Threads

Create thread

Thread beta().threads().create(ThreadCreateParamsparams = ThreadCreateParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

post /threads

Create a thread.

Parameters

• ThreadCreateParams params

  • Optional<List<Message>> messages

    A list of messages to start the thread with.

    • Content content

      The text contents of the message.

      • String

      • List<MessageContentPartParam>

        • class ImageFileContentBlock:

          References an image File in the content of a message.

          • ImageFile imageFile

            • String fileId

              The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

            • Optional<Detail> detail

              Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

              • AUTO("auto")

              • LOW("low")

              • HIGH("high")

          • JsonValue; type "image_file"constant

            Always image_file.

            • IMAGE_FILE("image_file")

        • class ImageUrlContentBlock:

          References an image URL in the content of a message.

          • ImageUrl imageUrl

            • String url

              The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

            • Optional<Detail> detail

              Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

              • AUTO("auto")

              • LOW("low")

              • HIGH("high")

          • JsonValue; type "image_url"constant

            The type of the content part.

            • IMAGE_URL("image_url")

        • class TextContentBlockParam:

          The text content that is part of a message.

          • String text

            Text content to be sent to the model

          • JsonValue; type "text"constant

            Always text.

            • TEXT("text")

    • Role role

      The role of the entity that is creating the message. Allowed values include:

      • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

      • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

      • USER("user")

      • ASSISTANT("assistant")

    • Optional<List<Attachment>> attachments

      A list of files attached to the message, and the tools they should be added to.

      • Optional<String> fileId

        The ID of the file to attach to the message.

      • Optional<List<Tool>> tools

        The tools to add this file to.

        • class CodeInterpreterTool:

          • JsonValue; type "code_interpreter"constant

            The type of tool being defined: code_interpreter

            • CODE_INTERPRETER("code_interpreter")

        • JsonValue;

          • JsonValue; type "file_search"constant

            The type of tool being defined: file_search

            • FILE_SEARCH("file_search")

    • Optional<Metadata> 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.

  • Optional<Metadata> 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.

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

      • Optional<List<VectorStore>> vectorStores

        A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.

        • Optional<ChunkingStrategy> chunkingStrategy

          The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

          • JsonValue;

            • JsonValue; type "auto"constant

              Always auto.

              • AUTO("auto")

          • class Static:

            • InnerStatic static_

              • long chunkOverlapTokens

                The number of tokens that overlap between chunks. The default value is 400.

                Note that the overlap must not exceed half of max_chunk_size_tokens.

              • long maxChunkSizeTokens

                The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

            • JsonValue; type "static"constant

              Always static.

              • STATIC("static")

        • Optional<List<String>> fileIds

          A list of file IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.

        • Optional<Metadata> 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.

Returns

• class Thread:

  Represents a thread that contains messages.

  • String id

    The identifier, which can be referenced in API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the thread was created.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread"constant

    The object type, which is always thread.

    • THREAD("thread")

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.Thread;
import com.openai.models.beta.threads.ThreadCreateParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        Thread thread = client.beta().threads().create();
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Create thread and run

Run beta().threads().createAndRun(ThreadCreateAndRunParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /threads/runs

Create a thread and run it in one request.

Parameters

• ThreadCreateAndRunParams params

  • String assistantId

    The ID of the assistant to use to execute this run.

  • Optional<String> instructions

    Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Optional<Metadata> 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.

  • Optional<ChatModel> model

    The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

  • Optional<Boolean> parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • Optional<Double> temperature

    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.

  • Optional<Thread> thread

    Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.

    • Optional<List<Message>> messages

      A list of messages to start the thread with.

      • Content content

        The text contents of the message.

        • String

        • List<MessageContentPartParam>

          • class ImageFileContentBlock:

            References an image File in the content of a message.

            • ImageFile imageFile

              • String fileId

                The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

              • Optional<Detail> detail

                Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

                • AUTO("auto")

                • LOW("low")

                • HIGH("high")

            • JsonValue; type "image_file"constant

              Always image_file.

              • IMAGE_FILE("image_file")

          • class ImageUrlContentBlock:

            References an image URL in the content of a message.

            • ImageUrl imageUrl

              • String url

                The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

              • Optional<Detail> detail

                Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

                • AUTO("auto")

                • LOW("low")

                • HIGH("high")

            • JsonValue; type "image_url"constant

              The type of the content part.

              • IMAGE_URL("image_url")

          • class TextContentBlockParam:

            The text content that is part of a message.

            • String text

              Text content to be sent to the model

            • JsonValue; type "text"constant

              Always text.

              • TEXT("text")

      • Role role

        The role of the entity that is creating the message. Allowed values include:

        • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

        • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

        • USER("user")

        • ASSISTANT("assistant")

      • Optional<List<Attachment>> attachments

        A list of files attached to the message, and the tools they should be added to.

        • Optional<String> fileId

          The ID of the file to attach to the message.

        • Optional<List<Tool>> tools

          The tools to add this file to.

          • class CodeInterpreterTool:

            • JsonValue; type "code_interpreter"constant

              The type of tool being defined: code_interpreter

              • CODE_INTERPRETER("code_interpreter")

          • JsonValue;

            • JsonValue; type "file_search"constant

              The type of tool being defined: file_search

              • FILE_SEARCH("file_search")

      • Optional<Metadata> 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.

