguments.delta."response.function_call_arguments.delta"
-
-
class ResponseFunctionCallArgumentsDoneEvent: …Emitted when function-call arguments are finalized.
-
arguments: strThe function-call arguments.
-
item_id: strThe ID of the item.
-
name: strThe name of the function that was called.
-
output_index: intThe index of the output item.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.done"]"response.function_call_arguments.done"
-
-
class ResponseInProgressEvent: …Emitted when the response is in progress.
-
response: ResponseThe response that is in progress.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.in_progress"]The type of the event. Always
response.in_progress."response.in_progress"
-
-
class ResponseFailedEvent: …An event that is emitted when a response fails.
-
response: ResponseThe response that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.failed"]The type of the event. Always
response.failed."response.failed"
-
-
class ResponseIncompleteEvent: …An event that is emitted when a response finishes as incomplete.
-
response: ResponseThe response that was incomplete.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.incomplete"]The type of the event. Always
response.incomplete."response.incomplete"
-
-
class ResponseOutputItemAddedEvent: …Emitted when a new output item is added.
-
item: ResponseOutputItemThe output item that was added.
-
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: … -
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: … -
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: … -
class ResponseToolSearchOutputItem: … -
class AdditionalTools: … -
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI. -
class ImageGenerationCall: …An image generation request made by the model.
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
class McpCall: …An invocation of a tool on an MCP server.
-
class McpListTools: …A list of tools available on an MCP server.
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
class McpApprovalResponse: …A response to an MCP approval request.
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
-
output_index: intThe index of the output item that was added.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.added"]The type of the event. Always
response.output_item.added."response.output_item.added"
-
-
class ResponseOutputItemDoneEvent: …Emitted when an output item is marked done.
-
item: ResponseOutputItemThe output item that was marked done.
-
output_index: intThe index of the output item that was marked done.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.done"]The type of the event. Always
response.output_item.done."response.output_item.done"
-
-
class ResponseReasoningSummaryPartAddedEvent: …Emitted when a new reasoning summary part is added.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe summary part that was added.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.added"]The type of the event. Always
response.reasoning_summary_part.added."response.reasoning_summary_part.added"
-
-
class ResponseReasoningSummaryPartDoneEvent: …Emitted when a reasoning summary part is completed.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe completed summary part.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.done"]The type of the event. Always
response.reasoning_summary_part.done."response.reasoning_summary_part.done"
-
-
class ResponseReasoningSummaryTextDeltaEvent: …Emitted when a delta is added to a reasoning summary text.
-
delta: strThe text delta that was added to the summary.
-
item_id: strThe ID of the item this summary text delta is associated with.
-
output_index: intThe index of the output item this summary text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_text.delta"]The type of the event. Always
response.reasoning_summary_text.delta."response.reasoning_summary_text.delta"
-
-
class ResponseReasoningSummaryTextDoneEvent: …Emitted when a reasoning summary text is completed.
-
item_id: strThe ID of the item this summary text is associated with.
-
output_index: intThe index of the output item this summary text is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
text: strThe full text of the completed reasoning summary.
-
type: Literal["response.reasoning_summary_text.done"]The type of the event. Always
response.reasoning_summary_text.done."response.reasoning_summary_text.done"
-
-
class ResponseReasoningTextDeltaEvent: …Emitted when a delta is added to a reasoning text.
-
content_index: intThe index of the reasoning content part this delta is associated with.
-
delta: strThe text delta that was added to the reasoning content.
-
item_id: strThe ID of the item this reasoning text delta is associated with.
-
output_index: intThe index of the output item this reasoning text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.reasoning_text.delta"]The type of the event. Always
response.reasoning_text.delta."response.reasoning_text.delta"
-
-
class ResponseReasoningTextDoneEvent: …Emitted when a reasoning text is completed.
-
content_index: intThe index of the reasoning content part.
-
item_id: strThe ID of the item this reasoning text is associated with.
-
output_index: intThe index of the output item this reasoning text is associated with.
-
sequence_number: intThe sequence number of this event.
-
text: strThe full text of the completed reasoning content.
-
type: Literal["response.reasoning_text.done"]The type of the event. Always
response.reasoning_text.done."response.reasoning_text.done"
-
-
class ResponseRefusalDeltaEvent: …Emitted when there is a partial refusal text.
-
content_index: intThe index of the content part that the refusal text is added to.
-
delta: strThe refusal text that is added.
-
item_id: strThe ID of the output item that the refusal text is added to.
-
output_index: intThe index of the output item that the refusal text is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.delta"]The type of the event. Always
response.refusal.delta."response.refusal.delta"
-
-
class ResponseRefusalDoneEvent: …Emitted when refusal text is finalized.
-
content_index: intThe index of the content part that the refusal text is finalized.
-
item_id: strThe ID of the output item that the refusal text is finalized.
-
output_index: intThe index of the output item that the refusal text is finalized.
-
refusal: strThe refusal text that is finalized.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.done"]The type of the event. Always
response.refusal.done."response.refusal.done"
-
-
class ResponseTextDeltaEvent: …Emitted when there is an additional text delta.
-
content_index: intThe index of the content part that the text delta was added to.
-
delta: strThe text delta that was added.
-
item_id: strThe ID of the output item that the text delta was added to.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text delta was added to.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.output_text.delta"]The type of the event. Always
response.output_text.delta."response.output_text.delta"
-
-
class ResponseTextDoneEvent: …Emitted when text content is finalized.
-
content_index: intThe index of the content part that the text content is finalized.
-
item_id: strThe ID of the output item that the text content is finalized.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text content is finalized.
-
sequence_number: intThe sequence number for this event.
-
text: strThe text content that is finalized.
-
type: Literal["response.output_text.done"]The type of the event. Always
response.output_text.done."response.output_text.done"
-
-
class ResponseWebSearchCallCompletedEvent: …Emitted when a web search call is completed.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.completed"]The type of the event. Always
response.web_search_call.completed."response.web_search_call.completed"
-
-
class ResponseWebSearchCallInProgressEvent: …Emitted when a web search call is initiated.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.in_progress"]The type of the event. Always
response.web_search_call.in_progress."response.web_search_call.in_progress"
-
-
class ResponseWebSearchCallSearchingEvent: …Emitted when a web search call is executing.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.searching"]The type of the event. Always
response.web_search_call.searching."response.web_search_call.searching"
-
-
class ResponseImageGenCallCompletedEvent: …Emitted when an image generation tool call has completed and the final image is available.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.image_generation_call.completed"]The type of the event. Always 'response.image_generation_call.completed'.
"response.image_generation_call.completed"
-
-
class ResponseImageGenCallGeneratingEvent: …Emitted when an image generation tool call is actively generating an image (intermediate state).
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.generating"]The type of the event. Always 'response.image_generation_call.generating'.
"response.image_generation_call.generating"
-
-
class ResponseImageGenCallInProgressEvent: …Emitted when an image generation tool call is in progress.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.in_progress"]The type of the event. Always 'response.image_generation_call.in_progress'.
"response.image_generation_call.in_progress"
-
-
class ResponseImageGenCallPartialImageEvent: …Emitted when a partial image is available during image generation streaming.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
partial_image_b64: strBase64-encoded partial image data, suitable for rendering as an image.
-
partial_image_index: int0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.partial_image"]The type of the event. Always 'response.image_generation_call.partial_image'.
"response.image_generation_call.partial_image"
-
-
class ResponseMcpCallArgumentsDeltaEvent: …Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
-
delta: strA JSON string containing the partial update to the arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.delta"]The type of the event. Always 'response.mcp_call_arguments.delta'.
"response.mcp_call_arguments.delta"
-
-
class ResponseMcpCallArgumentsDoneEvent: …Emitted when the arguments for an MCP tool call are finalized.
-
arguments: strA JSON string containing the finalized arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.done"]The type of the event. Always 'response.mcp_call_arguments.done'.
"response.mcp_call_arguments.done"
-
-
class ResponseMcpCallCompletedEvent: …Emitted when an MCP tool call has completed successfully.
-
item_id: strThe ID of the MCP tool call item that completed.
-
output_index: intThe index of the output item that completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.completed"]The type of the event. Always 'response.mcp_call.completed'.
"response.mcp_call.completed"
-
-
class ResponseMcpCallFailedEvent: …Emitted when an MCP tool call has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.failed"]The type of the event. Always 'response.mcp_call.failed'.
"response.mcp_call.failed"
-
-
class ResponseMcpCallInProgressEvent: …Emitted when an MCP tool call is in progress.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.in_progress"]The type of the event. Always 'response.mcp_call.in_progress'.
"response.mcp_call.in_progress"
-
-
class ResponseMcpListToolsCompletedEvent: …Emitted when the list of available MCP tools has been successfully retrieved.
-
item_id: strThe ID of the MCP tool call item that produced this output.
-
output_index: intThe index of the output item that was processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.completed"]The type of the event. Always 'response.mcp_list_tools.completed'.
"response.mcp_list_tools.completed"
-
-
class ResponseMcpListToolsFailedEvent: …Emitted when the attempt to list available MCP tools has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.failed"]The type of the event. Always 'response.mcp_list_tools.failed'.
"response.mcp_list_tools.failed"
-
-
class ResponseMcpListToolsInProgressEvent: …Emitted when the system is in the process of retrieving the list of available MCP tools.
-
item_id: strThe ID of the MCP tool call item that is being processed.
-
output_index: intThe index of the output item that is being processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.in_progress"]The type of the event. Always 'response.mcp_list_tools.in_progress'.
"response.mcp_list_tools.in_progress"
-
-
class ResponseOutputTextAnnotationAddedEvent: …Emitted when an annotation is added to output text content.
-
annotation: objectThe annotation object being added. (See annotation schema for details.)
-
annotation_index: intThe index of the annotation within the content part.
-
content_index: intThe index of the content part within the output item.
-
item_id: strThe unique identifier of the item to which the annotation is being added.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_text.annotation.added"]The type of the event. Always 'response.output_text.annotation.added'.
"response.output_text.annotation.added"
-
-
class ResponseQueuedEvent: …Emitted when a response is queued and waiting to be processed.
-
response: ResponseThe full response object that is queued.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.queued"]The type of the event. Always 'response.queued'.
"response.queued"
-
-
class ResponseCustomToolCallInputDeltaEvent: …Event representing a delta (partial update) to the input of a custom tool call.
-
delta: strThe incremental input data (delta) for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this delta applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.delta"]The event type identifier.
"response.custom_tool_call_input.delta"
-
-
class ResponseCustomToolCallInputDoneEvent: …Event indicating that input for a custom tool call is complete.
-
input: strThe complete input data for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this event applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.done"]The event type identifier.
"response.custom_tool_call_input.done"
-
-
Response Text Config
-
class ResponseTextConfig: …Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
Response Text Delta Event
-
class ResponseTextDeltaEvent: …Emitted when there is an additional text delta.
-
content_index: intThe index of the content part that the text delta was added to.
-
delta: strThe text delta that was added.
-
item_id: strThe ID of the output item that the text delta was added to.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text delta was added to.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.output_text.delta"]The type of the event. Always
response.output_text.delta."response.output_text.delta"
-
Response Text Done Event
-
class ResponseTextDoneEvent: …Emitted when text content is finalized.
-
content_index: intThe index of the content part that the text content is finalized.
-
item_id: strThe ID of the output item that the text content is finalized.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text content is finalized.
-
sequence_number: intThe sequence number for this event.
-
text: strThe text content that is finalized.
-
type: Literal["response.output_text.done"]The type of the event. Always
response.output_text.done."response.output_text.done"
-
Response Tool Search Call
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Tool Search Output Item
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
Response Tool Search Output Item Param
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
Response Usage
-
class ResponseUsage: …Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
Response Web Search Call Completed Event
-
class ResponseWebSearchCallCompletedEvent: …Emitted when a web search call is completed.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.completed"]The type of the event. Always
response.web_search_call.completed."response.web_search_call.completed"
-
Response Web Search Call In Progress Event
-
class ResponseWebSearchCallInProgressEvent: …Emitted when a web search call is initiated.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.in_progress"]The type of the event. Always
response.web_search_call.in_progress."response.web_search_call.in_progress"
-
Response Web Search Call Searching Event
-
class ResponseWebSearchCallSearchingEvent: …Emitted when a web search call is executing.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.searching"]The type of the event. Always
response.web_search_call.searching."response.web_search_call.searching"
-
Responses Client Event
-
class ResponsesClientEvent: …-
type: Literal["response.create"]The type of the client event. Always
response.create."response.create"
-
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
context_management: Optional[List[ContextManagement]]Context management configuration for this request.
