diff --git a/en/resources/beta/index.md b/en/resources/beta/index.md index ae9f18b8..9eac3376 100644 --- a/en/resources/beta/index.md +++ b/en/resources/beta/index.md @@ -104,15 +104,15 @@ Create an assistant with a model and instructions. - `"gpt-3.5-turbo-16k-0613"` -- `description: optional string` +- `description: optional string or null` The description of the assistant. The maximum length is 512 characters. -- `instructions: optional string` +- `instructions: optional string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -121,11 +121,11 @@ Create an assistant with a model and instructions. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `name: optional string` +- `name: optional string or null` The name of the assistant. The maximum length is 256 characters. -- `reasoning_effort: optional ReasoningEffort` +- `reasoning_effort: optional ReasoningEffort or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -149,7 +149,7 @@ Create an assistant with a model and instructions. - `"max"` -- `response_format: optional AssistantResponseFormatOption` +- `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -212,7 +212,7 @@ Create an assistant with a model and instructions. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -226,11 +226,11 @@ Create an assistant with a model and instructions. - `"json_schema"` -- `temperature: optional number` +- `temperature: optional number or null` 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. -- `tool_resources: optional object { code_interpreter, file_search }` +- `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -288,7 +288,7 @@ Create an assistant with a model and instructions. A list of [file](/docs/api-reference/files) 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. - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -363,7 +363,7 @@ Create an assistant with a model and instructions. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -373,7 +373,7 @@ Create an assistant with a model and instructions. - `"function"` -- `top_p: optional number` +- `top_p: optional number or null` 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. @@ -393,15 +393,15 @@ Create an assistant with a model and instructions. The Unix timestamp (in seconds) for when the assistant was created. - - `description: string` + - `description: string or null` The description of the assistant. The maximum length is 512 characters. - - `instructions: string` + - `instructions: string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -414,7 +414,7 @@ Create an assistant with a model and instructions. ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. - - `name: string` + - `name: string or null` The name of the assistant. The maximum length is 256 characters. @@ -490,7 +490,7 @@ Create an assistant with a model and instructions. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -500,7 +500,7 @@ Create an assistant with a model and instructions. - `"function"` - - `response_format: optional AssistantResponseFormatOption` + - `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -563,7 +563,7 @@ Create an assistant with a model and instructions. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -577,11 +577,11 @@ Create an assistant with a model and instructions. - `"json_schema"` - - `temperature: optional number` + - `temperature: optional number or null` 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. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -597,7 +597,7 @@ Create an assistant with a model and instructions. The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - - `top_p: optional number` + - `top_p: optional number or null` 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. @@ -836,15 +836,15 @@ Returns a list of assistants. The Unix timestamp (in seconds) for when the assistant was created. - - `description: string` + - `description: string or null` The description of the assistant. The maximum length is 512 characters. - - `instructions: string` + - `instructions: string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -857,7 +857,7 @@ Returns a list of assistants. ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. - - `name: string` + - `name: string or null` The name of the assistant. The maximum length is 256 characters. @@ -933,7 +933,7 @@ Returns a list of assistants. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -943,7 +943,7 @@ Returns a list of assistants. - `"function"` - - `response_format: optional AssistantResponseFormatOption` + - `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -1006,7 +1006,7 @@ Returns a list of assistants. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -1020,11 +1020,11 @@ Returns a list of assistants. - `"json_schema"` - - `temperature: optional number` + - `temperature: optional number or null` 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. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -1040,7 +1040,7 @@ Returns a list of assistants. The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - - `top_p: optional number` + - `top_p: optional number or null` 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. @@ -1198,15 +1198,15 @@ Retrieves an assistant. The Unix timestamp (in seconds) for when the assistant was created. - - `description: string` + - `description: string or null` The description of the assistant. The maximum length is 512 characters. - - `instructions: string` + - `instructions: string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -1219,7 +1219,7 @@ Retrieves an assistant. ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. - - `name: string` + - `name: string or null` The name of the assistant. The maximum length is 256 characters. @@ -1295,7 +1295,7 @@ Retrieves an assistant. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -1305,7 +1305,7 @@ Retrieves an assistant. - `"function"` - - `response_format: optional AssistantResponseFormatOption` + - `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -1368,7 +1368,7 @@ Retrieves an assistant. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -1382,11 +1382,11 @@ Retrieves an assistant. - `"json_schema"` - - `temperature: optional number` + - `temperature: optional number or null` 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. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -1402,7 +1402,7 @@ Retrieves an assistant. The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - - `top_p: optional number` + - `top_p: optional number or null` 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. @@ -1497,15 +1497,15 @@ Modifies an assistant. ### Body Parameters -- `description: optional string` +- `description: optional string or null` The description of the assistant. The maximum length is 512 characters. -- `instructions: optional string` +- `instructions: optional string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -1608,11 +1608,11 @@ Modifies an assistant. - `"gpt-3.5-turbo-16k-0613"` -- `name: optional string` +- `name: optional string or null` The name of the assistant. The maximum length is 256 characters. -- `reasoning_effort: optional ReasoningEffort` +- `reasoning_effort: optional ReasoningEffort or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -1636,7 +1636,7 @@ Modifies an assistant. - `"max"` -- `response_format: optional AssistantResponseFormatOption` +- `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -1699,7 +1699,7 @@ Modifies an assistant. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -1713,11 +1713,11 @@ Modifies an assistant. - `"json_schema"` -- `temperature: optional number` +- `temperature: optional number or null` 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. -- `tool_resources: optional object { code_interpreter, file_search }` +- `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -1799,7 +1799,7 @@ Modifies an assistant. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -1809,7 +1809,7 @@ Modifies an assistant. - `"function"` -- `top_p: optional number` +- `top_p: optional number or null` 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. @@ -1829,15 +1829,15 @@ Modifies an assistant. The Unix timestamp (in seconds) for when the assistant was created. - - `description: string` + - `description: string or null` The description of the assistant. The maximum length is 512 characters. - - `instructions: string` + - `instructions: string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -1850,7 +1850,7 @@ Modifies an assistant. ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. - - `name: string` + - `name: string or null` The name of the assistant. The maximum length is 256 characters. @@ -1926,7 +1926,7 @@ Modifies an assistant. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -1936,7 +1936,7 @@ Modifies an assistant. - `"function"` - - `response_format: optional AssistantResponseFormatOption` + - `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -1999,7 +1999,7 @@ Modifies an assistant. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -2013,11 +2013,11 @@ Modifies an assistant. - `"json_schema"` - - `temperature: optional number` + - `temperature: optional number or null` 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. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -2033,7 +2033,7 @@ Modifies an assistant. The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - - `top_p: optional number` + - `top_p: optional number or null` 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. @@ -2147,15 +2147,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the assistant was created. - - `description: string` + - `description: string or null` The description of the assistant. The maximum length is 512 characters. - - `instructions: string` + - `instructions: string or null` The system instructions that the assistant uses. The maximum length is 256,000 characters. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -2168,7 +2168,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. - - `name: string` + - `name: string or null` The name of the assistant. The maximum length is 256 characters. @@ -2244,7 +2244,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -2254,7 +2254,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"function"` - - `response_format: optional AssistantResponseFormatOption` + - `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -2317,7 +2317,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -2331,11 +2331,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"json_schema"` - - `temperature: optional number` + - `temperature: optional number or null` 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. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -2351,7 +2351,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. - - `top_p: optional number` + - `top_p: optional number or null` 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. @@ -2409,7 +2409,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -2424,7 +2424,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -2464,11 +2464,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -2476,15 +2476,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -2500,7 +2500,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -2518,15 +2518,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -2549,7 +2549,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -2589,7 +2589,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -2652,7 +2652,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -2666,7 +2666,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -2696,7 +2696,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -2800,7 +2800,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -2810,7 +2810,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -2822,11 +2822,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -2842,11 +2842,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -2978,11 +2978,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run step was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run step completed. @@ -2990,15 +2990,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the run step was created. - - `expired_at: number` + - `expired_at: number or null` The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run step failed. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run step. Will be `null` if there are no errors. @@ -3014,7 +3014,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ A human-readable description of the error. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -3209,7 +3209,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -3237,7 +3237,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"tool_calls"` - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. @@ -3433,7 +3433,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The name of the function. - - `output: optional string` + - `output: optional string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -3507,11 +3507,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -3533,7 +3533,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -3675,11 +3675,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -3697,7 +3697,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -3720,7 +3720,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -3980,11 +3980,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `data: ErrorObject` - - `code: string` + - `code: string or null` - `message: string` - - `param: string` + - `param: string or null` - `type: string` @@ -4072,7 +4072,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -4100,11 +4100,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -4132,7 +4132,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -4274,11 +4274,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -4296,7 +4296,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -4319,7 +4319,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -4595,11 +4595,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run step was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run step completed. @@ -4607,15 +4607,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the run step was created. - - `expired_at: number` + - `expired_at: number or null` The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run step failed. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run step. Will be `null` if there are no errors. @@ -4631,7 +4631,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ A human-readable description of the error. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -4826,7 +4826,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -4854,7 +4854,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"tool_calls"` - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. @@ -5050,7 +5050,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The name of the function. - - `output: optional string` + - `output: optional string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -5134,11 +5134,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -5146,15 +5146,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -5170,7 +5170,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -5188,15 +5188,15 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -5219,7 +5219,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -5259,7 +5259,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -5322,7 +5322,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -5336,7 +5336,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -5366,7 +5366,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -5470,7 +5470,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -5480,7 +5480,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -5492,11 +5492,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -5512,11 +5512,11 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -5650,7 +5650,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -5665,7 +5665,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -5703,7 +5703,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Identifier of the workflow backing the session. - - `state_variables: map[string or boolean or number]` + - `state_variables: map[string or boolean or number] or null` State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided. @@ -5721,7 +5721,7 @@ curl https://api.openai.com/v1/assistants/asst_abc123 \ Indicates whether tracing is enabled. - - `version: string` + - `version: string or null` Specific workflow version used for the session. Defaults to null when using the latest deployment. @@ -5769,11 +5769,11 @@ Cancelling prevents new requests from using the issued client secret. Indicates if uploads are enabled for the session. - - `max_file_size: number` + - `max_file_size: number or null` Maximum upload size in