    • Optional<Metadata> 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.

    • Optional<ToolResources> toolResources

      A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

      • Optional<CodeInterpreter> codeInterpreter

        • Optional<List<String>> fileIds

          A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

      • Optional<FileSearch> fileSearch

        • Optional<List<String>> vectorStoreIds

          The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

        • Optional<List<VectorStore>> vectorStores

          A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.

          • Optional<ChunkingStrategy> chunkingStrategy

            The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

            • JsonValue;

              • JsonValue; type "auto"constant

                Always auto.

                • AUTO("auto")

            • class Static:

              • InnerStatic static_

                • long chunkOverlapTokens

                  The number of tokens that overlap between chunks. The default value is 400.

                  Note that the overlap must not exceed half of max_chunk_size_tokens.

                • long maxChunkSizeTokens

                  The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

              • JsonValue; type "static"constant

                Always static.

                • STATIC("static")

          • Optional<List<String>> fileIds

            A list of file IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.

          • Optional<Metadata> 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.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • Optional<ToolResources> toolResources

    A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.

  • Optional<List<AssistantTool>> tools

    Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

    • class CodeInterpreterTool:

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<Double> topP

    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 temperature but not both.

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.ThreadCreateAndRunParams;
import com.openai.models.beta.threads.runs.Run;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        ThreadCreateAndRunParams params = ThreadCreateAndRunParams.builder()
            .assistantId("assistant_id")
            .build();
        Run run = client.beta().threads().createAndRun(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Retrieve thread

Thread beta().threads().retrieve(ThreadRetrieveParamsparams = ThreadRetrieveParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

get /threads/{thread_id}

Retrieves a thread.

Parameters

• ThreadRetrieveParams params

  • Optional<String> threadId

Returns

• class Thread:

  Represents a thread that contains messages.

  • String id

    The identifier, which can be referenced in API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the thread was created.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread"constant

    The object type, which is always thread.

    • THREAD("thread")

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.Thread;
import com.openai.models.beta.threads.ThreadRetrieveParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        Thread thread = client.beta().threads().retrieve("thread_id");
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Modify thread

Thread beta().threads().update(ThreadUpdateParamsparams = ThreadUpdateParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

post /threads/{thread_id}

Modifies a thread.

Parameters

• ThreadUpdateParams params

  • Optional<String> threadId

  • Optional<Metadata> 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.

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Returns

• class Thread:

  Represents a thread that contains messages.

  • String id

    The identifier, which can be referenced in API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the thread was created.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread"constant

    The object type, which is always thread.

    • THREAD("thread")

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.Thread;
import com.openai.models.beta.threads.ThreadUpdateParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        Thread thread = client.beta().threads().update("thread_id");
    }
}

Response

{
  "id": "id",
  "created_at": 0,
  "metadata": {
    "foo": "string"
  },
  "object": "thread",
  "tool_resources": {
    "code_interpreter": {
      "file_ids": [
        "string"
      ]
    },
    "file_search": {
      "vector_store_ids": [
        "string"
      ]
    }
  }
}

Delete thread

ThreadDeleted beta().threads().delete(ThreadDeleteParamsparams = ThreadDeleteParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

delete /threads/{thread_id}

Delete a thread.

Parameters

• ThreadDeleteParams params

  • Optional<String> threadId

Returns

• class ThreadDeleted:

  • String id

  • boolean deleted

  • JsonValue; object_ "thread.deleted"constant

    • THREAD_DELETED("thread.deleted")

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.ThreadDeleteParams;
import com.openai.models.beta.threads.ThreadDeleted;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        ThreadDeleted threadDeleted = client.beta().threads().delete("thread_id");
    }
}

Response

{
  "id": "id",
  "deleted": true,
  "object": "thread.deleted"
}

Domain Types

Assistant Response Format Option

• class AssistantResponseFormatOption: A class that can be one of several variants.union

  Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

  Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

  Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

  Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • JsonValue;

    • AUTO("auto")

  • class ResponseFormatText:

    Default response format. Used to generate text responses.

    • JsonValue; type "text"constant

      The type of response format being defined. Always text.

      • TEXT("text")

  • class ResponseFormatJsonObject:

    JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

    • JsonValue; type "json_object"constant

      The type of response format being defined. Always json_object.

      • JSON_OBJECT("json_object")

  • class ResponseFormatJsonSchema:

    JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

    • JsonSchema jsonSchema

      Structured Outputs configuration options, including a JSON Schema.

      • String name

        The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

      • Optional<String> description

        A description of what the response format is for, used by the model to determine how to respond in the format.

      • Optional<Schema> schema

        The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

      • Optional<Boolean> strict

        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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

    • JsonValue; type "json_schema"constant

      The type of response format being defined. Always json_schema.

      • JSON_SCHEMA("json_schema")

Assistant Tool Choice

• class AssistantToolChoice:

  Specifies a tool the model should use. Use to force the model to call a specific tool.

  • Type type

    The type of the tool. If type is function, the function name must be set

    • FUNCTION("function")

    • CODE_INTERPRETER("code_interpreter")

    • FILE_SEARCH("file_search")

  • Optional<AssistantToolChoiceFunction> function

    • String name

      The name of the function to call.

Assistant Tool Choice Function

• class AssistantToolChoiceFunction:

  • String name

    The name of the function to call.