-
type: strThe context management entry type. Currently only 'compaction' is supported.
-
compact_threshold: Optional[int]Token threshold at which compaction should be triggered for this entry.
-
-
conversation: Optional[Conversation]The conversation that this response belongs to. Items from this conversation are prepended to
input_itemsfor this response request. Input items and output items from this response are automatically added to this conversation after this response completes.-
strThe unique ID of the conversation.
-
class ResponseConversationParam: …The conversation that this response belongs to.
-
id: strThe unique ID of the conversation.
-
-
-
include: Optional[List[ResponseIncludable]]Specify additional output data to include in the model response. Currently supported values are:
-
web_search_call.action.sources: Include the sources of the web search tool call. -
code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items. -
computer_call_output.output.image_url: Include image urls from the computer call output. -
file_search_call.results: Include the search results of the file search tool call. -
message.input_image.image_url: Include image urls from the input message. -
message.output_text.logprobs: Include logprobs with assistant messages. -
reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when thestoreparameter is set tofalse, or when an organization is enrolled in the zero data retention program). -
"file_search_call.results" -
"web_search_call.results" -
"web_search_call.action.sources" -
"message.input_image.image_url" -
"computer_call_output.output.image_url" -
"code_interpreter_call.outputs" -
"reasoning.encrypted_content" -
"message.output_text.logprobs"
-
-
input: Optional[Union[str, ResponseInput, null]]Text, image, or file inputs to the model, used to generate a response.
Learn more:
-
strA text input to the model, equivalent to a text input with the
userrole. -
List[ResponseInputItem]-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
instructions: Optional[str]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: Optional[ResponsesModel]Model ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
moderation: Optional[Moderation]Configuration for running moderation on the input and output of this response.
-
model: strThe moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.
-
-
parallel_tool_calls: Optional[bool]Whether to allow the model to run tool calls in parallel.
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
store: Optional[bool]Whether to store the generated model response for later retrieval via API.
-
stream: Optional[bool]If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
-
stream_options: Optional[StreamOptions]Options for streaming responses. Only set this when you set
stream: true.-
include_obfuscation: Optional[bool]When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an
obfuscationfield on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can setinclude_obfuscationto false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
-
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
tool_choice: Optional[ToolChoice]How the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: Optional[List[Tool]]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
Responses Server Event
-
ResponsesServerEventServer events emitted by the Responses WebSocket server.
-
class ResponseAudioDeltaEvent: …Emitted when there is a partial audio response.
-
delta: strA chunk of Base64 encoded response audio bytes.
-
sequence_number: intA sequence number for this chunk of the stream response.
-
type: Literal["response.audio.delta"]The type of the event. Always
response.audio.delta."response.audio.delta"
-
-
class ResponseAudioDoneEvent: …Emitted when the audio response is complete.
-
sequence_number: intThe sequence number of the delta.
-
type: Literal["response.audio.done"]The type of the event. Always
response.audio.done."response.audio.done"
-
-
class ResponseAudioTranscriptDeltaEvent: …Emitted when there is a partial transcript of audio.
-
delta: strThe partial transcript of the audio response.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.delta"]The type of the event. Always
response.audio.transcript.delta."response.audio.transcript.delta"
-
-
class ResponseAudioTranscriptDoneEvent: …Emitted when the full audio transcript is completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.audio.transcript.done"]The type of the event. Always
response.audio.transcript.done."response.audio.transcript.done"
-
-
class ResponseCodeInterpreterCallCodeDeltaEvent: …Emitted when a partial code snippet is streamed by the code interpreter.
-
delta: strThe partial code snippet being streamed by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is being streamed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.delta"]The type of the event. Always
response.code_interpreter_call_code.delta."response.code_interpreter_call_code.delta"
-
-
class ResponseCodeInterpreterCallCodeDoneEvent: …Emitted when the code snippet is finalized by the code interpreter.
-
code: strThe final code snippet output by the code interpreter.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code is finalized.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call_code.done"]The type of the event. Always
response.code_interpreter_call_code.done."response.code_interpreter_call_code.done"
-
-
class ResponseCodeInterpreterCallCompletedEvent: …Emitted when the code interpreter call is completed.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is completed.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.completed"]The type of the event. Always
response.code_interpreter_call.completed."response.code_interpreter_call.completed"
-
-
class ResponseCodeInterpreterCallInProgressEvent: …Emitted when a code interpreter call is in progress.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter call is in progress.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.in_progress"]The type of the event. Always
response.code_interpreter_call.in_progress."response.code_interpreter_call.in_progress"
-
-
class ResponseCodeInterpreterCallInterpretingEvent: …Emitted when the code interpreter is actively interpreting the code snippet.
-
item_id: strThe unique identifier of the code interpreter tool call item.
-
output_index: intThe index of the output item in the response for which the code interpreter is interpreting code.
-
sequence_number: intThe sequence number of this event, used to order streaming events.
-
type: Literal["response.code_interpreter_call.interpreting"]The type of the event. Always
response.code_interpreter_call.interpreting."response.code_interpreter_call.interpreting"
-
-
class ResponseCompletedEvent: …Emitted when the model response is complete.
-
response: ResponseProperties of the completed response.
-
id: strUnique identifier for this Response.
-
created_at: floatUnix timestamp (in seconds) of when this Response was created.
-
error: Optional[ResponseError]An error object returned when the model fails to generate a Response.
-
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt", 15 more]The error code for the response.
-
"server_error" -
"rate_limit_exceeded" -
"invalid_prompt" -
"vector_store_timeout" -
"invalid_image" -
"invalid_image_format" -
"invalid_base64_image" -
"invalid_image_url" -
"image_too_large" -
"image_too_small" -
"image_parse_error" -
"image_content_policy_violation" -
"invalid_image_mode" -
"image_file_too_large" -
"unsupported_image_media_type" -
"empty_image_file" -
"failed_to_download_image" -
"image_file_not_found"
-
-
message: strA human-readable description of the error.
-
-
incomplete_details: Optional[IncompleteDetails]Details about why the response is incomplete.
-
reason: Optional[Literal["max_output_tokens", "content_filter"]]The reason why the response is incomplete.
-
"max_output_tokens" -
"content_filter"
-
-
-
instructions: Union[str, List[ResponseInputItem], null]A system (or developer) message inserted into the model's context.
When using along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.-
strA text input to the model, equivalent to a text input with the
developerrole. -
List[ResponseInputItem]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
metadata: Optional[Metadata]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: ResponsesModelModel ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.-
str -
Literal["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", 75 more]-
"gpt-5.4" -
"gpt-5.4-mini" -
"gpt-5.4-nano" -
"gpt-5.4-mini-2026-03-17" -
"gpt-5.4-nano-2026-03-17" -
"gpt-5.3-chat-latest" -
"gpt-5.2" -
"gpt-5.2-2025-12-11" -
"gpt-5.2-chat-latest" -
"gpt-5.2-pro" -
"gpt-5.2-pro-2025-12-11" -
"gpt-5.1" -
"gpt-5.1-2025-11-13" -
"gpt-5.1-codex" -
"gpt-5.1-mini" -
"gpt-5.1-chat-latest" -
"gpt-5" -
"gpt-5-mini" -
"gpt-5-nano" -
"gpt-5-2025-08-07" -
"gpt-5-mini-2025-08-07" -
"gpt-5-nano-2025-08-07" -
"gpt-5-chat-latest" -
"gpt-4.1" -
"gpt-4.1-mini" -
"gpt-4.1-nano" -
"gpt-4.1-2025-04-14" -
"gpt-4.1-mini-2025-04-14" -
"gpt-4.1-nano-2025-04-14" -
"o4-mini" -
"o4-mini-2025-04-16" -
"o3" -
"o3-2025-04-16" -
"o3-mini" -
"o3-mini-2025-01-31" -
"o1" -
"o1-2024-12-17" -
"o1-preview" -
"o1-preview-2024-09-12" -
"o1-mini" -
"o1-mini-2024-09-12" -
"gpt-4o" -
"gpt-4o-2024-11-20" -
"gpt-4o-2024-08-06" -
"gpt-4o-2024-05-13" -
"gpt-4o-audio-preview" -
"gpt-4o-audio-preview-2024-10-01" -
"gpt-4o-audio-preview-2024-12-17" -
"gpt-4o-audio-preview-2025-06-03" -
"gpt-4o-mini-audio-preview" -
"gpt-4o-mini-audio-preview-2024-12-17" -
"gpt-4o-search-preview" -
"gpt-4o-mini-search-preview" -
"gpt-4o-search-preview-2025-03-11" -
"gpt-4o-mini-search-preview-2025-03-11" -
"chatgpt-4o-latest" -
"codex-mini-latest" -
"gpt-4o-mini" -
"gpt-4o-mini-2024-07-18" -
"gpt-4-turbo" -
"gpt-4-turbo-2024-04-09" -
"gpt-4-0125-preview" -
"gpt-4-turbo-preview" -
"gpt-4-1106-preview" -
"gpt-4-vision-preview" -
"gpt-4" -
"gpt-4-0314" -
"gpt-4-0613" -
"gpt-4-32k" -
"gpt-4-32k-0314" -
"gpt-4-32k-0613" -
"gpt-3.5-turbo" -
"gpt-3.5-turbo-16k" -
"gpt-3.5-turbo-0301" -
"gpt-3.5-turbo-0613" -
"gpt-3.5-turbo-1106" -
"gpt-3.5-turbo-0125" -
"gpt-3.5-turbo-16k-0613"
-
-
Literal["o1-pro", "o1-pro-2025-03-19", "o3-pro", 11 more]-
"o1-pro" -
"o1-pro-2025-03-19" -
"o3-pro" -
"o3-pro-2025-06-10" -
"o3-deep-research" -
"o3-deep-research-2025-06-26" -
"o4-mini-deep-research" -
"o4-mini-deep-research-2025-06-26" -
"computer-use-preview" -
"computer-use-preview-2025-03-11" -
"gpt-5-codex" -
"gpt-5-pro" -
"gpt-5-pro-2025-10-06" -
"gpt-5.1-codex-max"
-
-
-
object: Literal["response"]The object type of this resource - always set to
response."response"
-
output: List[ResponseOutputItem]An array of content items generated by the model.
-
The length and order of items in the
outputarray is dependent on the model's response. -
Rather than accessing the first item in the
outputarray and assuming it's anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs. -
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
parallel_tool_calls: boolWhether to allow the model to run tool calls in parallel.
-
temperature: Optional[float]What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or
top_pbut not both. -
tool_choice: ToolChoiceHow the model should select which tool (or tools) to use when generating a response. See the
toolsparameter to see how to specify which tools the model can call.-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: List[Tool]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.We support the following categories of tools:
-
Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
-
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
-
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
top_p: Optional[float]An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or
temperaturebut not both. -
background: Optional[bool]Whether to run the model response in the background. Learn more.
-
completed_at: Optional[float]Unix timestamp (in seconds) of when this Response was completed. Only present when the status is
completed. -
conversation: Optional[Conversation]The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
-
id: strThe unique ID of the conversation that this response was associated with.
-
-
max_output_tokens: Optional[int]An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
-
max_tool_calls: Optional[int]The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
-
moderation: Optional[Moderation]Moderation results for the response input and output, if moderated completions were requested.
-
input: ModerationInputModeration for the response input.
-
class ModerationInputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationInputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
output: ModerationOutputModeration for the response output.
-
class ModerationOutputModerationResult: …A moderation result produced for the response input or output.
-
categories: Dict[str, bool]A dictionary of moderation categories to booleans, True if the input is flagged under this category.
-
category_applied_input_types: Dict[str, List[Literal["text", "image"]]]Which modalities of input are reflected by the score for each category.
-
"text" -
"image"
-
-
category_scores: Dict[str, float]A dictionary of moderation categories to scores.
-
flagged: boolA boolean indicating whether the content was flagged by any category.
-
model: strThe moderation model that produced this result.