megabytes. - - `max_files: number` + - `max_files: number or null` Maximum number of uploads allowed during the session. @@ -5785,7 +5785,7 @@ Cancelling prevents new requests from using the issued client secret. Indicates if chat history is persisted for the session. - - `recent_threads: number` + - `recent_threads: number or null` Number of prior threads surfaced in history views. Defaults to null when all history is retained. @@ -5837,7 +5837,7 @@ Cancelling prevents new requests from using the issued client secret. Identifier of the workflow backing the session. - - `state_variables: map[string or boolean or number]` + - `state_variables: map[string or boolean or number] or null` State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided. @@ -5855,7 +5855,7 @@ Cancelling prevents new requests from using the issued client secret. Indicates whether tracing is enabled. - - `version: string` + - `version: string or null` Specific workflow version used for the session. Defaults to null when using the latest deployment. @@ -6072,11 +6072,11 @@ Create a ChatKit session. Indicates if uploads are enabled for the session. - - `max_file_size: number` + - `max_file_size: number or null` Maximum upload size in megabytes. - - `max_files: number` + - `max_files: number or null` Maximum number of uploads allowed during the session. @@ -6088,7 +6088,7 @@ Create a ChatKit session. Indicates if chat history is persisted for the session. - - `recent_threads: number` + - `recent_threads: number or null` Number of prior threads surfaced in history views. Defaults to null when all history is retained. @@ -6140,7 +6140,7 @@ Create a ChatKit session. Identifier of the workflow backing the session. - - `state_variables: map[string or boolean or number]` + - `state_variables: map[string or boolean or number] or null` State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided. @@ -6158,7 +6158,7 @@ Create a ChatKit session. Indicates whether tracing is enabled. - - `version: string` + - `version: string or null` Specific workflow version used for the session. Defaults to null when using the latest deployment. @@ -6377,7 +6377,7 @@ List ChatKit threads with optional pagination and user filters. Indicates that a thread is locked and cannot accept new input. - - `reason: string` + - `reason: string or null` Reason that the thread was locked. Defaults to null when no reason is recorded. @@ -6391,7 +6391,7 @@ List ChatKit threads with optional pagination and user filters. Indicates that a thread has been closed. - - `reason: string` + - `reason: string or null` Reason that the thread was closed. Defaults to null when no reason is recorded. @@ -6401,7 +6401,7 @@ List ChatKit threads with optional pagination and user filters. - `"closed"` - - `title: string` + - `title: string or null` Optional human-readable title for the thread. Defaults to null when no title has been generated. @@ -6409,7 +6409,7 @@ List ChatKit threads with optional pagination and user filters. Free-form string that identifies your end user who owns the thread. -- `first_id: string` +- `first_id: string or null` The ID of the first item in the list. @@ -6417,7 +6417,7 @@ List ChatKit threads with optional pagination and user filters. Whether there are more items available. -- `last_id: string` +- `last_id: string or null` The ID of the last item in the list. @@ -6553,7 +6553,7 @@ List items that belong to a ChatKit thread. Original display name for the attachment. - - `preview_url: string` + - `preview_url: string or null` Preview URL for rendering the attachment inline. @@ -6601,15 +6601,15 @@ List items that belong to a ChatKit thread. Unix timestamp (in seconds) for when the item was created. - - `inference_options: object { model, tool_choice }` + - `inference_options: object { model, tool_choice } or null` Inference overrides applied to the message. Defaults to null when unset. - - `model: string` + - `model: string or null` Model name that generated the response. Defaults to null when using the session default. - - `tool_choice: object { id }` + - `tool_choice: object { id } or null` Preferred tool to invoke. Defaults to null when ChatKit should auto-select. @@ -6787,7 +6787,7 @@ List items that belong to a ChatKit thread. - `"chatkit.thread_item"` - - `output: string` + - `output: string or null` JSON-encoded output captured from the tool. Defaults to null while execution is in progress. @@ -6821,7 +6821,7 @@ List items that belong to a ChatKit thread. Unix timestamp (in seconds) for when the item was created. - - `heading: string` + - `heading: string or null` Optional heading for the task. Defaults to null when not provided. @@ -6831,7 +6831,7 @@ List items that belong to a ChatKit thread. - `"chatkit.thread_item"` - - `summary: string` + - `summary: string or null` Optional summary that describes the task. Defaults to null when omitted. @@ -6875,11 +6875,11 @@ List items that belong to a ChatKit thread. Tasks included in the group. - - `heading: string` + - `heading: string or null` Optional heading for the grouped task. Defaults to null when not provided. - - `summary: string` + - `summary: string or null` Optional summary that describes the grouped task. Defaults to null when omitted. @@ -6901,7 +6901,7 @@ List items that belong to a ChatKit thread. - `"chatkit.task_group"` - - `first_id: string` + - `first_id: string or null` The ID of the first item in the list. @@ -6909,7 +6909,7 @@ List items that belong to a ChatKit thread. Whether there are more items available. - - `last_id: string` + - `last_id: string or null` The ID of the last item in the list. @@ -7058,7 +7058,7 @@ Retrieve a ChatKit thread by its identifier. Indicates that a thread is locked and cannot accept new input. - - `reason: string` + - `reason: string or null` Reason that the thread was locked. Defaults to null when no reason is recorded. @@ -7072,7 +7072,7 @@ Retrieve a ChatKit thread by its identifier. Indicates that a thread has been closed. - - `reason: string` + - `reason: string or null` Reason that the thread was closed. Defaults to null when no reason is recorded. @@ -7082,7 +7082,7 @@ Retrieve a ChatKit thread by its identifier. - `"closed"` - - `title: string` + - `title: string or null` Optional human-readable title for the thread. Defaults to null when no title has been generated. @@ -7191,11 +7191,11 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if uploads are enabled for the session. - - `max_file_size: number` + - `max_file_size: number or null` Maximum upload size in megabytes. - - `max_files: number` + - `max_files: number or null` Maximum number of uploads allowed during the session. @@ -7207,7 +7207,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if chat history is persisted for the session. - - `recent_threads: number` + - `recent_threads: number or null` Number of prior threads surfaced in history views. Defaults to null when all history is retained. @@ -7259,7 +7259,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Identifier of the workflow backing the session. - - `state_variables: map[string or boolean or number]` + - `state_variables: map[string or boolean or number] or null` State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided. @@ -7277,7 +7277,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates whether tracing is enabled. - - `version: string` + - `version: string or null` Specific workflow version used for the session. Defaults to null when using the latest deployment. @@ -7313,11 +7313,11 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if uploads are enabled for the session. - - `max_file_size: number` + - `max_file_size: number or null` Maximum upload size in megabytes. - - `max_files: number` + - `max_files: number or null` Maximum number of uploads allowed during the session. @@ -7329,7 +7329,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if chat history is persisted for the session. - - `recent_threads: number` + - `recent_threads: number or null` Number of prior threads surfaced in history views. Defaults to null when all history is retained. @@ -7401,11 +7401,11 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if uploads are enabled for the session. - - `max_file_size: number` + - `max_file_size: number or null` Maximum upload size in megabytes. - - `max_files: number` + - `max_files: number or null` Maximum number of uploads allowed during the