Assistant Tool Choice Option

• class AssistantToolChoiceOption: A class that can be one of several variants.union

  Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • Auto

    • NONE("none")

    • AUTO("auto")

    • REQUIRED("required")

  • class AssistantToolChoice:

    Specifies a tool the model should use. Use to force the model to call a specific tool.

    • Type type

      The type of the tool. If type is function, the function name must be set

      • FUNCTION("function")

      • CODE_INTERPRETER("code_interpreter")

      • FILE_SEARCH("file_search")

    • Optional<AssistantToolChoiceFunction> function

      • String name

        The name of the function to call.

Thread

• class Thread:

  Represents a thread that contains messages.

  • String id

    The identifier, which can be referenced in API endpoints.

  • long createdAt

    The Unix timestamp (in seconds) for when the thread was created.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread"constant

    The object type, which is always thread.

    • THREAD("thread")

  • Optional<ToolResources> toolResources

    A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    • Optional<CodeInterpreter> codeInterpreter

      • Optional<List<String>> fileIds

        A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.

    • Optional<FileSearch> fileSearch

      • Optional<List<String>> vectorStoreIds

        The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.

Thread Deleted

• class ThreadDeleted:

  • String id

  • boolean deleted

  • JsonValue; object_ "thread.deleted"constant

    • THREAD_DELETED("thread.deleted")

Runs

List runs

RunListPage beta().threads().runs().list(RunListParamsparams = RunListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())

get /threads/{thread_id}/runs

Returns a list of runs belonging to a thread.

Parameters

• RunListParams params

  • Optional<String> threadId

  • Optional<String> after

    A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

  • Optional<String> before

    A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

  • Optional<Long> limit

    A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

  • Optional<Order> order

    Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

    • ASC("asc")

    • DESC("desc")

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.RunListPage;
import com.openai.models.beta.threads.runs.RunListParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunListPage page = client.beta().threads().runs().list("thread_id");
    }
}

Response

{
  "data": [
    {
      "id": "id",
      "assistant_id": "assistant_id",
      "cancelled_at": 0,
      "completed_at": 0,
      "created_at": 0,
      "expires_at": 0,
      "failed_at": 0,
      "incomplete_details": {
        "reason": "max_completion_tokens"
      },
      "instructions": "instructions",
      "last_error": {
        "code": "server_error",
        "message": "message"
      },
      "max_completion_tokens": 256,
      "max_prompt_tokens": 256,
      "metadata": {
        "foo": "string"
      },
      "model": "model",
      "object": "thread.run",
      "parallel_tool_calls": true,
      "required_action": {
        "submit_tool_outputs": {
          "tool_calls": [
            {
              "id": "id",
              "function": {
                "arguments": "arguments",
                "name": "name"
              },
              "type": "function"
            }
          ]
        },
        "type": "submit_tool_outputs"
      },
      "response_format": "auto",
      "started_at": 0,
      "status": "queued",
      "thread_id": "thread_id",
      "tool_choice": "none",
      "tools": [
        {
          "type": "code_interpreter"
        }
      ],
      "truncation_strategy": {
        "type": "auto",
        "last_messages": 1
      },
      "usage": {
        "completion_tokens": 0,
        "prompt_tokens": 0,
        "total_tokens": 0
      },
      "temperature": 0,
      "top_p": 0
    }
  ],
  "first_id": "run_abc123",
  "has_more": false,
  "last_id": "run_abc456",
  "object": "list"
}

Create run

Run beta().threads().runs().create(RunCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /threads/{thread_id}/runs

Create a run.

Parameters

• RunCreateParams params

  • Optional<String> threadId

  • Optional<List<RunStepInclude>> include

    A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • STEP_DETAILS_TOOL_CALLS_FILE_SEARCH_RESULTS_CONTENT("step_details.tool_calls[*].file_search.results[*].content")

  • String assistantId

    The ID of the assistant to use to execute this run.

  • Optional<String> additionalInstructions

    Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.

  • Optional<List<AdditionalMessage>> additionalMessages

    Adds additional messages to the thread before creating the run.

    • Content content

      The text contents of the message.

      • String

      • List<MessageContentPartParam>

        • class ImageFileContentBlock:

          References an image File in the content of a message.

          • ImageFile imageFile

            • String fileId

              The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.

            • Optional<Detail> detail

              Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.

              • AUTO("auto")

              • LOW("low")

              • HIGH("high")

          • JsonValue; type "image_file"constant

            Always image_file.

            • IMAGE_FILE("image_file")

        • class ImageUrlContentBlock:

          References an image URL in the content of a message.

          • ImageUrl imageUrl

            • String url

              The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.

            • Optional<Detail> detail

              Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto

              • AUTO("auto")

              • LOW("low")

              • HIGH("high")

          • JsonValue; type "image_url"constant

            The type of the content part.

            • IMAGE_URL("image_url")

        • class TextContentBlockParam:

          The text content that is part of a message.

          • String text

            Text content to be sent to the model

          • JsonValue; type "text"constant

            Always text.

            • TEXT("text")

    • Role role

      The role of the entity that is creating the message. Allowed values include:

      • user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.

      • assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.

      • USER("user")

      • ASSISTANT("assistant")

    • Optional<List<Attachment>> attachments

      A list of files attached to the message, and the tools they should be added to.