-
type: Literal["moderation_result"]The object type, which was always
moderation_resultfor successful moderation results."moderation_result"
-
-
class ModerationOutputError: …An error produced while attempting moderation for the response input or output.
-
code: strThe error code.
-
message: strThe error message.
-
type: Literal["error"]The object type, which was always
errorfor moderation failures."error"
-
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
prompt: Optional[ResponsePrompt]Reference to a prompt template and its variables. Learn more.
-
id: strThe unique identifier of the prompt template to use.
-
variables: Optional[Dict[str, Variables]]Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
-
str -
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
version: Optional[str]Optional version of the prompt template.
-
-
prompt_cache_key: Optional[str]Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the
userfield. Learn more. -
prompt_cache_retention: Optional[Literal["in_memory", "24h"]]The retention policy for the prompt cache. Set to
24hto enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. Forgpt-5.5,gpt-5.5-pro, and future models, only24his supported.For older models that support both
in_memoryand24h, the default depends on your organization's data retention policy:-
Organizations without ZDR enabled default to
24h. -
Organizations with ZDR enabled default to
in_memorywhenprompt_cache_retentionis not specified. -
"in_memory" -
"24h"
-
-
reasoning: Optional[Reasoning]gpt-5 and o-series models only
Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
safety_identifier: Optional[str]A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
-
service_tier: Optional[Literal["auto", "default", "flex", 2 more]]Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
- If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
- If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the
service_tierparameter is set, the response body will include theservice_tiervalue based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.-
"auto" -
"default" -
"flex" -
"scale" -
"priority"
-
status: Optional[ResponseStatus]The status of the response generation. One of
completed,failed,in_progress,cancelled,queued, orincomplete.-
"completed" -
"failed" -
"in_progress" -
"cancelled" -
"queued" -
"incomplete"
-
-
text: Optional[ResponseTextConfig]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfig]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
top_logprobs: Optional[int]An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response.
-
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -
disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. -
"auto" -
"disabled"
-
-
usage: Optional[ResponseUsage]Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
-
input_tokens: intThe number of input tokens.
-
input_tokens_details: InputTokensDetailsA detailed breakdown of the input tokens.
-
cached_tokens: intThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: intThe number of output tokens.
-
output_tokens_details: OutputTokensDetailsA detailed breakdown of the output tokens.
-
reasoning_tokens: intThe number of reasoning tokens.
-
-
total_tokens: intThe total number of tokens used.
-
-
user: Optional[str]This field is being replaced by
safety_identifierandprompt_cache_key. Useprompt_cache_keyinstead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
-
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.completed"]The type of the event. Always
response.completed."response.completed"
-
-
class ResponseContentPartAddedEvent: …Emitted when a new content part is added.
-
content_index: intThe index of the content part that was added.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that was added.
-
class ResponseOutputText: …A text output from the model.
-
class ResponseOutputRefusal: …A refusal from the model.
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.added"]The type of the event. Always
response.content_part.added."response.content_part.added"
-
-
class ResponseContentPartDoneEvent: …Emitted when a content part is done.
-
content_index: intThe index of the content part that is done.
-
item_id: strThe ID of the output item that the content part was added to.
-
output_index: intThe index of the output item that the content part was added to.
-
part: PartThe content part that is done.
-
class ResponseOutputText: …A text output from the model.
-
class ResponseOutputRefusal: …A refusal from the model.
-
class PartReasoningText: …Reasoning text from the model.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.content_part.done"]The type of the event. Always
response.content_part.done."response.content_part.done"
-
-
class ResponseCreatedEvent: …An event that is emitted when a response is created.
-
response: ResponseThe response that was created.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.created"]The type of the event. Always
response.created."response.created"
-
-
class ResponseErrorEvent: …Emitted when an error occurs.
-
code: Optional[str]The error code.
-
message: strThe error message.
-
param: Optional[str]The error parameter.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["error"]The type of the event. Always
error."error"
-
-
class ResponseFileSearchCallCompletedEvent: …Emitted when a file search call is completed (results found).
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.completed"]The type of the event. Always
response.file_search_call.completed."response.file_search_call.completed"
-
-
class ResponseFileSearchCallInProgressEvent: …Emitted when a file search call is initiated.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is initiated.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.in_progress"]The type of the event. Always
response.file_search_call.in_progress."response.file_search_call.in_progress"
-
-
class ResponseFileSearchCallSearchingEvent: …Emitted when a file search is currently searching.
-
item_id: strThe ID of the output item that the file search call is initiated.
-
output_index: intThe index of the output item that the file search call is searching.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.file_search_call.searching"]The type of the event. Always
response.file_search_call.searching."response.file_search_call.searching"
-
-
class ResponseFunctionCallArgumentsDeltaEvent: …Emitted when there is a partial function-call arguments delta.
-
delta: strThe function-call arguments delta that is added.
-
item_id: strThe ID of the output item that the function-call arguments delta is added to.
-
output_index: intThe index of the output item that the function-call arguments delta is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.delta"]The type of the event. Always
response.function_call_arguments.delta."response.function_call_arguments.delta"
-
-
class ResponseFunctionCallArgumentsDoneEvent: …Emitted when function-call arguments are finalized.
-
arguments: strThe function-call arguments.
-
item_id: strThe ID of the item.
-
name: strThe name of the function that was called.
-
output_index: intThe index of the output item.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.function_call_arguments.done"]"response.function_call_arguments.done"
-
-
class ResponseInProgressEvent: …Emitted when the response is in progress.
-
response: ResponseThe response that is in progress.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.in_progress"]The type of the event. Always
response.in_progress."response.in_progress"
-
-
class ResponseFailedEvent: …An event that is emitted when a response fails.
-
response: ResponseThe response that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.failed"]The type of the event. Always
response.failed."response.failed"
-
-
class ResponseIncompleteEvent: …An event that is emitted when a response finishes as incomplete.
-
response: ResponseThe response that was incomplete.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.incomplete"]The type of the event. Always
response.incomplete."response.incomplete"
-
-
class ResponseOutputItemAddedEvent: …Emitted when a new output item is added.
-
item: ResponseOutputItemThe output item that was added.
-
class ResponseOutputMessage: …An output message from the model.
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
class ResponseFunctionToolCallOutputItem: … -
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
class ResponseComputerToolCallOutputItem: … -
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context. -
class ResponseToolSearchCall: … -
class ResponseToolSearchOutputItem: … -
class AdditionalTools: … -
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI. -
class ImageGenerationCall: …An image generation request made by the model.
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
class McpCall: …An invocation of a tool on an MCP server.
-
class McpListTools: …A list of tools available on an MCP server.
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
class McpApprovalResponse: …A response to an MCP approval request.
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
-
output_index: intThe index of the output item that was added.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.added"]The type of the event. Always
response.output_item.added."response.output_item.added"
-
-
class ResponseOutputItemDoneEvent: …Emitted when an output item is marked done.
-
item: ResponseOutputItemThe output item that was marked done.
-
output_index: intThe index of the output item that was marked done.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_item.done"]The type of the event. Always
response.output_item.done."response.output_item.done"
-
-
class ResponseReasoningSummaryPartAddedEvent: …Emitted when a new reasoning summary part is added.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe summary part that was added.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.added"]The type of the event. Always
response.reasoning_summary_part.added."response.reasoning_summary_part.added"
-
-
class ResponseReasoningSummaryPartDoneEvent: …Emitted when a reasoning summary part is completed.
-
item_id: strThe ID of the item this summary part is associated with.
-
output_index: intThe index of the output item this summary part is associated with.
-
part: PartThe completed summary part.
-
text: strThe text of the summary part.
-
type: Literal["summary_text"]The type of the summary part. Always
summary_text."summary_text"
-
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_part.done"]The type of the event. Always
response.reasoning_summary_part.done."response.reasoning_summary_part.done"
-
-
class ResponseReasoningSummaryTextDeltaEvent: …Emitted when a delta is added to a reasoning summary text.
-
delta: strThe text delta that was added to the summary.
-
item_id: strThe ID of the item this summary text delta is associated with.
-
output_index: intThe index of the output item this summary text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
type: Literal["response.reasoning_summary_text.delta"]The type of the event. Always
response.reasoning_summary_text.delta."response.reasoning_summary_text.delta"
-
-
class ResponseReasoningSummaryTextDoneEvent: …Emitted when a reasoning summary text is completed.
-
item_id: strThe ID of the item this summary text is associated with.
-
output_index: intThe index of the output item this summary text is associated with.
-
sequence_number: intThe sequence number of this event.
-
summary_index: intThe index of the summary part within the reasoning summary.
-
text: strThe full text of the completed reasoning summary.
-
type: Literal["response.reasoning_summary_text.done"]The type of the event. Always
response.reasoning_summary_text.done."response.reasoning_summary_text.done"
-
-
class ResponseReasoningTextDeltaEvent: …Emitted when a delta is added to a reasoning text.
-
content_index: intThe index of the reasoning content part this delta is associated with.
-
delta: strThe text delta that was added to the reasoning content.
-
item_id: strThe ID of the item this reasoning text delta is associated with.
-
output_index: intThe index of the output item this reasoning text delta is associated with.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.reasoning_text.delta"]The type of the event. Always
response.reasoning_text.delta."response.reasoning_text.delta"
-
-
class ResponseReasoningTextDoneEvent: …Emitted when a reasoning text is completed.
-
content_index: intThe index of the reasoning content part.
-
item_id: strThe ID of the item this reasoning text is associated with.
-
output_index: intThe index of the output item this reasoning text is associated with.
-
sequence_number: intThe sequence number of this event.
-
text: strThe full text of the completed reasoning content.
-
type: Literal["response.reasoning_text.done"]The type of the event. Always
response.reasoning_text.done."response.reasoning_text.done"
-
-
class ResponseRefusalDeltaEvent: …Emitted when there is a partial refusal text.
-
content_index: intThe index of the content part that the refusal text is added to.
-
delta: strThe refusal text that is added.
-
item_id: strThe ID of the output item that the refusal text is added to.
-
output_index: intThe index of the output item that the refusal text is added to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.delta"]The type of the event. Always
response.refusal.delta."response.refusal.delta"
-
-
class ResponseRefusalDoneEvent: …Emitted when refusal text is finalized.
-
content_index: intThe index of the content part that the refusal text is finalized.
-
item_id: strThe ID of the output item that the refusal text is finalized.
-
output_index: intThe index of the output item that the refusal text is finalized.
-
refusal: strThe refusal text that is finalized.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.refusal.done"]The type of the event. Always
response.refusal.done."response.refusal.done"
-
-
class ResponseTextDeltaEvent: …Emitted when there is an additional text delta.
-
content_index: intThe index of the content part that the text delta was added to.
-
delta: strThe text delta that was added.
-
item_id: strThe ID of the output item that the text delta was added to.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text delta was added to.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.output_text.delta"]The type of the event. Always
response.output_text.delta."response.output_text.delta"
-
-
class ResponseTextDoneEvent: …Emitted when text content is finalized.
-
content_index: intThe index of the content part that the text content is finalized.
-
item_id: strThe ID of the output item that the text content is finalized.
-
logprobs: List[Logprob]The log probabilities of the tokens in the delta.
-
token: strA possible text token.
-
logprob: floatThe log probability of this token.
-
top_logprobs: Optional[List[LogprobTopLogprob]]The log probabilities of up to 20 of the most likely tokens.
-
token: Optional[str]A possible text token.
-
logprob: Optional[float]The log probability of this token.
-
-
-
output_index: intThe index of the output item that the text content is finalized.
-
sequence_number: intThe sequence number for this event.
-
text: strThe text content that is finalized.
-
type: Literal["response.output_text.done"]The type of the event. Always
response.output_text.done."response.output_text.done"
-
-
class ResponseWebSearchCallCompletedEvent: …Emitted when a web search call is completed.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.completed"]The type of the event. Always
response.web_search_call.completed."response.web_search_call.completed"
-
-
class ResponseWebSearchCallInProgressEvent: …Emitted when a web search call is initiated.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.in_progress"]The type of the event. Always
response.web_search_call.in_progress."response.web_search_call.in_progress"
-
-
class ResponseWebSearchCallSearchingEvent: …Emitted when a web search call is executing.
-
item_id: strUnique ID for the output item associated with the web search call.
-
output_index: intThe index of the output item that the web search call is associated with.
-
sequence_number: intThe sequence number of the web search call being processed.