      • Optional<String> fileId

        The ID of the file to attach to the message.

      • Optional<List<Tool>> tools

        The tools to add this file to.

        • class CodeInterpreterTool:

          • JsonValue; type "code_interpreter"constant

            The type of tool being defined: code_interpreter

            • CODE_INTERPRETER("code_interpreter")

        • JsonValue;

          • JsonValue; type "file_search"constant

            The type of tool being defined: file_search

            • FILE_SEARCH("file_search")

    • Optional<Metadata> 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.

  • Optional<String> instructions

    Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

  • Optional<Metadata> 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.

  • Optional<ChatModel> model

    The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

  • Optional<Boolean> parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<ReasoningEffort> reasoningEffort

    Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

    • gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
    • All models before gpt-5.1 default to medium reasoning effort, and do not support none.
    • The gpt-5-pro model defaults to (and only supports) high reasoning effort.
    • xhigh is supported for all models after gpt-5.1-codex-max.

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

  • Optional<Double> temperature

    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.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

  • Optional<List<AssistantTool>> tools

    Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

    • class CodeInterpreterTool:

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<Double> topP

    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 temperature but not both.

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.Run;
import com.openai.models.beta.threads.runs.RunCreateParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunCreateParams params = RunCreateParams.builder()
            .threadId("thread_id")
            .assistantId("assistant_id")
            .build();
        Run run = client.beta().threads().runs().create(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Retrieve run

Run beta().threads().runs().retrieve(RunRetrieveParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

get /threads/{thread_id}/runs/{run_id}

Retrieves a run.

Parameters

• RunRetrieveParams params

  • String threadId

  • Optional<String> runId

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.Run;
import com.openai.models.beta.threads.runs.RunRetrieveParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunRetrieveParams params = RunRetrieveParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .build();
        Run run = client.beta().threads().runs().retrieve(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Modify run

Run beta().threads().runs().update(RunUpdateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /threads/{thread_id}/runs/{run_id}

Modifies a run.

Parameters

• RunUpdateParams params

  • String threadId

  • Optional<String> runId

  • Optional<Metadata> 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.

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.Run;
import com.openai.models.beta.threads.runs.RunUpdateParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunUpdateParams params = RunUpdateParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .build();
        Run run = client.beta().threads().runs().update(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Submit tool outputs to run

Run beta().threads().runs().submitToolOutputs(RunSubmitToolOutputsParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /threads/{thread_id}/runs/{run_id}/submit_tool_outputs

When a run has the status: "requires_action" and required_action.type is submit_tool_outputs, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.

Parameters

• RunSubmitToolOutputsParams params

  • String threadId

  • Optional<String> runId

  • List<ToolOutput> toolOutputs

    A list of tools for which the outputs are being submitted.

    • Optional<String> output

      The output of the tool call to be submitted to continue the run.

    • Optional<String> toolCallId

      The ID of the tool call in the required_action object within the run object the output is being submitted for.

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.Run;
import com.openai.models.beta.threads.runs.RunSubmitToolOutputsParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunSubmitToolOutputsParams params = RunSubmitToolOutputsParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .addToolOutput(RunSubmitToolOutputsParams.ToolOutput.builder().build())
            .build();
        Run run = client.beta().threads().runs().submitToolOutputs(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Cancel a run

Run beta().threads().runs().cancel(RunCancelParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /threads/{thread_id}/runs/{run_id}/cancel

Cancels a run that is in_progress.

Parameters

• RunCancelParams params

  • String threadId

  • Optional<String> runId

Returns

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.Run;
import com.openai.models.beta.threads.runs.RunCancelParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunCancelParams params = RunCancelParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .build();
        Run run = client.beta().threads().runs().cancel(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "instructions",
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "max_completion_tokens": 256,
  "max_prompt_tokens": 256,
  "metadata": {
    "foo": "string"
  },
  "model": "model",
  "object": "thread.run",
  "parallel_tool_calls": true,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "id",
          "function": {
            "arguments": "arguments",
            "name": "name"
          },
          "type": "function"
        }
      ]
    },
    "type": "submit_tool_outputs"
  },
  "response_format": "auto",
  "started_at": 0,
  "status": "queued",
  "thread_id": "thread_id",
  "tool_choice": "none",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Domain Types

Required Action Function Tool Call

• class RequiredActionFunctionToolCall:

  Tool call objects

  • String id

    The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

  • Function function

    The function definition.

    • String arguments

      The arguments that the model expects you to pass to the function.

    • String name

      The name of the function.

  • JsonValue; type "function"constant

    The type of tool call the output is required for. For now, this is always function.

    • FUNCTION("function")

Run

• class Run:

  Represents an execution run on a thread.

  • String id

    The identifier, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant used for execution of this run.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run was completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run was created.

  • Optional<Long> expiresAt

    The Unix timestamp (in seconds) for when the run will expire.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run failed.

  • Optional<IncompleteDetails> incompleteDetails

    Details on why the run is incomplete. Will be null if the run is not incomplete.

    • Optional<Reason> reason

      The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.

      • MAX_COMPLETION_TOKENS("max_completion_tokens")

      • MAX_PROMPT_TOKENS("max_prompt_tokens")

  • String instructions

    The instructions that the assistant used for this run.