-
type: Literal["response.web_search_call.searching"]The type of the event. Always
response.web_search_call.searching."response.web_search_call.searching"
-
-
class ResponseImageGenCallCompletedEvent: …Emitted when an image generation tool call has completed and the final image is available.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.image_generation_call.completed"]The type of the event. Always 'response.image_generation_call.completed'.
"response.image_generation_call.completed"
-
-
class ResponseImageGenCallGeneratingEvent: …Emitted when an image generation tool call is actively generating an image (intermediate state).
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.generating"]The type of the event. Always 'response.image_generation_call.generating'.
"response.image_generation_call.generating"
-
-
class ResponseImageGenCallInProgressEvent: …Emitted when an image generation tool call is in progress.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.in_progress"]The type of the event. Always 'response.image_generation_call.in_progress'.
"response.image_generation_call.in_progress"
-
-
class ResponseImageGenCallPartialImageEvent: …Emitted when a partial image is available during image generation streaming.
-
item_id: strThe unique identifier of the image generation item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
partial_image_b64: strBase64-encoded partial image data, suitable for rendering as an image.
-
partial_image_index: int0-based index for the partial image (backend is 1-based, but this is 0-based for the user).
-
sequence_number: intThe sequence number of the image generation item being processed.
-
type: Literal["response.image_generation_call.partial_image"]The type of the event. Always 'response.image_generation_call.partial_image'.
"response.image_generation_call.partial_image"
-
-
class ResponseMcpCallArgumentsDeltaEvent: …Emitted when there is a delta (partial update) to the arguments of an MCP tool call.
-
delta: strA JSON string containing the partial update to the arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.delta"]The type of the event. Always 'response.mcp_call_arguments.delta'.
"response.mcp_call_arguments.delta"
-
-
class ResponseMcpCallArgumentsDoneEvent: …Emitted when the arguments for an MCP tool call are finalized.
-
arguments: strA JSON string containing the finalized arguments for the MCP tool call.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call_arguments.done"]The type of the event. Always 'response.mcp_call_arguments.done'.
"response.mcp_call_arguments.done"
-
-
class ResponseMcpCallCompletedEvent: …Emitted when an MCP tool call has completed successfully.
-
item_id: strThe ID of the MCP tool call item that completed.
-
output_index: intThe index of the output item that completed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.completed"]The type of the event. Always 'response.mcp_call.completed'.
"response.mcp_call.completed"
-
-
class ResponseMcpCallFailedEvent: …Emitted when an MCP tool call has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.failed"]The type of the event. Always 'response.mcp_call.failed'.
"response.mcp_call.failed"
-
-
class ResponseMcpCallInProgressEvent: …Emitted when an MCP tool call is in progress.
-
item_id: strThe unique identifier of the MCP tool call item being processed.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_call.in_progress"]The type of the event. Always 'response.mcp_call.in_progress'.
"response.mcp_call.in_progress"
-
-
class ResponseMcpListToolsCompletedEvent: …Emitted when the list of available MCP tools has been successfully retrieved.
-
item_id: strThe ID of the MCP tool call item that produced this output.
-
output_index: intThe index of the output item that was processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.completed"]The type of the event. Always 'response.mcp_list_tools.completed'.
"response.mcp_list_tools.completed"
-
-
class ResponseMcpListToolsFailedEvent: …Emitted when the attempt to list available MCP tools has failed.
-
item_id: strThe ID of the MCP tool call item that failed.
-
output_index: intThe index of the output item that failed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.failed"]The type of the event. Always 'response.mcp_list_tools.failed'.
"response.mcp_list_tools.failed"
-
-
class ResponseMcpListToolsInProgressEvent: …Emitted when the system is in the process of retrieving the list of available MCP tools.
-
item_id: strThe ID of the MCP tool call item that is being processed.
-
output_index: intThe index of the output item that is being processed.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.mcp_list_tools.in_progress"]The type of the event. Always 'response.mcp_list_tools.in_progress'.
"response.mcp_list_tools.in_progress"
-
-
class ResponseOutputTextAnnotationAddedEvent: …Emitted when an annotation is added to output text content.
-
annotation: objectThe annotation object being added. (See annotation schema for details.)
-
annotation_index: intThe index of the annotation within the content part.
-
content_index: intThe index of the content part within the output item.
-
item_id: strThe unique identifier of the item to which the annotation is being added.
-
output_index: intThe index of the output item in the response's output array.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.output_text.annotation.added"]The type of the event. Always 'response.output_text.annotation.added'.
"response.output_text.annotation.added"
-
-
class ResponseQueuedEvent: …Emitted when a response is queued and waiting to be processed.
-
response: ResponseThe full response object that is queued.
-
sequence_number: intThe sequence number for this event.
-
type: Literal["response.queued"]The type of the event. Always 'response.queued'.
"response.queued"
-
-
class ResponseCustomToolCallInputDeltaEvent: …Event representing a delta (partial update) to the input of a custom tool call.
-
delta: strThe incremental input data (delta) for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this delta applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.delta"]The event type identifier.
"response.custom_tool_call_input.delta"
-
-
class ResponseCustomToolCallInputDoneEvent: …Event indicating that input for a custom tool call is complete.
-
input: strThe complete input data for the custom tool call.
-
item_id: strUnique identifier for the API item associated with this event.
-
output_index: intThe index of the output this event applies to.
-
sequence_number: intThe sequence number of this event.
-
type: Literal["response.custom_tool_call_input.done"]The event type identifier.
"response.custom_tool_call_input.done"
-
-
Skill Reference
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
Tool
-
ToolA tool that can be used to generate a response.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
Tool Choice Allowed
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
Tool Choice Apply Patch
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
Tool Choice Custom
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
Tool Choice Function
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
Tool Choice Mcp
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
Tool Choice Options
-
Literal["none", "auto", "required"]Controls which (if any) tool is called by the model.
nonemeans the model will not call any tool and instead generates a message.automeans the model can pick between generating a message or calling one or more tools.requiredmeans the model must call one or more tools.-
"none" -
"auto" -
"required"
-
Tool Choice Shell
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
Tool Choice Types
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
Tool Search Tool
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
Web Search Preview Tool
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
Web Search Tool
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
Input Items
List input items
responses.input_items.list(strresponse_id, InputItemListParams**kwargs) -> SyncCursorPage[ResponseItem]
get /responses/{response_id}/input_items
Returns a list of input items for a given response.
Parameters
-
response_id: str -
after: Optional[str]An item ID to list items after, used in pagination.
-
include: Optional[List[ResponseIncludable]]Additional fields to include in the response. See the
includeparameter for Response creation above for more information.-
"file_search_call.results" -
"web_search_call.results" -
"web_search_call.action.sources" -
"message.input_image.image_url" -
"computer_call_output.output.image_url" -
"code_interpreter_call.outputs" -
"reasoning.encrypted_content" -
"message.output_text.logprobs"
-
-
limit: Optional[int]A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.
-
order: Optional[Literal["asc", "desc"]]The order to return the input items in. Default is
desc.-
asc: Return the input items in ascending order. -
desc: Return the input items in descending order. -
"asc" -
"desc"
-
Returns
-
ResponseItemContent item used to generate a response.
-
class ResponseInputMessageItem: …-
id: strThe unique ID of the message input.
-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
type: Literal["message"]The type of the message input. Always set to
message."message"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCallItem: …A tool call to run a function. See the function calling guide for more information.
-
id: strThe unique ID of the function tool call.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallItem: …A call to a custom tool created by the model.
-
id: strThe unique ID of the custom tool call item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
page = client.responses.input_items.list(
response_id="response_id",
)
page = page.data[0]
print(page)
Response
{
"data": [
{
"id": "id",
"content": [
{
"text": "text",
"type": "input_text"
}
],
"role": "user",
"type": "message",
"status": "in_progress"
}
],
"first_id": "first_id",
"has_more": true,
"last_id": "last_id",
"object": "list"
}
Example
from openai import OpenAI
client = OpenAI()
response = client.responses.input_items.list("resp_123")
print(response.data)
Response
{
"object": "list",
"data": [
{
"id": "msg_abc123",
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "Tell me a three sentence bedtime story about a unicorn."
}
]
}
],
"first_id": "msg_abc123",
"last_id": "msg_abc123",
"has_more": false
}
Domain Types
Response Item List
-
class ResponseItemList: …A list of Response items.
-
data: List[ResponseItem]A list of items used to generate this response.
-
class ResponseInputMessageItem: …-
id: strThe unique ID of the message input.
-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
type: Literal["message"]The type of the message input. Always set to
message."message"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ResponseComputerToolCallOutputItem: …-
id: strThe unique ID of the computer call tool output.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
status: Literal["completed", "incomplete", "failed", "in_progress"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"completed" -
"incomplete" -
"failed" -
"in_progress"
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
acknowledged_safety_checks: Optional[List[AcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCallItem: …A tool call to run a function. See the function calling guide for more information.
-
id: strThe unique ID of the function tool call.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseFunctionToolCallOutputItem: …-
id: strThe unique ID of the function call tool output.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, List[OutputOutputContentList]]The output from the function call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the function call.
-
List[OutputOutputContentList]Text, image, or file output of the function call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchCall: …-
id: strThe unique ID of the tool search call item.
-
arguments: objectArguments used for the tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search call item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["tool_search_call"]The type of the item. Always
tool_search_call."tool_search_call"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseToolSearchOutputItem: …-
id: strThe unique ID of the tool search output item.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Literal["server", "client"]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the tool search output item that was recorded.
-
"in_progress" -
"completed" -
"incomplete"
-
-
tools: List[Tool]The loaded tool definitions returned by tool search.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The type of the item. Always
tool_search_output."tool_search_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class AdditionalTools: …-
id: strThe unique ID of the additional tools item.
-
role: Literal["unknown", "user", "assistant", 5 more]The role that provided the additional tools.
-
"unknown" -
"user" -
"assistant" -
"system" -
"critic" -
"discriminator" -
"developer" -
"tool"
-
-
tools: List[Tool]The additional tool definitions made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The type of the item. Always
additional_tools."additional_tools"
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItem: …A compaction item generated by the
v1/responses/compactAPI.-
id: strThe unique ID of the compaction item.
-
encrypted_content: strThe encrypted content that was produced by compaction.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionShellToolCall: …A tool call that executes one or more shell commands in a managed environment.
-
id: strThe unique ID of the shell tool call. Populated when this item is returned via API.
-
action: ActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str] -
max_output_length: Optional[int]Optional maximum number of characters to return from each command.
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the commands.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
environment: Optional[Environment]Represents the use of a local environment to perform shell actions.
-
class ResponseLocalEnvironment: …Represents the use of a local environment to perform shell actions.
-
type: Literal["local"]The environment type. Always
local."local"
-
-
class ResponseContainerReference: …Represents a container created with /v1/containers.
-
container_id: str -
type: Literal["container_reference"]The environment type. Always
container_reference."container_reference"
-
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseFunctionShellToolCallOutput: …The output of a shell tool call that was emitted.
-
id: strThe unique ID of the shell call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
max_output_length: Optional[int]The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
-
output: List[Output]An array of shell call output contents
-
outcome: OutputOutcomeRepresents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.
-
class OutputOutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutputOutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intExit code from the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strThe standard error output that was captured.
-
stdout: strThe standard output that was captured.
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the shell call output. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["shell_call_output"]The type of the shell call output. Always
shell_call_output."shell_call_output"
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseApplyPatchToolCall: …A tool call that applies file diffs by creating, deleting, or updating files.
-
id: strThe unique ID of the apply patch tool call. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: OperationOne of the create_file, delete_file, or update_file operations applied via apply_patch.
-
class OperationCreateFile: …Instruction describing how to create a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to create.
-
type: Literal["create_file"]Create a new file with the provided diff.
"create_file"
-
-
class OperationDeleteFile: …Instruction describing how to delete a file via the apply_patch tool.
-
path: strPath of the file to delete.
-
type: Literal["delete_file"]Delete the specified file.
"delete_file"
-
-
class OperationUpdateFile: …Instruction describing how to update a file via the apply_patch tool.
-
diff: strDiff to apply.
-
path: strPath of the file to update.
-
type: Literal["update_file"]Update an existing file with the provided diff.
"update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
created_by: Optional[str]The ID of the entity that created this tool call.
-
-
class ResponseApplyPatchToolCallOutput: …The output emitted by an apply patch tool call.
-
id: strThe unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
created_by: Optional[str]The ID of the entity that created this tool call output.
-
output: Optional[str]Optional textual output returned by the apply patch tool.
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
id: strThe unique ID of the approval response
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallItem: …A call to a custom tool created by the model.
-
id: strThe unique ID of the custom tool call item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
class ResponseCustomToolCallOutputItem: …The output of a custom tool call from your code, being sent back to the model.
-
id: strThe unique ID of the custom tool call output item.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
created_by: Optional[str]The identifier of the actor that created the item.
-
-
-
first_id: strThe ID of the first item in the list.
-
has_more: boolWhether there are more items available.
-
last_id: strThe ID of the last item in the list.
-
object: Literal["list"]The type of object returned, must be
list."list"
-
Input Tokens
Get input token counts
responses.input_tokens.count(InputTokenCountParams**kwargs) -> InputTokenCountResponse
post /responses/input_tokens
Returns input token counts of the request.
Returns an object with object set to response.input_tokens and an input_tokens count.
Parameters
-
conversation: Optional[Conversation]The conversation that this response belongs to. Items from this conversation are prepended to
input_itemsfor this response request. Input items and output items from this response are automatically added to this conversation after this response completes.-
strThe unique ID of the conversation.
-
class ResponseConversationParam: …The conversation that this response belongs to.
-
id: strThe unique ID of the conversation.
-
-
-
input: Optional[Union[str, Iterable[ResponseInputItemParam], null]]Text, image, or file inputs to the model, used to generate a response
-
strA text input to the model, equivalent to a text input with the
userrole. -
Iterable[ResponseInputItemParam]A list of one or many input items to the model, containing different content types.
-
class EasyInputMessage: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole. Messages with theassistantrole are presumed to have been generated by the model in previous interactions.-
content: Union[str, ResponseInputMessageContentList]Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
-
strA text input to the model.
-
List[ResponseInputContent]-
class ResponseInputText: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
detail: Literal["low", "high", "auto", "original"]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFile: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The content of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
role: Literal["user", "assistant", "system", "developer"]The role of the message input. One of
user,assistant,system, ordeveloper.-
"user" -
"assistant" -
"system" -
"developer"
-
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
type: Optional[Literal["message"]]The type of the message input. Always
message."message"
-
-
class Message: …A message input to the model with a role indicating instruction following hierarchy. Instructions given with the
developerorsystemrole take precedence over instructions given with theuserrole.-
content: ResponseInputMessageContentListA list of one or many input items to the model, containing different content types.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
role: Literal["user", "system", "developer"]The role of the message input. One of
user,system, ordeveloper.-
"user" -
"system" -
"developer"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Optional[Literal["message"]]The type of the message input. Always set to
message."message"
-
-
class ResponseOutputMessage: …An output message from the model.
-
id: strThe unique ID of the output message.
-
content: List[Content]The content of the output message.
-
class ResponseOutputText: …A text output from the model.
-
annotations: List[Annotation]The annotations of the text output.
-
class AnnotationFileCitation: …A citation to a file.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the file cited.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_citation"]The type of the file citation. Always
file_citation."file_citation"
-
-
class AnnotationURLCitation: …A citation for a web resource used to generate a model response.
-
end_index: intThe index of the last character of the URL citation in the message.
-
start_index: intThe index of the first character of the URL citation in the message.
-
title: strThe title of the web resource.
-
type: Literal["url_citation"]The type of the URL citation. Always
url_citation."url_citation"
-
url: strThe URL of the web resource.
-
-
class AnnotationContainerFileCitation: …A citation for a container file used to generate a model response.
-
container_id: strThe ID of the container file.
-
end_index: intThe index of the last character of the container file citation in the message.
-
file_id: strThe ID of the file.
-
filename: strThe filename of the container file cited.
-
start_index: intThe index of the first character of the container file citation in the message.
-
type: Literal["container_file_citation"]The type of the container file citation. Always
container_file_citation."container_file_citation"
-
-
class AnnotationFilePath: …A path to a file.
-
file_id: strThe ID of the file.
-
index: intThe index of the file in the list of files.
-
type: Literal["file_path"]The type of the file path. Always
file_path."file_path"
-
-
-
text: strThe text output from the model.
-
type: Literal["output_text"]The type of the output text. Always
output_text."output_text"
-
logprobs: Optional[List[Logprob]]-
token: str -
bytes: List[int] -
logprob: float -
top_logprobs: List[LogprobTopLogprob]-
token: str -
bytes: List[int] -
logprob: float
-
-
-
-
class ResponseOutputRefusal: …A refusal from the model.
-
refusal: strThe refusal explanation from the model.
-
type: Literal["refusal"]The type of the refusal. Always
refusal."refusal"
-
-
-
role: Literal["assistant"]The role of the output message. Always
assistant."assistant"
-
status: Literal["in_progress", "completed", "incomplete"]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["message"]The type of the output message. Always
message."message"
-
phase: Optional[Literal["commentary", "final_answer"]]Labels an
assistantmessage as intermediate commentary (commentary) or the final answer (final_answer). For models likegpt-5.3-codexand beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.-
"commentary" -
"final_answer"
-
-
-
class ResponseFileSearchToolCall: …The results of a file search tool call. See the file search guide for more information.
-
id: strThe unique ID of the file search tool call.
-
queries: List[str]The queries used to search for files.
-
status: Literal["in_progress", "searching", "completed", 2 more]The status of the file search tool call. One of
in_progress,searching,incompleteorfailed,-
"in_progress" -
"searching" -
"completed" -
"incomplete" -
"failed"
-
-
type: Literal["file_search_call"]The type of the file search tool call. Always
file_search_call."file_search_call"
-
results: Optional[List[Result]]The results of the file search tool call.
-
attributes: Optional[Dict[str, Union[str, float, bool]]]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.
-
str -
float -
bool
-
-
file_id: Optional[str]The unique ID of the file.
-
filename: Optional[str]The name of the file.
-
score: Optional[float]The relevance score of the file - a value between 0 and 1.
-
text: Optional[str]The text that was retrieved from the file.
-
-
-
class ResponseComputerToolCall: …A tool call to a computer use tool. See the computer use guide for more information.
-
id: strThe unique ID of the computer call.
-
call_id: strAn identifier used when responding to the tool call with output.
-
pending_safety_checks: List[PendingSafetyCheck]The pending safety checks for the computer call.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Literal["in_progress", "completed", "incomplete"]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["computer_call"]The type of the computer call. Always
computer_call."computer_call"
-
action: Optional[Action]A click action.
-
class ActionClick: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class ActionDoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class ActionDrag: …A drag action.
-
path: List[ActionDragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class ActionKeypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class ActionMove: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class ActionScreenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class ActionScroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class ActionType: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class ActionWait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
actions: Optional[ComputerActionList]Flattened batched actions for
computer_use. Each action includes antypediscriminator and action-specific fields.-
class Click: …A click action.
-
button: Literal["left", "right", "wheel", 2 more]Indicates which mouse button was pressed during the click. One of
left,right,wheel,back, orforward.-
"left" -
"right" -
"wheel" -
"back" -
"forward"
-
-
type: Literal["click"]Specifies the event type. For a click action, this property is always
click."click"
-
x: intThe x-coordinate where the click occurred.
-
y: intThe y-coordinate where the click occurred.
-
keys: Optional[List[str]]The keys being held while clicking.
-
-
class DoubleClick: …A double click action.
-
keys: Optional[List[str]]The keys being held while double-clicking.
-
type: Literal["double_click"]Specifies the event type. For a double click action, this property is always set to
double_click."double_click"
-
x: intThe x-coordinate where the double click occurred.
-
y: intThe y-coordinate where the double click occurred.
-
-
class Drag: …A drag action.
-
path: List[DragPath]An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg
[ { x: 100, y: 200 }, { x: 200, y: 300 } ]-
x: intThe x-coordinate.
-
y: intThe y-coordinate.
-
-
type: Literal["drag"]Specifies the event type. For a drag action, this property is always set to
drag."drag"
-
keys: Optional[List[str]]The keys being held while dragging the mouse.
-
-
class Keypress: …A collection of keypresses the model would like to perform.
-
keys: List[str]The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.
-
type: Literal["keypress"]Specifies the event type. For a keypress action, this property is always set to
keypress."keypress"
-
-
class Move: …A mouse move action.
-
type: Literal["move"]Specifies the event type. For a move action, this property is always set to
move."move"
-
x: intThe x-coordinate to move to.
-
y: intThe y-coordinate to move to.
-
keys: Optional[List[str]]The keys being held while moving the mouse.
-
-
class Screenshot: …A screenshot action.
-
type: Literal["screenshot"]Specifies the event type. For a screenshot action, this property is always set to
screenshot."screenshot"
-
-
class Scroll: …A scroll action.
-
scroll_x: intThe horizontal scroll distance.
-
scroll_y: intThe vertical scroll distance.
-
type: Literal["scroll"]Specifies the event type. For a scroll action, this property is always set to
scroll."scroll"
-
x: intThe x-coordinate where the scroll occurred.
-
y: intThe y-coordinate where the scroll occurred.
-
keys: Optional[List[str]]The keys being held while scrolling.
-
-
class Type: …An action to type in text.
-
text: strThe text to type.
-
type: Literal["type"]Specifies the event type. For a type action, this property is always set to
type."type"
-
-
class Wait: …A wait action.
-
type: Literal["wait"]Specifies the event type. For a wait action, this property is always set to
wait."wait"
-
-
-
-
class ComputerCallOutput: …The output of a computer tool call.
-
call_id: strThe ID of the computer tool call that produced the output.
-
output: ResponseComputerToolCallOutputScreenshotA computer screenshot image used with the computer use tool.
-
type: Literal["computer_screenshot"]Specifies the event type. For a computer screenshot, this property is always set to
computer_screenshot."computer_screenshot"
-
file_id: Optional[str]The identifier of an uploaded file that contains the screenshot.
-
image_url: Optional[str]The URL of the screenshot image.
-
-
type: Literal["computer_call_output"]The type of the computer tool call output. Always
computer_call_output."computer_call_output"
-
id: Optional[str]The ID of the computer tool call output.
-
acknowledged_safety_checks: Optional[List[ComputerCallOutputAcknowledgedSafetyCheck]]The safety checks reported by the API that have been acknowledged by the developer.
-
id: strThe ID of the pending safety check.
-
code: Optional[str]The type of the pending safety check.
-
message: Optional[str]Details about the pending safety check.
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the message input. One of
in_progress,completed, orincomplete. Populated when input items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseFunctionWebSearch: …The results of a web search tool call. See the web search guide for more information.
-
id: strThe unique ID of the web search tool call.
-
action: ActionAn object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
-
class ActionSearch: …Action type "search" - Performs a web search query.
-
type: Literal["search"]The action type.
"search"
-
queries: Optional[List[str]]The search queries.
-
query: Optional[str]The search query.
-
sources: Optional[List[ActionSearchSource]]The sources used in the search.
-
type: Literal["url"]The type of source. Always
url."url"
-
url: strThe URL of the source.
-
-
-
class ActionOpenPage: …Action type "open_page" - Opens a specific URL from search results.
-
type: Literal["open_page"]The action type.
"open_page"
-
url: Optional[str]The URL opened by the model.
-
-
class ActionFindInPage: …Action type "find_in_page": Searches for a pattern within a loaded page.
-
pattern: strThe pattern or text to search for within the page.
-
type: Literal["find_in_page"]The action type.
"find_in_page"
-
url: strThe URL of the page searched for the pattern.
-
-
-
status: Literal["in_progress", "searching", "completed", "failed"]The status of the web search tool call.
-
"in_progress" -
"searching" -
"completed" -
"failed"
-
-
type: Literal["web_search_call"]The type of the web search tool call. Always
web_search_call."web_search_call"
-
-
class ResponseFunctionToolCall: …A tool call to run a function. See the function calling guide for more information.
-
arguments: strA JSON string of the arguments to pass to the function.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
name: strThe name of the function to run.
-
type: Literal["function_call"]The type of the function tool call. Always
function_call."function_call"
-
id: Optional[str]The unique ID of the function tool call.
-
namespace: Optional[str]The namespace of the function to run.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class FunctionCallOutput: …The output of a function tool call.