  • Optional<LastError> lastError

    The last error associated with this run. Will be null if there are no errors.

    • Code code

      One of server_error, rate_limit_exceeded, or invalid_prompt.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

      • INVALID_PROMPT("invalid_prompt")

    • String message

      A human-readable description of the error.

  • Optional<Long> maxCompletionTokens

    The maximum number of completion tokens specified to have been used over the course of the run.

  • Optional<Long> maxPromptTokens

    The maximum number of prompt tokens specified to have been used over the course of the run.

  • Optional<Metadata> 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.

  • String model

    The model that the assistant used for this run.

  • JsonValue; object_ "thread.run"constant

    The object type, which is always thread.run.

    • THREAD_RUN("thread.run")

  • boolean parallelToolCalls

    Whether to enable parallel function calling during tool use.

  • Optional<RequiredAction> requiredAction

    Details on the action required to continue the run. Will be null if no action is required.

    • SubmitToolOutputs submitToolOutputs

      Details on the tool outputs needed for this run to continue.

      • List<RequiredActionFunctionToolCall> toolCalls

        A list of the relevant tool calls.

        • String id

          The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.

        • Function function

          The function definition.

          • String arguments

            The arguments that the model expects you to pass to the function.

          • String name

            The name of the function.

        • JsonValue; type "function"constant

          The type of tool call the output is required for. For now, this is always function.

          • FUNCTION("function")

    • JsonValue; type "submit_tool_outputs"constant

      For now, this is always submit_tool_outputs.

      • SUBMIT_TOOL_OUTPUTS("submit_tool_outputs")

  • Optional<AssistantResponseFormatOption> responseFormat

    Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

    Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

    Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    • JsonValue;

      • AUTO("auto")

    • class ResponseFormatText:

      Default response format. Used to generate text responses.

      • JsonValue; type "text"constant

        The type of response format being defined. Always text.

        • TEXT("text")

    • class ResponseFormatJsonObject:

      JSON object response format. An older method of generating JSON responses. Using json_schema is 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.

      • JsonValue; type "json_object"constant

        The type of response format being defined. Always json_object.

        • JSON_OBJECT("json_object")

    • class ResponseFormatJsonSchema:

      JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.

      • JsonSchema jsonSchema

        Structured Outputs configuration options, including a JSON Schema.

        • String name

          The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the response format is for, used by the model to determine how to respond in the format.

        • Optional<Schema> schema

          The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

        • Optional<Boolean> strict

          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 schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

      • JsonValue; type "json_schema"constant

        The type of response format being defined. Always json_schema.

        • JSON_SCHEMA("json_schema")

  • Optional<Long> startedAt

    The Unix timestamp (in seconds) for when the run was started.

  • RunStatus status

    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

    • QUEUED("queued")

    • IN_PROGRESS("in_progress")

    • REQUIRES_ACTION("requires_action")

    • CANCELLING("cancelling")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • INCOMPLETE("incomplete")

    • EXPIRED("expired")

  • String threadId

    The ID of the thread that was executed on as a part of this run.

  • Optional<AssistantToolChoiceOption> toolChoice

    Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

    • Auto

      • NONE("none")

      • AUTO("auto")

      • REQUIRED("required")

    • class AssistantToolChoice:

      Specifies a tool the model should use. Use to force the model to call a specific tool.

      • Type type

        The type of the tool. If type is function, the function name must be set

        • FUNCTION("function")

        • CODE_INTERPRETER("code_interpreter")

        • FILE_SEARCH("file_search")

      • Optional<AssistantToolChoiceFunction> function

        • String name

          The name of the function to call.

  • List<AssistantTool> tools

    The list of tools that the assistant used for this run.

    • class CodeInterpreterTool:

      • JsonValue; type "code_interpreter"constant

        The type of tool being defined: code_interpreter

        • CODE_INTERPRETER("code_interpreter")

    • class FileSearchTool:

      • JsonValue; type "file_search"constant

        The type of tool being defined: file_search

        • FILE_SEARCH("file_search")

      • Optional<FileSearch> fileSearch

        Overrides for the file search tool.

        • Optional<Long> maxNumResults

          The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.

          Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.

        • Optional<RankingOptions> rankingOptions

          The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.

          See the file search tool documentation for more information.

          • double scoreThreshold

            The score threshold for the file search. All values must be a floating point number between 0 and 1.

          • Optional<Ranker> ranker

            The ranker to use for the file search. If not specified will use the auto ranker.

            • AUTO("auto")

            • DEFAULT_2024_08_21("default_2024_08_21")

    • class FunctionTool:

      • FunctionDefinition function

        • String name

          The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

        • Optional<String> description

          A description of what the function does, used by the model to choose when and how to call the function.

        • Optional<FunctionParameters> parameters

          The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

          Omitting parameters defines a function with an empty parameter list.

        • Optional<Boolean> strict

          Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

      • JsonValue; type "function"constant

        The type of tool being defined: function

        • FUNCTION("function")

  • Optional<TruncationStrategy> truncationStrategy

    Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

    • Type type

      The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.

      • AUTO("auto")

      • LAST_MESSAGES("last_messages")

    • Optional<Long> lastMessages

      The number of most recent messages from the thread when constructing the context for the run.

  • Optional<Usage> usage

    Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

    • long completionTokens

      Number of completion tokens used over the course of the run.