-
call_id: strThe unique ID of the function tool call generated by the model.
-
output: Union[str, ResponseFunctionCallOutputItemList]Text, image, or file output of the function tool call.
-
strA JSON string of the output of the function tool call.
-
List[ResponseFunctionCallOutputItem]-
class ResponseInputTextContent: …A text input to the model.
-
text: strThe text input to the model.
-
type: Literal["input_text"]The type of the input item. Always
input_text."input_text"
-
-
class ResponseInputImageContent: …An image input to the model. Learn about image inputs
-
type: Literal["input_image"]The type of the input item. Always
input_image."input_image"
-
detail: Optional[Literal["low", "high", "auto", "original"]]The detail level of the image to be sent to the model. One of
high,low,auto, ororiginal. Defaults toauto.-
"low" -
"high" -
"auto" -
"original"
-
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
image_url: Optional[str]The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.
-
-
class ResponseInputFileContent: …A file input to the model.
-
type: Literal["input_file"]The type of the input item. Always
input_file."input_file"
-
detail: Optional[Literal["low", "high"]]The detail level of the file to be sent to the model. Use
lowfor the default rendering behavior, orhighto render the file at higher quality. Defaults tolow.-
"low" -
"high"
-
-
file_data: Optional[str]The base64-encoded data of the file to be sent to the model.
-
file_id: Optional[str]The ID of the file to be sent to the model.
-
file_url: Optional[str]The URL of the file to be sent to the model.
-
filename: Optional[str]The name of the file to be sent to the model.
-
-
-
-
type: Literal["function_call_output"]The type of the function tool call output. Always
function_call_output."function_call_output"
-
id: Optional[str]The unique ID of the function tool call output. Populated when this item is returned via API.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ToolSearchCall: …-
arguments: objectThe arguments supplied to the tool search call.
-
type: Literal["tool_search_call"]The item type. Always
tool_search_call."tool_search_call"
-
id: Optional[str]The unique ID of this tool search call.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseToolSearchOutputItemParam: …-
tools: List[Tool]The loaded tool definitions returned by the tool search output.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
name: strThe name of the function to call.
-
parameters: Optional[Dict[str, object]]A JSON schema object describing the parameters of the function.
-
strict: Optional[bool]Whether to enforce strict parameter validation. Default
true. -
type: Literal["function"]The type of the function tool. Always
function."function"
-
defer_loading: Optional[bool]Whether this function is deferred and loaded via tool search.
-
description: Optional[str]A description of the function. Used by the model to determine whether or not to call the function.
-
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
type: Literal["file_search"]The type of the file search tool. Always
file_search."file_search"
-
vector_store_ids: List[str]The IDs of the vector stores to search.
-
filters: Optional[Filters]A filter to apply.
-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
key: strThe key to compare against the value.
-
type: Literal["eq", "ne", "gt", 5 more]Specifies the comparison operator:
eq,ne,gt,gte,lt,lte,in,nin.-
eq: equals -
ne: not equal -
gt: greater than -
gte: greater than or equal -
lt: less than -
lte: less than or equal -
in: in -
nin: not in -
"eq" -
"ne" -
"gt" -
"gte" -
"lt" -
"lte" -
"in" -
"nin"
-
-
value: Union[str, float, bool, List[Union[str, float]]]The value to compare against the attribute key; supports string, number, or boolean types.
-
str -
float -
bool -
List[Union[str, float]]-
str -
float
-
-
-
-
class CompoundFilter: …Combine multiple filters using
andoror.-
filters: List[Filter]Array of filters to combine. Items can be
ComparisonFilterorCompoundFilter.-
class ComparisonFilter: …A filter used to compare a specified attribute key to a given value using a defined comparison operation.
-
object
-
-
type: Literal["and", "or"]Type of operation:
andoror.-
"and" -
"or"
-
-
-
-
max_num_results: Optional[int]The maximum number of results to return. This number should be between 1 and 50 inclusive.
-
ranking_options: Optional[RankingOptions]Ranking options for search.
-
hybrid_search: Optional[RankingOptionsHybridSearch]Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.
-
embedding_weight: floatThe weight of the embedding in the reciprocal ranking fusion.
-
text_weight: floatThe weight of the text in the reciprocal ranking fusion.
-
-
ranker: Optional[Literal["auto", "default-2024-11-15"]]The ranker to use for the file search.
-
"auto" -
"default-2024-11-15"
-
-
score_threshold: Optional[float]The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
-
-
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
type: Literal["computer"]The type of the computer tool. Always
computer."computer"
-
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
display_height: intThe height of the computer display.
-
display_width: intThe width of the computer display.
-
environment: Literal["windows", "mac", "linux", 2 more]The type of computer environment to control.
-
"windows" -
"mac" -
"linux" -
"ubuntu" -
"browser"
-
-
type: Literal["computer_use_preview"]The type of the computer use tool. Always
computer_use_preview."computer_use_preview"
-
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
type: Literal["web_search", "web_search_2025_08_26"]The type of the web search tool. One of
web_searchorweb_search_2025_08_26.-
"web_search" -
"web_search_2025_08_26"
-
-
filters: Optional[Filters]Filters for the search.
-
allowed_domains: Optional[List[str]]Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well.
Example:
["pubmed.ncbi.nlm.nih.gov"]
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The approximate location of the user.
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles. -
type: Optional[Literal["approximate"]]The type of location approximation. Always
approximate."approximate"
-
-
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
server_label: strA label for this MCP server, used to identify it in tool calls.
-
type: Literal["mcp"]The type of the MCP tool. Always
mcp."mcp"
-
allowed_tools: Optional[McpAllowedTools]List of allowed tool names or a filter object.
-
List[str]A string array of allowed tool names
-
class McpAllowedToolsMcpToolFilter: …A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
authorization: Optional[str]An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.
-
connector_id: Optional[Literal["connector_dropbox", "connector_gmail", "connector_googlecalendar", 5 more]]Identifier for service connectors, like those available in ChatGPT. One of
server_urlorconnector_idmust be provided. Learn more about service connectors here.Currently supported
connector_idvalues are:-
Dropbox:
connector_dropbox -
Gmail:
connector_gmail -
Google Calendar:
connector_googlecalendar -
Google Drive:
connector_googledrive -
Microsoft Teams:
connector_microsoftteams -
Outlook Calendar:
connector_outlookcalendar -
Outlook Email:
connector_outlookemail -
SharePoint:
connector_sharepoint -
"connector_dropbox" -
"connector_gmail" -
"connector_googlecalendar" -
"connector_googledrive" -
"connector_microsoftteams" -
"connector_outlookcalendar" -
"connector_outlookemail" -
"connector_sharepoint"
-
-
defer_loading: Optional[bool]Whether this MCP tool is deferred and discovered via tool search.
-
headers: Optional[Dict[str, str]]Optional HTTP headers to send to the MCP server. Use for authentication or other purposes.
-
require_approval: Optional[McpRequireApproval]Specify which of the MCP server's tools require approval.
-
class McpRequireApprovalMcpToolApprovalFilter: …Specify which of the MCP server's tools require approval. Can be
always,never, or a filter object associated with tools that require approval.-
always: Optional[McpRequireApprovalMcpToolApprovalFilterAlways]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
never: Optional[McpRequireApprovalMcpToolApprovalFilterNever]A filter object to specify which tools are allowed.
-
read_only: Optional[bool]Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with
readOnlyHint, it will match this filter. -
tool_names: Optional[List[str]]List of allowed tool names.
-
-
-
Literal["always", "never"]Specify a single approval policy for all tools. One of
alwaysornever. When set toalways, all tools will require approval. When set tonever, all tools will not require approval.-
"always" -
"never"
-
-
-
server_description: Optional[str]Optional description of the MCP server, used to provide more context.
-
server_url: Optional[str]The URL for the MCP server. One of
server_urlorconnector_idmust be provided.
-
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
container: CodeInterpreterContainerThe code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional
memory_limitsetting.-
strThe container ID.
-
class CodeInterpreterContainerCodeInterpreterToolAuto: …Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
-
type: Literal["auto"]Always
auto."auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the code interpreter container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[CodeInterpreterContainerCodeInterpreterToolAutoNetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: …-
type: Literal["disabled"]Disable outbound network access. Always
disabled."disabled"
-
-
class ContainerNetworkPolicyAllowlist: …-
allowed_domains: List[str]A list of allowed domains when type is
allowlist. -
type: Literal["allowlist"]Allow outbound network access only to specified domains. Always
allowlist."allowlist"
-
domain_secrets: Optional[List[ContainerNetworkPolicyDomainSecret]]Optional domain-scoped secrets for allowlisted domains.
-
domain: strThe domain associated with the secret.
-
name: strThe name of the secret to inject for the domain.
-
value: strThe secret value to inject for the domain.
-
-
-
-
-
-
type: Literal["code_interpreter"]The type of the code interpreter tool. Always
code_interpreter."code_interpreter"
-
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
type: Literal["image_generation"]The type of the image generation tool. Always
image_generation."image_generation"
-
action: Optional[Literal["generate", "edit", "auto"]]Whether to generate a new image or edit an existing image. Default:
auto.-
"generate" -
"edit" -
"auto"
-
-
background: Optional[Literal["transparent", "opaque", "auto"]]Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of
transparent,opaque, orauto(default value). Whenautois used, the model will automatically determine the best background for the image.gpt-image-2andgpt-image-2-2026-04-21do not support transparent backgrounds. Requests withbackgroundset totransparentwill return an error for these models; useopaqueorautoinstead.If
transparent, the output format needs to support transparency, so it should be set to eitherpng(default value) orwebp.-
"transparent" -
"opaque" -
"auto"
-
-
input_fidelity: Optional[Literal["high", "low"]]Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for
gpt-image-1andgpt-image-1.5and later models, unsupported forgpt-image-1-mini. Supportshighandlow. Defaults tolow.-
"high" -
"low"
-
-
input_image_mask: Optional[ImageGenerationInputImageMask]Optional mask for inpainting. Contains
image_url(string, optional) andfile_id(string, optional).-
file_id: Optional[str]File ID for the mask image.
-
image_url: Optional[str]Base64-encoded mask image.
-
-
model: Optional[Union[str, Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more], null]]The image generation model to use. Default:
gpt-image-1.-
str -
Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 3 more]The image generation model to use. Default:
gpt-image-1.-
"gpt-image-1" -
"gpt-image-1-mini" -
"gpt-image-2" -
"gpt-image-2-2026-04-21" -
"gpt-image-1.5" -
"chatgpt-image-latest"
-
-
-
moderation: Optional[Literal["auto", "low"]]Moderation level for the generated image. Default:
auto.-
"auto" -
"low"
-
-
output_compression: Optional[int]Compression level for the output image. Default: 100.
-
output_format: Optional[Literal["png", "webp", "jpeg"]]The output format of the generated image. One of
png,webp, orjpeg. Default:png.-
"png" -
"webp" -
"jpeg"
-
-
partial_images: Optional[int]Number of partial images to generate in streaming mode, from 0 (default value) to 3.
-
quality: Optional[Literal["low", "medium", "high", "auto"]]The quality of the generated image. One of
low,medium,high, orauto. Default:auto.-
"low" -
"medium" -
"high" -
"auto"
-
-
size: Optional[Union[str, Literal["1024x1024", "1024x1536", "1536x1024", "auto"], null]]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
str -
Literal["1024x1024", "1024x1536", "1536x1024", "auto"]The size of the generated images. For
gpt-image-2andgpt-image-2-2026-04-21, arbitrary resolutions are supported asWIDTHxHEIGHTstrings, for example1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above2560x1440are experimental, and the maximum supported resolution is3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes1024x1024,1536x1024, and1024x1536are supported by the GPT image models;autois supported for models that allow automatic sizing. Fordall-e-2, use one of256x256,512x512, or1024x1024. Fordall-e-3, use one of1024x1024,1792x1024, or1024x1792.-
"1024x1024" -
"1024x1536" -
"1536x1024" -
"auto"
-
-
-
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
type: Literal["local_shell"]The type of the local shell tool. Always
local_shell."local_shell"
-
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
type: Literal["shell"]The type of the shell tool. Always
shell."shell"
-
environment: Optional[Environment]-
class ContainerAuto: …-
type: Literal["container_auto"]Automatically creates a container for this request
"container_auto"
-
file_ids: Optional[List[str]]An optional list of uploaded files to make available to your code.