    • long promptTokens

      Number of prompt tokens used over the course of the run.

    • long totalTokens

      Total number of tokens used (prompt + completion).

  • Optional<Double> temperature

    The sampling temperature used for this run. If not set, defaults to 1.

  • Optional<Double> topP

    The nucleus sampling value used for this run. If not set, defaults to 1.

Run Status

• enum RunStatus:

  The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

  • QUEUED("queued")

  • IN_PROGRESS("in_progress")

  • REQUIRES_ACTION("requires_action")

  • CANCELLING("cancelling")

  • CANCELLED("cancelled")

  • FAILED("failed")

  • COMPLETED("completed")

  • INCOMPLETE("incomplete")

  • EXPIRED("expired")

Steps

List run steps

StepListPage beta().threads().runs().steps().list(StepListParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

get /threads/{thread_id}/runs/{run_id}/steps

Returns a list of run steps belonging to a run.

Parameters

• StepListParams params

  • String threadId

  • Optional<String> runId

  • Optional<String> after

    A cursor for use in pagination. after is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.

  • Optional<String> before

    A cursor for use in pagination. before is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.

  • Optional<List<RunStepInclude>> include

    A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • STEP_DETAILS_TOOL_CALLS_FILE_SEARCH_RESULTS_CONTENT("step_details.tool_calls[*].file_search.results[*].content")

  • Optional<Long> limit

    A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.

  • Optional<Order> order

    Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

    • ASC("asc")

    • DESC("desc")

Returns

• class RunStep:

  Represents a step in execution of a run.

  • String id

    The identifier of the run step, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant associated with the run step.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run step was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run step completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run step was created.

  • Optional<Long> expiredAt

    The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run step failed.

  • Optional<LastError> lastError

    The last error associated with this run step. Will be null if there are no errors.

    • Code code

      One of server_error or rate_limit_exceeded.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

    • String message

      A human-readable description of the error.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread.run.step"constant

    The object type, which is always thread.run.step.

    • THREAD_RUN_STEP("thread.run.step")

  • String runId

    The ID of the run that this run step is a part of.

  • Status status

    The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

    • IN_PROGRESS("in_progress")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • EXPIRED("expired")

  • StepDetails stepDetails

    The details of the run step.

    • class MessageCreationStepDetails:

      Details of the message creation by the run step.

      • MessageCreation messageCreation

        • String messageId

          The ID of the message that was created by this run step.

      • JsonValue; type "message_creation"constant

        Always message_creation.

        • MESSAGE_CREATION("message_creation")

    • class ToolCallsStepDetails:

      Details of the tool call.

      • List<ToolCall> toolCalls

        An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

        • class CodeInterpreterToolCall:

          Details of the Code Interpreter tool call the run step was involved in.

          • String id

            The ID of the tool call.

          • CodeInterpreter codeInterpreter

            The Code Interpreter tool call definition.

            • String input

              The input to the Code Interpreter tool call.

            • List<Output> outputs

              The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

              • class LogsOutput:

                Text output from the Code Interpreter tool call as part of a run step.

                • String logs

                  The text output from the Code Interpreter tool call.

                • JsonValue; type "logs"constant

                  Always logs.

                  • LOGS("logs")

              • class ImageOutput:

                • Image image

                  • String fileId

                    The file ID of the image.

                • JsonValue; type "image"constant

                  Always image.

                  • IMAGE("image")

          • JsonValue; type "code_interpreter"constant

            The type of tool call. This is always going to be code_interpreter for this type of tool call.

            • CODE_INTERPRETER("code_interpreter")

        • class FileSearchToolCall:

          • String id

            The ID of the tool call object.

          • FileSearch fileSearch

            For now, this is always going to be an empty object.

            • Optional<RankingOptions> rankingOptions

              The ranking options for the file search.

              • Ranker ranker

                The ranker to use for the file search. If not specified will use the auto ranker.

                • AUTO("auto")

                • DEFAULT_2024_08_21("default_2024_08_21")

              • double scoreThreshold

                The score threshold for the file search. All values must be a floating point number between 0 and 1.

            • Optional<List<Result>> results

              The results of the file search.

              • String fileId

                The ID of the file that result was found in.

              • String fileName

                The name of the file that result was found in.

              • double score

                The score of the result. All values must be a floating point number between 0 and 1.

              • Optional<List<Content>> content

                The content of the result that was found. The content is only included if requested via the include query parameter.

                • Optional<String> text

                  The text content of the file.

                • Optional<Type> type

                  The type of the content.

                  • TEXT("text")

          • JsonValue; type "file_search"constant

            The type of tool call. This is always going to be file_search for this type of tool call.

            • FILE_SEARCH("file_search")

        • class FunctionToolCall:

          • String id

            The ID of the tool call object.

          • Function function

            The definition of the function that was called.

            • String arguments

              The arguments passed to the function.

            • String name

              The name of the function.

            • Optional<String> output

              The output of the function. This will be null if the outputs have not been submitted yet.

          • JsonValue; type "function"constant

            The type of tool call. This is always going to be function for this type of tool call.

            • FUNCTION("function")

      • JsonValue; type "tool_calls"constant

        Always tool_calls.

        • TOOL_CALLS("tool_calls")

  • String threadId

    The ID of the thread that was run.

  • Type type

    The type of run step, which can be either message_creation or tool_calls.