-
memory_limit: Optional[Literal["1g", "4g", "16g", "64g"]]The memory limit for the container.
-
"1g" -
"4g" -
"16g" -
"64g"
-
-
network_policy: Optional[NetworkPolicy]Network access policy for the container.
-
class ContainerNetworkPolicyDisabled: … -
class ContainerNetworkPolicyAllowlist: …
-
-
skills: Optional[List[Skill]]An optional list of skills referenced by id or inline data.
-
class SkillReference: …-
skill_id: strThe ID of the referenced skill.
-
type: Literal["skill_reference"]References a skill created with the /v1/skills endpoint.
"skill_reference"
-
version: Optional[str]Optional skill version. Use a positive integer or 'latest'. Omit for default.
-
-
class InlineSkill: …-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
source: InlineSkillSourceInline skill payload
-
data: strBase64-encoded skill zip bundle.
-
media_type: Literal["application/zip"]The media type of the inline skill payload. Must be
application/zip."application/zip"
-
type: Literal["base64"]The type of the inline skill source. Must be
base64."base64"
-
-
type: Literal["inline"]Defines an inline skill for this request.
"inline"
-
-
-
-
class LocalEnvironment: …-
type: Literal["local"]Use a local computer environment.
"local"
-
skills: Optional[List[LocalSkill]]An optional list of skills.
-
description: strThe description of the skill.
-
name: strThe name of the skill.
-
path: strThe path to the directory containing the skill.
-
-
-
class ContainerReference: …-
container_id: strThe ID of the referenced container.
-
type: Literal["container_reference"]References a container created with the /v1/containers endpoint
"container_reference"
-
-
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
name: strThe name of the custom tool, used to identify it in tool calls.
-
type: Literal["custom"]The type of the custom tool. Always
custom."custom"
-
defer_loading: Optional[bool]Whether this tool should be deferred and discovered via tool search.
-
description: Optional[str]Optional description of the custom tool, used to provide more context.
-
format: Optional[CustomToolInputFormat]The input format for the custom tool. Default is unconstrained text.
-
class Text: …Unconstrained free-form text.
-
type: Literal["text"]Unconstrained text format. Always
text."text"
-
-
class Grammar: …A grammar defined by the user.
-
definition: strThe grammar definition.
-
syntax: Literal["lark", "regex"]The syntax of the grammar definition. One of
larkorregex.-
"lark" -
"regex"
-
-
type: Literal["grammar"]Grammar format. Always
grammar."grammar"
-
-
-
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
description: strA description of the namespace shown to the model.
-
name: strThe namespace name used in tool calls (for example,
crm). -
tools: List[Tool]The function/custom tools available inside this namespace.
-
class ToolFunction: …-
name: str -
type: Literal["function"]"function"
-
defer_loading: Optional[bool]Whether this function should be deferred and discovered via tool search.
-
description: Optional[str] -
parameters: Optional[object] -
strict: Optional[bool]
-
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
-
type: Literal["namespace"]The type of the tool. Always
namespace."namespace"
-
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
type: Literal["tool_search"]The type of the tool. Always
tool_search."tool_search"
-
description: Optional[str]Description shown to the model for a client-executed tool search tool.
-
execution: Optional[Literal["server", "client"]]Whether tool search is executed by the server or by the client.
-
"server" -
"client"
-
-
parameters: Optional[object]Parameter schema for a client-executed tool search tool.
-
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
type: Literal["web_search_preview", "web_search_preview_2025_03_11"]The type of the web search tool. One of
web_search_previeworweb_search_preview_2025_03_11.-
"web_search_preview" -
"web_search_preview_2025_03_11"
-
-
search_content_types: Optional[List[Literal["text", "image"]]]-
"text" -
"image"
-
-
search_context_size: Optional[Literal["low", "medium", "high"]]High level guidance for the amount of context window space to use for the search. One of
low,medium, orhigh.mediumis the default.-
"low" -
"medium" -
"high"
-
-
user_location: Optional[UserLocation]The user's location.
-
type: Literal["approximate"]The type of location approximation. Always
approximate."approximate"
-
city: Optional[str]Free text input for the city of the user, e.g.
San Francisco. -
country: Optional[str]The two-letter ISO country code of the user, e.g.
US. -
region: Optional[str]Free text input for the region of the user, e.g.
California. -
timezone: Optional[str]The IANA timezone of the user, e.g.
America/Los_Angeles.
-
-
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
type: Literal["apply_patch"]The type of the tool. Always
apply_patch."apply_patch"
-
-
-
type: Literal["tool_search_output"]The item type. Always
tool_search_output."tool_search_output"
-
id: Optional[str]The unique ID of this tool search output.
-
call_id: Optional[str]The unique ID of the tool search call generated by the model.
-
execution: Optional[Literal["server", "client"]]Whether tool search was executed by the server or by the client.
-
"server" -
"client"
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the tool search output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class AdditionalTools: …-
role: Literal["developer"]The role that provided the additional tools. Only
developeris supported."developer"
-
tools: List[Tool]A list of additional tools made available at this item.
-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
type: Literal["additional_tools"]The item type. Always
additional_tools."additional_tools"
-
id: Optional[str]The unique ID of this additional tools item.
-
-
class ResponseReasoningItem: …A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your
inputto the Responses API for subsequent turns of a conversation if you are manually managing context.-
id: strThe unique identifier of the reasoning content.
-
summary: List[Summary]Reasoning summary content.
-
text: strA summary of the reasoning output from the model so far.
-
type: Literal["summary_text"]The type of the object. Always
summary_text."summary_text"
-
-
type: Literal["reasoning"]The type of the object. Always
reasoning."reasoning"
-
content: Optional[List[Content]]Reasoning text content.
-
text: strThe reasoning text from the model.
-
type: Literal["reasoning_text"]The type of the reasoning text. Always
reasoning_text."reasoning_text"
-
-
encrypted_content: Optional[str]The encrypted content of the reasoning item - populated when a response is generated with
reasoning.encrypted_contentin theincludeparameter. -
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete. Populated when items are returned via API.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ResponseCompactionItemParam: …A compaction item generated by the
v1/responses/compactAPI.-
encrypted_content: strThe encrypted content of the compaction summary.
-
type: Literal["compaction"]The type of the item. Always
compaction."compaction"
-
id: Optional[str]The ID of the compaction item.
-
-
class ImageGenerationCall: …An image generation request made by the model.
-
id: strThe unique ID of the image generation call.
-
result: Optional[str]The generated image encoded in base64.
-
status: Literal["in_progress", "completed", "generating", "failed"]The status of the image generation call.
-
"in_progress" -
"completed" -
"generating" -
"failed"
-
-
type: Literal["image_generation_call"]The type of the image generation call. Always
image_generation_call."image_generation_call"
-
-
class ResponseCodeInterpreterToolCall: …A tool call to run code.
-
id: strThe unique ID of the code interpreter tool call.
-
code: Optional[str]The code to run, or null if not available.
-
container_id: strThe ID of the container used to run the code.
-
outputs: Optional[List[Output]]The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
-
class OutputLogs: …The logs output from the code interpreter.
-
logs: strThe logs output from the code interpreter.
-
type: Literal["logs"]The type of the output. Always
logs."logs"
-
-
class OutputImage: …The image output from the code interpreter.
-
type: Literal["image"]The type of the output. Always
image."image"
-
url: strThe URL of the image output from the code interpreter.
-
-
-
status: Literal["in_progress", "completed", "incomplete", 2 more]The status of the code interpreter tool call. Valid values are
in_progress,completed,incomplete,interpreting, andfailed.-
"in_progress" -
"completed" -
"incomplete" -
"interpreting" -
"failed"
-
-
type: Literal["code_interpreter_call"]The type of the code interpreter tool call. Always
code_interpreter_call."code_interpreter_call"
-
-
class LocalShellCall: …A tool call to run a command on the local shell.
-
id: strThe unique ID of the local shell call.
-
action: LocalShellCallActionExecute a shell command on the server.
-
command: List[str]The command to run.
-
env: Dict[str, str]Environment variables to set for the command.
-
type: Literal["exec"]The type of the local shell action. Always
exec."exec"
-
timeout_ms: Optional[int]Optional timeout in milliseconds for the command.
-
user: Optional[str]Optional user to run the command as.
-
working_directory: Optional[str]Optional working directory to run the command in.
-
-
call_id: strThe unique ID of the local shell tool call generated by the model.
-
status: Literal["in_progress", "completed", "incomplete"]The status of the local shell call.
-
"in_progress" -
"completed" -
"incomplete"
-
-
type: Literal["local_shell_call"]The type of the local shell call. Always
local_shell_call."local_shell_call"
-
-
class LocalShellCallOutput: …The output of a local shell tool call.
-
id: strThe unique ID of the local shell tool call generated by the model.
-
output: strA JSON string of the output of the local shell tool call.
-
type: Literal["local_shell_call_output"]The type of the local shell tool call output. Always
local_shell_call_output."local_shell_call_output"
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the item. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCall: …A tool representing a request to execute one or more shell commands.
-
action: ShellCallActionThe shell commands and limits that describe how to run the tool call.
-
commands: List[str]Ordered shell commands for the execution environment to run.
-
max_output_length: Optional[int]Maximum number of UTF-8 characters to capture from combined stdout and stderr output.
-
timeout_ms: Optional[int]Maximum wall-clock time in milliseconds to allow the shell commands to run.
-
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
type: Literal["shell_call"]The type of the item. Always
shell_call."shell_call"
-
id: Optional[str]The unique ID of the shell tool call. Populated when this item is returned via API.
-
environment: Optional[ShellCallEnvironment]The environment to execute the shell commands in.
-
class LocalEnvironment: … -
class ContainerReference: …
-
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call. One of
in_progress,completed, orincomplete.-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ShellCallOutput: …The streamed output items emitted by a shell tool call.
-
call_id: strThe unique ID of the shell tool call generated by the model.
-
output: List[ResponseFunctionShellCallOutputContent]Captured chunks of stdout and stderr output, along with their associated outcomes.
-
outcome: OutcomeThe exit or timeout outcome associated with this shell call.
-
class OutcomeTimeout: …Indicates that the shell call exceeded its configured time limit.
-
type: Literal["timeout"]The outcome type. Always
timeout."timeout"
-
-
class OutcomeExit: …Indicates that the shell commands finished and returned an exit code.
-
exit_code: intThe exit code returned by the shell process.
-
type: Literal["exit"]The outcome type. Always
exit."exit"
-
-
-
stderr: strCaptured stderr output for the shell call.
-
stdout: strCaptured stdout output for the shell call.
-
-
type: Literal["shell_call_output"]The type of the item. Always
shell_call_output."shell_call_output"
-
id: Optional[str]The unique ID of the shell tool call output. Populated when this item is returned via API.
-
max_output_length: Optional[int]The maximum number of UTF-8 characters captured for this shell call's combined output.
-
status: Optional[Literal["in_progress", "completed", "incomplete"]]The status of the shell call output.
-
"in_progress" -
"completed" -
"incomplete"
-
-
-
class ApplyPatchCall: …A tool call representing a request to create, delete, or update files using diff patches.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
operation: ApplyPatchCallOperationThe specific create, delete, or update instruction for the apply_patch tool call.
-
class ApplyPatchCallOperationCreateFile: …Instruction for creating a new file via the apply_patch tool.
-
diff: strUnified diff content to apply when creating the file.
-
path: strPath of the file to create relative to the workspace root.
-
type: Literal["create_file"]The operation type. Always
create_file."create_file"
-
-
class ApplyPatchCallOperationDeleteFile: …Instruction for deleting an existing file via the apply_patch tool.
-
path: strPath of the file to delete relative to the workspace root.
-
type: Literal["delete_file"]The operation type. Always
delete_file."delete_file"
-
-
class ApplyPatchCallOperationUpdateFile: …Instruction for updating an existing file via the apply_patch tool.
-
diff: strUnified diff content to apply to the existing file.
-
path: strPath of the file to update relative to the workspace root.
-
type: Literal["update_file"]The operation type. Always
update_file."update_file"
-
-
-
status: Literal["in_progress", "completed"]The status of the apply patch tool call. One of
in_progressorcompleted.-
"in_progress" -
"completed"
-
-
type: Literal["apply_patch_call"]The type of the item. Always
apply_patch_call."apply_patch_call"
-
id: Optional[str]The unique ID of the apply patch tool call. Populated when this item is returned via API.