    • MESSAGE_CREATION("message_creation")

    • TOOL_CALLS("tool_calls")

  • Optional<Usage> usage

    Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

    • long completionTokens

      Number of completion tokens used over the course of the run step.

    • long promptTokens

      Number of prompt tokens used over the course of the run step.

    • long totalTokens

      Total number of tokens used (prompt + completion).

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.steps.StepListPage;
import com.openai.models.beta.threads.runs.steps.StepListParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        StepListParams params = StepListParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .build();
        StepListPage page = client.beta().threads().runs().steps().list(params);
    }
}

Response

{
  "data": [
    {
      "id": "id",
      "assistant_id": "assistant_id",
      "cancelled_at": 0,
      "completed_at": 0,
      "created_at": 0,
      "expired_at": 0,
      "failed_at": 0,
      "last_error": {
        "code": "server_error",
        "message": "message"
      },
      "metadata": {
        "foo": "string"
      },
      "object": "thread.run.step",
      "run_id": "run_id",
      "status": "in_progress",
      "step_details": {
        "message_creation": {
          "message_id": "message_id"
        },
        "type": "message_creation"
      },
      "thread_id": "thread_id",
      "type": "message_creation",
      "usage": {
        "completion_tokens": 0,
        "prompt_tokens": 0,
        "total_tokens": 0
      }
    }
  ],
  "first_id": "step_abc123",
  "has_more": false,
  "last_id": "step_abc456",
  "object": "list"
}

Retrieve run step

RunStep beta().threads().runs().steps().retrieve(StepRetrieveParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

get /threads/{thread_id}/runs/{run_id}/steps/{step_id}

Retrieves a run step.

Parameters

• StepRetrieveParams params

  • String threadId

  • String runId

  • Optional<String> stepId

  • Optional<List<RunStepInclude>> include

    A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

    See the file search tool documentation for more information.

    • STEP_DETAILS_TOOL_CALLS_FILE_SEARCH_RESULTS_CONTENT("step_details.tool_calls[*].file_search.results[*].content")

Returns

• class RunStep:

  Represents a step in execution of a run.

  • String id

    The identifier of the run step, which can be referenced in API endpoints.

  • String assistantId

    The ID of the assistant associated with the run step.

  • Optional<Long> cancelledAt

    The Unix timestamp (in seconds) for when the run step was cancelled.

  • Optional<Long> completedAt

    The Unix timestamp (in seconds) for when the run step completed.

  • long createdAt

    The Unix timestamp (in seconds) for when the run step was created.

  • Optional<Long> expiredAt

    The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

  • Optional<Long> failedAt

    The Unix timestamp (in seconds) for when the run step failed.

  • Optional<LastError> lastError

    The last error associated with this run step. Will be null if there are no errors.

    • Code code

      One of server_error or rate_limit_exceeded.

      • SERVER_ERROR("server_error")

      • RATE_LIMIT_EXCEEDED("rate_limit_exceeded")

    • String message

      A human-readable description of the error.

  • Optional<Metadata> 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.

  • JsonValue; object_ "thread.run.step"constant

    The object type, which is always thread.run.step.

    • THREAD_RUN_STEP("thread.run.step")

  • String runId

    The ID of the run that this run step is a part of.

  • Status status

    The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

    • IN_PROGRESS("in_progress")

    • CANCELLED("cancelled")

    • FAILED("failed")

    • COMPLETED("completed")

    • EXPIRED("expired")

  • StepDetails stepDetails

    The details of the run step.

    • class MessageCreationStepDetails:

      Details of the message creation by the run step.

      • MessageCreation messageCreation

        • String messageId

          The ID of the message that was created by this run step.

      • JsonValue; type "message_creation"constant

        Always message_creation.

        • MESSAGE_CREATION("message_creation")

    • class ToolCallsStepDetails:

      Details of the tool call.

      • List<ToolCall> toolCalls

        An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.

        • class CodeInterpreterToolCall:

          Details of the Code Interpreter tool call the run step was involved in.

          • String id

            The ID of the tool call.

          • CodeInterpreter codeInterpreter

            The Code Interpreter tool call definition.

            • String input

              The input to the Code Interpreter tool call.

            • List<Output> outputs

              The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

              • class LogsOutput:

                Text output from the Code Interpreter tool call as part of a run step.

                • String logs

                  The text output from the Code Interpreter tool call.

                • JsonValue; type "logs"constant

                  Always logs.

                  • LOGS("logs")

              • class ImageOutput:

                • Image image

                  • String fileId

                    The file ID of the image.

                • JsonValue; type "image"constant

                  Always image.

                  • IMAGE("image")

          • JsonValue; type "code_interpreter"constant

            The type of tool call. This is always going to be code_interpreter for this type of tool call.

            • CODE_INTERPRETER("code_interpreter")

        • class FileSearchToolCall:

          • String id

            The ID of the tool call object.

          • FileSearch fileSearch

            For now, this is always going to be an empty object.

            • Optional<RankingOptions> rankingOptions

              The ranking options for the file search.

              • Ranker ranker

                The ranker to use for the file search. If not specified will use the auto ranker.

                • AUTO("auto")

                • DEFAULT_2024_08_21("default_2024_08_21")

              • double scoreThreshold

                The score threshold for the file search. All values must be a floating point number between 0 and 1.