-
-
class ApplyPatchCallOutput: …The streamed output emitted by an apply patch tool call.
-
call_id: strThe unique ID of the apply patch tool call generated by the model.
-
status: Literal["completed", "failed"]The status of the apply patch tool call output. One of
completedorfailed.-
"completed" -
"failed"
-
-
type: Literal["apply_patch_call_output"]The type of the item. Always
apply_patch_call_output."apply_patch_call_output"
-
id: Optional[str]The unique ID of the apply patch tool call output. Populated when this item is returned via API.
-
output: Optional[str]Optional human-readable log text from the apply patch tool (e.g., patch results or errors).
-
-
class McpListTools: …A list of tools available on an MCP server.
-
id: strThe unique ID of the list.
-
server_label: strThe label of the MCP server.
-
tools: List[McpListToolsTool]The tools available on the server.
-
input_schema: objectThe JSON schema describing the tool's input.
-
name: strThe name of the tool.
-
annotations: Optional[object]Additional annotations about the tool.
-
description: Optional[str]The description of the tool.
-
-
type: Literal["mcp_list_tools"]The type of the item. Always
mcp_list_tools."mcp_list_tools"
-
error: Optional[str]Error message if the server could not list tools.
-
-
class McpApprovalRequest: …A request for human approval of a tool invocation.
-
id: strThe unique ID of the approval request.
-
arguments: strA JSON string of arguments for the tool.
-
name: strThe name of the tool to run.
-
server_label: strThe label of the MCP server making the request.
-
type: Literal["mcp_approval_request"]The type of the item. Always
mcp_approval_request."mcp_approval_request"
-
-
class McpApprovalResponse: …A response to an MCP approval request.
-
approval_request_id: strThe ID of the approval request being answered.
-
approve: boolWhether the request was approved.
-
type: Literal["mcp_approval_response"]The type of the item. Always
mcp_approval_response."mcp_approval_response"
-
id: Optional[str]The unique ID of the approval response
-
reason: Optional[str]Optional reason for the decision.
-
-
class McpCall: …An invocation of a tool on an MCP server.
-
id: strThe unique ID of the tool call.
-
arguments: strA JSON string of the arguments passed to the tool.
-
name: strThe name of the tool that was run.
-
server_label: strThe label of the MCP server running the tool.
-
type: Literal["mcp_call"]The type of the item. Always
mcp_call."mcp_call"
-
approval_request_id: Optional[str]Unique identifier for the MCP tool call approval request. Include this value in a subsequent
mcp_approval_responseinput to approve or reject the corresponding tool call. -
error: Optional[str]The error from the tool call, if any.
-
output: Optional[str]The output from the tool call.
-
status: Optional[Literal["in_progress", "completed", "incomplete", 2 more]]The status of the tool call. One of
in_progress,completed,incomplete,calling, orfailed.-
"in_progress" -
"completed" -
"incomplete" -
"calling" -
"failed"
-
-
-
class ResponseCustomToolCallOutput: …The output of a custom tool call from your code, being sent back to the model.
-
call_id: strThe call ID, used to map this custom tool call output to a custom tool call.
-
output: Union[str, List[OutputOutputContentList]]The output from the custom tool call generated by your code. Can be a string or an list of output content.
-
strA string of the output of the custom tool call.
-
List[OutputOutputContentList]Text, image, or file output of the custom tool call.
-
class ResponseInputText: …A text input to the model.
-
class ResponseInputImage: …An image input to the model. Learn about image inputs.
-
class ResponseInputFile: …A file input to the model.
-
-
-
type: Literal["custom_tool_call_output"]The type of the custom tool call output. Always
custom_tool_call_output."custom_tool_call_output"
-
id: Optional[str]The unique ID of the custom tool call output in the OpenAI platform.
-
-
class ResponseCustomToolCall: …A call to a custom tool created by the model.
-
call_id: strAn identifier used to map this custom tool call to a tool call output.
-
input: strThe input for the custom tool call generated by the model.
-
name: strThe name of the custom tool being called.
-
type: Literal["custom_tool_call"]The type of the custom tool call. Always
custom_tool_call."custom_tool_call"
-
id: Optional[str]The unique ID of the custom tool call in the OpenAI platform.
-
namespace: Optional[str]The namespace of the custom tool being called.
-
-
class CompactionTrigger: …Compacts the current context. Must be the final input item.
-
type: Literal["compaction_trigger"]The type of the item. Always
compaction_trigger."compaction_trigger"
-
-
class ItemReference: …An internal identifier for an item to reference.
-
id: strThe ID of the item to reference.
-
type: Optional[Literal["item_reference"]]The type of item to reference. Always
item_reference."item_reference"
-
-
-
-
instructions: Optional[str]A system (or developer) message inserted into the model's context. When used along with
previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -
model: Optional[str]Model ID used to generate the response, like
gpt-4ooro3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models. -
parallel_tool_calls: Optional[bool]Whether to allow the model to run tool calls in parallel.
-
personality: Optional[Union[str, Literal["friendly", "pragmatic"]]]A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters.
-
str -
Literal["friendly", "pragmatic"]A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters.
-
"friendly" -
"pragmatic"
-
-
-
previous_response_id: Optional[str]The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with
conversation. -
reasoning: Optional[Reasoning]gpt-5 and o-series models only Configuration options for reasoning models.
-
effort: Optional[ReasoningEffort]Constrains effort on reasoning for reasoning models. Currently supported values are
none,minimal,low,medium,high, andxhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.-
gpt-5.1defaults tonone, which does not perform reasoning. The supported reasoning values forgpt-5.1arenone,low,medium, andhigh. Tool calls are supported for all reasoning values in gpt-5.1. -
All models before
gpt-5.1default tomediumreasoning effort, and do not supportnone. -
The
gpt-5-promodel defaults to (and only supports)highreasoning effort. -
xhighis supported for all models aftergpt-5.1-codex-max. -
"none" -
"minimal" -
"low" -
"medium" -
"high" -
"xhigh"
-
-
generate_summary: Optional[Literal["auto", "concise", "detailed"]]Deprecated: use
summaryinstead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.-
"auto" -
"concise" -
"detailed"
-
-
summary: Optional[Literal["auto", "concise", "detailed"]]A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. One of
auto,concise, ordetailed.conciseis supported forcomputer-use-previewmodels and all reasoning models aftergpt-5.-
"auto" -
"concise" -
"detailed"
-
-
-
text: Optional[Text]Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
-
format: Optional[ResponseFormatTextConfigParam]An object specifying the format that the model must output.
Configuring
{ "type": "json_schema" }enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is
{ "type": "text" }with no additional options.Not recommended for gpt-4o and newer models:
Setting to
{ "type": "json_object" }enables the older JSON mode, which ensures the message the model generates is valid JSON. Usingjson_schemais preferred for models that support it.-
class ResponseFormatText: …Default response format. Used to generate text responses.
-
type: Literal["text"]The type of response format being defined. Always
text."text"
-
-
class ResponseFormatTextJSONSchemaConfig: …JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
-
name: strThe name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
-
schema: Dict[str, object]The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
-
type: Literal["json_schema"]The type of response format being defined. Always
json_schema."json_schema"
-
description: Optional[str]A description of what the response format is for, used by the model to determine how to respond in the format.
-
strict: Optional[bool]Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the
schemafield. Only a subset of JSON Schema is supported whenstrictistrue. To learn more, read the Structured Outputs guide.
-
-
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses. Using
json_schemais recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.-
type: Literal["json_object"]The type of response format being defined. Always
json_object."json_object"
-
-
-
verbosity: Optional[Literal["low", "medium", "high"]]Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are
low,medium, andhigh.-
"low" -
"medium" -
"high"
-
-
tool_choice: Optional[ToolChoice]Controls which tool the model should use, if any.
-
Literal["none", "auto", "required"]-
"none" -
"auto" -
"required"
-
-
class ToolChoiceAllowed: …Constrains the tools available to the model to a pre-defined set.
-
mode: Literal["auto", "required"]Constrains the tools available to the model to a pre-defined set.
autoallows the model to pick from among the allowed tools and generate a message.requiredrequires the model to call one or more of the allowed tools.-
"auto" -
"required"
-
-
tools: List[Dict[str, object]]A list of tool definitions that the model should be allowed to call.
For the Responses API, the list of tool definitions might look like:
[ { "type": "function", "name": "get_weather" }, { "type": "mcp", "server_label": "deepwiki" }, { "type": "image_generation" } ] -
type: Literal["allowed_tools"]Allowed tool configuration type. Always
allowed_tools."allowed_tools"
-
-
class ToolChoiceTypes: …Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.
-
type: Literal["file_search", "web_search_preview", "computer", 5 more]The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
-
file_search -
web_search_preview -
computer -
computer_use_preview -
computer_use -
code_interpreter -
image_generation -
"file_search" -
"web_search_preview" -
"computer" -
"computer_use_preview" -
"computer_use" -
"web_search_preview_2025_03_11" -
"image_generation" -
"code_interpreter"
-
-
-
class ToolChoiceFunction: …Use this option to force the model to call a specific function.
-
name: strThe name of the function to call.
-
type: Literal["function"]For function calling, the type is always
function."function"
-
-
class ToolChoiceMcp: …Use this option to force the model to call a specific tool on a remote MCP server.
-
server_label: strThe label of the MCP server to use.
-
type: Literal["mcp"]For MCP tools, the type is always
mcp."mcp"
-
name: Optional[str]The name of the tool to call on the server.
-
-
class ToolChoiceCustom: …Use this option to force the model to call a specific custom tool.
-
name: strThe name of the custom tool to call.
-
type: Literal["custom"]For custom tool calling, the type is always
custom."custom"
-
-
class ToolChoiceApplyPatch: …Forces the model to call the apply_patch tool when executing a tool call.
-
type: Literal["apply_patch"]The tool to call. Always
apply_patch."apply_patch"
-
-
class ToolChoiceShell: …Forces the model to call the shell tool when a tool call is required.
-
type: Literal["shell"]The tool to call. Always
shell."shell"
-
-
-
tools: Optional[Iterable[ToolParam]]An array of tools the model may call while generating a response. You can specify which tool to use by setting the
tool_choiceparameter.-
class FunctionTool: …Defines a function in your own code the model can choose to call. Learn more about function calling.
-
class FileSearchTool: …A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
-
class ComputerTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class ComputerUsePreviewTool: …A tool that controls a virtual computer. Learn more about the computer tool.
-
class WebSearchTool: …Search the Internet for sources related to the prompt. Learn more about the web search tool.
-
class Mcp: …Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
-
class CodeInterpreter: …A tool that runs Python code to help generate a response to a prompt.
-
class ImageGeneration: …A tool that generates images using the GPT image models.
-
class LocalShell: …A tool that allows the model to execute shell commands in a local environment.
-
class FunctionShellTool: …A tool that allows the model to execute shell commands.
-
class CustomTool: …A custom tool that processes input using a specified format. Learn more about custom tools
-
class NamespaceTool: …Groups function/custom tools under a shared namespace.
-
class ToolSearchTool: …Hosted or BYOT tool search configuration for deferred tools.
-
class WebSearchPreviewTool: …This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
-
class ApplyPatchTool: …Allows the assistant to create, delete, or update files using unified diffs.
-
-
truncation: Optional[Literal["auto", "disabled"]]The truncation strategy to use for the model response. -
auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. -disabled(default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.-
"auto" -
"disabled"
-
Returns
-
class InputTokenCountResponse: …-
input_tokens: int -
object: Literal["response.input_tokens"]"response.input_tokens"
-
Example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
)
response = client.responses.input_tokens.count()
print(response.input_tokens)
Response
{
"input_tokens": 123,
"object": "response.input_tokens"
}
Example
from openai import OpenAI
client = OpenAI()
response = client.responses.input_tokens.count(
model="gpt-5",
input="Tell me a joke."
)
print(response.input_tokens)
Response
{
"object": "response.input_tokens",
"input_tokens": 11
}
Domain Types
Input Token Count Response
-
class InputTokenCountResponse: …-
input_tokens: int -
object: Literal["response.input_tokens"]"response.input_tokens"
-