            • Optional<List<Result>> results

              The results of the file search.

              • String fileId

                The ID of the file that result was found in.

              • String fileName

                The name of the file that result was found in.

              • double score

                The score of the result. All values must be a floating point number between 0 and 1.

              • Optional<List<Content>> content

                The content of the result that was found. The content is only included if requested via the include query parameter.

                • Optional<String> text

                  The text content of the file.

                • Optional<Type> type

                  The type of the content.

                  • TEXT("text")

          • JsonValue; type "file_search"constant

            The type of tool call. This is always going to be file_search for this type of tool call.

            • FILE_SEARCH("file_search")

        • class FunctionToolCall:

          • String id

            The ID of the tool call object.

          • Function function

            The definition of the function that was called.

            • String arguments

              The arguments passed to the function.

            • String name

              The name of the function.

            • Optional<String> output

              The output of the function. This will be null if the outputs have not been submitted yet.

          • JsonValue; type "function"constant

            The type of tool call. This is always going to be function for this type of tool call.

            • FUNCTION("function")

      • JsonValue; type "tool_calls"constant

        Always tool_calls.

        • TOOL_CALLS("tool_calls")

  • String threadId

    The ID of the thread that was run.

  • Type type

    The type of run step, which can be either message_creation or tool_calls.

    • MESSAGE_CREATION("message_creation")

    • TOOL_CALLS("tool_calls")

  • Optional<Usage> usage

    Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

    • long completionTokens

      Number of completion tokens used over the course of the run step.

    • long promptTokens

      Number of prompt tokens used over the course of the run step.

    • long totalTokens

      Total number of tokens used (prompt + completion).

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.beta.threads.runs.steps.RunStep;
import com.openai.models.beta.threads.runs.steps.StepRetrieveParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        StepRetrieveParams params = StepRetrieveParams.builder()
            .threadId("thread_id")
            .runId("run_id")
            .stepId("step_id")
            .build();
        RunStep runStep = client.beta().threads().runs().steps().retrieve(params);
    }
}

Response

{
  "id": "id",
  "assistant_id": "assistant_id",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expired_at": 0,
  "failed_at": 0,
  "last_error": {
    "code": "server_error",
    "message": "message"
  },
  "metadata": {
    "foo": "string"
  },
  "object": "thread.run.step",
  "run_id": "run_id",
  "status": "in_progress",
  "step_details": {
    "message_creation": {
      "message_id": "message_id"
    },
    "type": "message_creation"
  },
  "thread_id": "thread_id",
  "type": "message_creation",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

Domain Types

Code Interpreter Logs

• class CodeInterpreterLogs:

  Text output from the Code Interpreter tool call as part of a run step.

  • long index

    The index of the output in the outputs array.

  • JsonValue; type "logs"constant

    Always logs.

    • LOGS("logs")

  • Optional<String> logs

    The text output from the Code Interpreter tool call.

Code Interpreter Output Image

• class CodeInterpreterOutputImage:

  • long index

    The index of the output in the outputs array.

  • JsonValue; type "image"constant

    Always image.

    • IMAGE("image")

  • Optional<Image> image

    • Optional<String> fileId

      The file ID of the image.

Code Interpreter Tool Call

• class CodeInterpreterToolCall:

  Details of the Code Interpreter tool call the run step was involved in.

  • String id

    The ID of the tool call.

  • CodeInterpreter codeInterpreter

    The Code Interpreter tool call definition.

    • String input

      The input to the Code Interpreter tool call.

    • List<Output> outputs

      The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

      • class LogsOutput:

        Text output from the Code Interpreter tool call as part of a run step.

        • String logs

          The text output from the Code Interpreter tool call.

        • JsonValue; type "logs"constant

          Always logs.

          • LOGS("logs")

      • class ImageOutput:

        • Image image

          • String fileId

            The file ID of the image.

        • JsonValue; type "image"constant

          Always image.

          • IMAGE("image")

  • JsonValue; type "code_interpreter"constant

    The type of tool call. This is always going to be code_interpreter for this type of tool call.

    • CODE_INTERPRETER("code_interpreter")

Code Interpreter Tool Call Delta

• class CodeInterpreterToolCallDelta:

  Details of the Code Interpreter tool call the run step was involved in.

  • long index

    The index of the tool call in the tool calls array.

  • JsonValue; type "code_interpreter"constant

    The type of tool call. This is always going to be code_interpreter for this type of tool call.

    • CODE_INTERPRETER("code_interpreter")

  • Optional<String> id

    The ID of the tool call.

  • Optional<CodeInterpreter> codeInterpreter

    The Code Interpreter tool call definition.

    • Optional<String> input

      The input to the Code Interpreter tool call.

    • Optional<List<Output>> outputs

      The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.

      • class CodeInterpreterLogs:

        Text output from the Code Interpreter tool call as part of a run step.

        • long index

          The index of the output in the outputs array.

        • JsonValue; type "logs"constant

          Always logs.

          • LOGS("logs")

        • Optional<String> logs

          The text output from the Code Interpreter tool call.

      • class CodeInterpreterOutputImage:

        • long index

          The index of the output in the outputs array.

        • JsonValue; type "image"constant

          Always image.

          • IMAGE("image")

        • Optional<Image> image

          • Optional<String> fileId

            The file ID of the image.