session. @@ -7419,7 +7419,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates if chat history is persisted for the session. - - `recent_threads: number` + - `recent_threads: number or null` Number of prior threads surfaced in history views. Defaults to null when all history is retained. @@ -7503,7 +7503,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Original display name for the attachment. - - `preview_url: string` + - `preview_url: string or null` Preview URL for rendering the attachment inline. @@ -7621,7 +7621,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates that a thread is locked and cannot accept new input. - - `reason: string` + - `reason: string or null` Reason that the thread was locked. Defaults to null when no reason is recorded. @@ -7635,7 +7635,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Indicates that a thread has been closed. - - `reason: string` + - `reason: string or null` Reason that the thread was closed. Defaults to null when no reason is recorded. @@ -7645,7 +7645,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ - `"closed"` - - `title: string` + - `title: string or null` Optional human-readable title for the thread. Defaults to null when no title has been generated. @@ -7783,7 +7783,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Original display name for the attachment. - - `preview_url: string` + - `preview_url: string or null` Preview URL for rendering the attachment inline. @@ -7831,15 +7831,15 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Unix timestamp (in seconds) for when the item was created. - - `inference_options: object { model, tool_choice }` + - `inference_options: object { model, tool_choice } or null` Inference overrides applied to the message. Defaults to null when unset. - - `model: string` + - `model: string or null` Model name that generated the response. Defaults to null when using the session default. - - `tool_choice: object { id }` + - `tool_choice: object { id } or null` Preferred tool to invoke. Defaults to null when ChatKit should auto-select. @@ -8017,7 +8017,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ - `"chatkit.thread_item"` - - `output: string` + - `output: string or null` JSON-encoded output captured from the tool. Defaults to null while execution is in progress. @@ -8051,7 +8051,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Unix timestamp (in seconds) for when the item was created. - - `heading: string` + - `heading: string or null` Optional heading for the task. Defaults to null when not provided. @@ -8061,7 +8061,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ - `"chatkit.thread_item"` - - `summary: string` + - `summary: string or null` Optional summary that describes the task. Defaults to null when omitted. @@ -8105,11 +8105,11 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Tasks included in the group. - - `heading: string` + - `heading: string or null` Optional heading for the grouped task. Defaults to null when not provided. - - `summary: string` + - `summary: string or null` Optional summary that describes the grouped task. Defaults to null when omitted. @@ -8131,7 +8131,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ - `"chatkit.task_group"` - - `first_id: string` + - `first_id: string or null` The ID of the first item in the list. @@ -8139,7 +8139,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Whether there are more items available. - - `last_id: string` + - `last_id: string or null` The ID of the last item in the list. @@ -8175,7 +8175,7 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Original display name for the attachment. - - `preview_url: string` + - `preview_url: string or null` Preview URL for rendering the attachment inline. @@ -8223,15 +8223,15 @@ curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \ Unix timestamp (in seconds) for when the item was created. - - `inference_options: object { model, tool_choice }` + - `inference_options: object { model, tool_choice } or null` Inference overrides applied to the message. Defaults to null when unset. - - `model: string` + - `model: string or null` Model name that generated the response. Defaults to null when using the session default. - - `tool_choice: object { id }` + - `tool_choice: object { id } or null` Preferred tool to invoke. Defaults to null when ChatKit should auto-select. @@ -8339,7 +8339,7 @@ the `background` parameter set to `true` can be cancelled. Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -8391,7 +8391,7 @@ the `background` parameter set to `true` can be cancelled. A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -8403,7 +8403,7 @@ the `background` parameter set to `true` can be cancelled. - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -8489,11 +8489,11 @@ the `background` parameter set to `true` can be cancelled. - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -8531,7 +8531,7 @@ the `background` parameter set to `true` can be cancelled. The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -8566,7 +8566,7 @@ the `background` parameter set to `true` can be cancelled. - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -8603,7 +8603,7 @@ the `background` parameter set to `true` can be cancelled. - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -8807,7 +8807,7 @@ the `background` parameter set to `true` can be cancelled. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -8815,7 +8815,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -8859,7 +8859,7 @@ the `background` parameter set to `true` can be cancelled. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -8867,11 +8867,11 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -8922,11 +8922,11 @@ the `background` parameter set to `true` can be cancelled. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -8983,7 +8983,7 @@ the `background` parameter set to `true` can be cancelled. The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -8991,7 +8991,7 @@ the `background` parameter set to `true` can be cancelled. A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -9038,7 +9038,7 @@ the `background` parameter set to `true` can be cancelled. - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -9074,7 +9074,7 @@ the `background` parameter set to `true` can be cancelled. The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -9114,7 +9114,7 @@ the `background` parameter set to `true` can be cancelled. The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -9183,7 +9183,7 @@ the `background` parameter set to `true` can be cancelled. A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9224,11 +9224,11 @@ the `background` parameter set to `true` can be cancelled. - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -9236,15 +9236,15 @@ the `background` parameter set to `true` can be cancelled. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9252,7 +9252,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -9318,7 +9318,7 @@ the `background` parameter set to `true` can be cancelled. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -9358,7 +9358,7 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9393,7 +9393,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9401,7 +9401,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -9470,7 +9470,7 @@ the `background` parameter set to `true` can be cancelled. - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -9490,7 +9490,7 @@ the `background` parameter set to `true` can be cancelled. - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -9502,15 +9502,15 @@ the `background` parameter set to `true` can be cancelled. - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -9540,23 +9540,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -9572,11 +9572,11 @@ the `background` parameter set to `true` can be cancelled. - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9584,7 +9584,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -9608,15 +9608,15 @@ the `background` parameter set to `true` can be cancelled. - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -9670,11 +9670,11 @@ the `background` parameter set to `true` can be cancelled. - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9714,11 +9714,11 @@ the `background` parameter set to `true` can be cancelled. - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9844,11 +9844,11 @@ the `background` parameter set to `true` can be cancelled. - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9868,11 +9868,11 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -9880,7 +9880,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -9892,7 +9892,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -9916,11 +9916,11 @@ the `background` parameter set to `true` can be cancelled. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -9930,7 +9930,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -9942,11 +9942,11 @@ the `background` parameter set to `true` can be cancelled. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -9964,7 +9964,7 @@ the `background` parameter set to `true` can be cancelled. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -10179,11 +10179,11 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -10200,23 +10200,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -10241,7 +10241,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10249,7 +10249,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -10314,12 +10314,12 @@ the `background` parameter set to `true` can be cancelled. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -10409,7 +10409,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -10467,7 +10467,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10514,7 +10514,7 @@ the `background` parameter set to `true` can be cancelled. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -10629,7 +10629,7 @@ the `background` parameter set to `true` can be cancelled. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10637,7 +10637,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -10651,7 +10651,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -10777,7 +10777,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10853,7 +10853,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10865,15 +10865,15 @@ the `background` parameter set to `true` can be cancelled. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -10891,7 +10891,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -10959,7 +10959,7 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -10971,7 +10971,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -11003,7 +11003,7 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -11013,19 +11013,19 @@ the `background` parameter set to `true` can be cancelled. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -11039,7 +11039,7 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11053,11 +11053,11 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -11065,7 +11065,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -11077,7 +11077,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -11107,11 +11107,11 @@ the `background` parameter set to `true` can be cancelled. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -11121,7 +11121,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11133,11 +11133,11 @@ the `background` parameter set to `true` can be cancelled. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -11155,7 +11155,7 @@ the `background` parameter set to `true` can be cancelled. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -11370,11 +11370,11 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -11391,23 +11391,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -11432,7 +11432,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11440,7 +11440,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -11505,12 +11505,12 @@ the `background` parameter set to `true` can be cancelled. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -11600,7 +11600,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -11626,7 +11626,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11673,7 +11673,7 @@ the `background` parameter set to `true` can be cancelled. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -11788,7 +11788,7 @@ the `background` parameter set to `true` can be cancelled. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11796,7 +11796,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -11818,7 +11818,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11894,7 +11894,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -11906,15 +11906,15 @@ the `background` parameter set to `true` can be cancelled. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -11932,7 +11932,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -12000,7 +12000,7 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -12012,7 +12012,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -12044,7 +12044,7 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -12054,19 +12054,19 @@ the `background` parameter set to `true` can be cancelled. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -12080,7 +12080,7 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -12094,11 +12094,11 @@ the `background` parameter set to `true` can be cancelled. - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12137,7 +12137,7 @@ the `background` parameter set to `true` can be cancelled. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12159,7 +12159,7 @@ the `background` parameter set to `true` can be cancelled. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -12190,11 +12190,11 @@ the `background` parameter set to `true` can be cancelled. - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12210,7 +12210,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -12232,7 +12232,7 @@ the `background` parameter set to `true` can be cancelled. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12248,7 +12248,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -12256,7 +12256,7 @@ the `background` parameter set to `true` can be cancelled. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -12309,7 +12309,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12343,15 +12343,15 @@ the `background` parameter set to `true` can be cancelled. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -12375,7 +12375,7 @@ the `background` parameter set to `true` can be cancelled. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12401,7 +12401,7 @@ the `background` parameter set to `true` can be cancelled. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12409,7 +12409,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -12431,11 +12431,11 @@ the `background` parameter set to `true` can be cancelled. Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -12449,11 +12449,11 @@ the `background` parameter set to `true` can be cancelled. - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12461,7 +12461,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -12485,7 +12485,7 @@ the `background` parameter set to `true` can be cancelled. - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -12493,7 +12493,7 @@ the `background` parameter set to `true` can be cancelled. - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -12557,11 +12557,11 @@ the `background` parameter set to `true` can be cancelled. - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12569,7 +12569,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -12593,11 +12593,11 @@ the `background` parameter set to `true` can be cancelled. - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -12683,11 +12683,11 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12695,7 +12695,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -12741,11 +12741,11 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12753,7 +12753,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -12777,7 +12777,7 @@ the `background` parameter set to `true` can be cancelled. - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -12805,11 +12805,11 @@ the `background` parameter set to `true` can be cancelled. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -12819,7 +12819,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12827,7 +12827,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -12857,7 +12857,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12883,11 +12883,11 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12895,7 +12895,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -12925,7 +12925,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -12933,16 +12933,16 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -13003,7 +13003,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13011,7 +13011,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -13061,7 +13061,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13069,7 +13069,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -13103,7 +13103,7 @@ the `background` parameter set to `true` can be cancelled. - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13119,7 +13119,7 @@ the `background` parameter set to `true` can be cancelled. The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13127,7 +13127,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -13157,7 +13157,7 @@ the `background` parameter set to `true` can be cancelled. - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13193,7 +13193,7 @@ the `background` parameter set to `true` can be cancelled. - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13201,7 +13201,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -13471,7 +13471,7 @@ the `background` parameter set to `true` can be cancelled. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13479,11 +13479,11 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -13540,7 +13540,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13548,7 +13548,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -13635,7 +13635,7 @@ the `background` parameter set to `true` can be cancelled. - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -13643,7 +13643,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -13763,11 +13763,11 @@ the `background` parameter set to `true` can be cancelled. - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -13981,7 +13981,7 @@ the `background` parameter set to `true` can be cancelled. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -14021,7 +14021,7 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -14050,11 +14050,11 @@ the `background` parameter set to `true` can be cancelled. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -14084,7 +14084,7 @@ the `background` parameter set to `true` can be cancelled. Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -14134,15 +14134,15 @@ the `background` parameter set to `true` can be cancelled. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -14185,7 +14185,7 @@ the `background` parameter set to `true` can be cancelled. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -14207,7 +14207,7 @@ the `background` parameter set to `true` can be cancelled. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -14302,7 +14302,7 @@ the `background` parameter set to `true` can be cancelled. Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -14348,7 +14348,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -14382,11 +14382,11 @@ the `background` parameter set to `true` can be cancelled. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -14396,7 +14396,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -14408,11 +14408,11 @@ the `background` parameter set to `true` can be cancelled. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -14430,7 +14430,7 @@ the `background` parameter set to `true` can be cancelled. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -14645,11 +14645,11 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -14666,23 +14666,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -14707,7 +14707,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -14715,7 +14715,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -14780,12 +14780,12 @@ the `background` parameter set to `true` can be cancelled. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -14875,7 +14875,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -14901,7 +14901,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -14948,7 +14948,7 @@ the `background` parameter set to `true` can be cancelled. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -15063,7 +15063,7 @@ the `background` parameter set to `true` can be cancelled. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15071,7 +15071,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -15093,7 +15093,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15169,7 +15169,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15181,15 +15181,15 @@ the `background` parameter set to `true` can be cancelled. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -15207,7 +15207,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15275,7 +15275,7 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -15287,7 +15287,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -15319,7 +15319,7 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -15329,19 +15329,19 @@ the `background` parameter set to `true` can be cancelled. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -15355,7 +15355,7 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15419,11 +15419,11 @@ the `background` parameter set to `true` can be cancelled. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -15433,7 +15433,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15445,11 +15445,11 @@ the `background` parameter set to `true` can be cancelled. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -15467,7 +15467,7 @@ the `background` parameter set to `true` can be cancelled. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -15682,11 +15682,11 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -15703,23 +15703,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -15744,7 +15744,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15752,7 +15752,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -15817,12 +15817,12 @@ the `background` parameter set to `true` can be cancelled. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -15912,7 +15912,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -15938,7 +15938,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -15985,7 +15985,7 @@ the `background` parameter set to `true` can be cancelled. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -16100,7 +16100,7 @@ the `background` parameter set to `true` can be cancelled. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -16108,7 +16108,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -16130,7 +16130,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -16206,7 +16206,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -16218,15 +16218,15 @@ the `background` parameter set to `true` can be cancelled. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -16244,7 +16244,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -16312,7 +16312,7 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -16324,7 +16324,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -16356,7 +16356,7 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -16366,19 +16366,19 @@ the `background` parameter set to `true` can be cancelled. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -16392,7 +16392,7 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -16452,7 +16452,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -16474,7 +16474,7 @@ the `background` parameter set to `true` can be cancelled. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -16490,7 +16490,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -16498,7 +16498,7 @@ the `background` parameter set to `true` can be cancelled. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -16551,7 +16551,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -16585,15 +16585,15 @@ the `background` parameter set to `true` can be cancelled. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -16617,7 +16617,7 @@ the `background` parameter set to `true` can be cancelled. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -16643,7 +16643,7 @@ the `background` parameter set to `true` can be cancelled. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -16651,7 +16651,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -16675,11 +16675,11 @@ the `background` parameter set to `true` can be cancelled. - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -16687,7 +16687,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -16737,7 +16737,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -16773,7 +16773,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -16845,7 +16845,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -16957,7 +16957,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -17015,7 +17015,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -17039,7 +17039,7 @@ the `background` parameter set to `true` can be cancelled. The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -17069,7 +17069,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17077,16 +17077,16 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -17128,11 +17128,11 @@ the `background` parameter set to `true` can be cancelled. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -17142,7 +17142,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17150,7 +17150,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -17180,7 +17180,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17210,7 +17210,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17218,7 +17218,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -17248,7 +17248,7 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17256,7 +17256,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -17332,7 +17332,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -17340,7 +17340,7 @@ the `background` parameter set to `true` can be cancelled. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -17372,7 +17372,7 @@ the `background` parameter set to `true` can be cancelled. Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -17501,7 +17501,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -17575,11 +17575,11 @@ the `background` parameter set to `true` can be cancelled. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -17589,7 +17589,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -17601,11 +17601,11 @@ the `background` parameter set to `true` can be cancelled. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -17623,7 +17623,7 @@ the `background` parameter set to `true` can be cancelled. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -17838,11 +17838,11 @@ the `background` parameter set to `true` can be cancelled. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -17859,23 +17859,23 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -17900,7 +17900,7 @@ the `background` parameter set to `true` can be cancelled. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -17908,7 +17908,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -17973,12 +17973,12 @@ the `background` parameter set to `true` can be cancelled. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -18068,7 +18068,7 @@ the `background` parameter set to `true` can be cancelled. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -18094,7 +18094,7 @@ the `background` parameter set to `true` can be cancelled. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18141,7 +18141,7 @@ the `background` parameter set to `true` can be cancelled. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -18256,7 +18256,7 @@ the `background` parameter set to `true` can be cancelled. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18264,7 +18264,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -18286,7 +18286,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18362,7 +18362,7 @@ the `background` parameter set to `true` can be cancelled. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18374,15 +18374,15 @@ the `background` parameter set to `true` can be cancelled. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -18400,7 +18400,7 @@ the `background` parameter set to `true` can be cancelled. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18468,7 +18468,7 @@ the `background` parameter set to `true` can be cancelled. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -18480,7 +18480,7 @@ the `background` parameter set to `true` can be cancelled. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -18512,7 +18512,7 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -18522,19 +18522,19 @@ the `background` parameter set to `true` can be cancelled. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -18548,7 +18548,7 @@ the `background` parameter set to `true` can be cancelled. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -18556,7 +18556,7 @@ the `background` parameter set to `true` can be cancelled. - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -18565,17 +18565,17 @@ the `background` parameter set to `true` can be cancelled. We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -18583,15 +18583,15 @@ the `background` parameter set to `true` can be cancelled. The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -18707,19 +18707,19 @@ the `background` parameter set to `true` can be cancelled. - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -18728,7 +18728,7 @@ the `background` parameter set to `true` can be cancelled. The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -18748,11 +18748,11 @@ the `background` parameter set to `true` can be cancelled. A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -18774,7 +18774,7 @@ the `background` parameter set to `true` can be cancelled. - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -18793,14 +18793,14 @@ the `background` parameter set to `true` can be cancelled. - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -18816,7 +18816,7 @@ the `background` parameter set to `true` can be cancelled. - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -18840,7 +18840,7 @@ the `background` parameter set to `true` can be cancelled. - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -18872,7 +18872,7 @@ the `background` parameter set to `true` can be cancelled. - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -18886,12 +18886,12 @@ the `background` parameter set to `true` can be cancelled. - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -18992,7 +18992,7 @@ the `background` parameter set to `true` can be cancelled. A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -19013,7 +19013,7 @@ the `background` parameter set to `true` can be cancelled. - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -19026,14 +19026,14 @@ the `background` parameter set to `true` can be cancelled. - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -19351,7 +19351,7 @@ Learn when and how to compact long-running conversations in the [conversation st ### Body Parameters -- `model: "gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 more or string` +- `model: "gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 more or string or null` Model ID used to generate the response, like `gpt-5` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](/docs/models) to browse and compare available models. @@ -19551,7 +19551,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `string` -- `input: optional string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` +- `input: optional string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` Text, image, or file inputs to the model, used to generate a response @@ -19631,11 +19631,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -19673,7 +19673,7 @@ Learn when and how to compact long-running conversations in the [conversation st The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -19708,7 +19708,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -19745,7 +19745,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -19949,7 +19949,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -19957,7 +19957,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -20001,7 +20001,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20009,11 +20009,11 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -20064,11 +20064,11 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -20125,7 +20125,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -20133,7 +20133,7 @@ Learn when and how to compact long-running conversations in the [conversation st A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -20180,7 +20180,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -20216,7 +20216,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -20256,7 +20256,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -20325,7 +20325,7 @@ Learn when and how to compact long-running conversations in the [conversation st A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20366,11 +20366,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -20378,15 +20378,15 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20394,7 +20394,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -20460,7 +20460,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -20500,7 +20500,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20535,7 +20535,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20543,7 +20543,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -20612,7 +20612,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -20632,7 +20632,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -20644,15 +20644,15 @@ Learn when and how to compact long-running conversations in the [conversation st - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -20682,23 +20682,23 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -20714,11 +20714,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20726,7 +20726,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -20750,15 +20750,15 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -20812,11 +20812,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20856,11 +20856,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -20986,11 +20986,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -21010,11 +21010,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -21022,7 +21022,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -21034,7 +21034,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -21058,11 +21058,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -21072,7 +21072,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -21084,11 +21084,11 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -21106,7 +21106,7 @@ Learn when and how to compact long-running conversations in the [conversation st The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -21321,11 +21321,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -21342,23 +21342,23 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -21383,7 +21383,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -21391,7 +21391,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -21456,12 +21456,12 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -21551,7 +21551,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -21609,7 +21609,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -21656,7 +21656,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -21771,7 +21771,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -21779,7 +21779,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -21793,7 +21793,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -21919,7 +21919,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -21995,7 +21995,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22007,15 +22007,15 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -22033,7 +22033,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22101,7 +22101,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -22113,7 +22113,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -22145,7 +22145,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -22155,19 +22155,19 @@ Learn when and how to compact long-running conversations in the [conversation st - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -22181,7 +22181,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22195,11 +22195,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -22207,7 +22207,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -22219,7 +22219,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -22249,11 +22249,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -22263,7 +22263,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22275,11 +22275,11 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -22297,7 +22297,7 @@ Learn when and how to compact long-running conversations in the [conversation st The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -22512,11 +22512,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -22533,23 +22533,23 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -22574,7 +22574,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22582,7 +22582,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -22647,12 +22647,12 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -22742,7 +22742,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -22768,7 +22768,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22815,7 +22815,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -22930,7 +22930,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -22938,7 +22938,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -22960,7 +22960,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -23036,7 +23036,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -23048,15 +23048,15 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -23074,7 +23074,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -23142,7 +23142,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -23154,7 +23154,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -23186,7 +23186,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -23196,19 +23196,19 @@ Learn when and how to compact long-running conversations in the [conversation st - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -23222,7 +23222,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -23236,11 +23236,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23279,7 +23279,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23301,7 +23301,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -23332,11 +23332,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23352,7 +23352,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -23374,7 +23374,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23390,7 +23390,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -23398,7 +23398,7 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -23451,7 +23451,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23485,15 +23485,15 @@ Learn when and how to compact long-running conversations in the [conversation st - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -23517,7 +23517,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23543,7 +23543,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23551,7 +23551,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -23573,11 +23573,11 @@ Learn when and how to compact long-running conversations in the [conversation st Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -23591,11 +23591,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23603,7 +23603,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -23627,7 +23627,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -23635,7 +23635,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -23699,11 +23699,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23711,7 +23711,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -23735,11 +23735,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -23825,11 +23825,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23837,7 +23837,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -23883,11 +23883,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23895,7 +23895,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -23919,7 +23919,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -23947,11 +23947,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -23961,7 +23961,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -23969,7 +23969,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -23999,7 +23999,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24025,11 +24025,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24037,7 +24037,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -24067,7 +24067,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24075,16 +24075,16 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -24145,7 +24145,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24153,7 +24153,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -24203,7 +24203,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24211,7 +24211,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -24245,7 +24245,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24261,7 +24261,7 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24269,7 +24269,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -24299,7 +24299,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24335,7 +24335,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24343,20 +24343,20 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. -- `instructions: optional string` +- `instructions: optional string or null` A system (or developer) message inserted into the model's context. When used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -- `previous_response_id: optional string` +- `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. -- `prompt_cache_key: optional string` +- `prompt_cache_key: optional string or null` A key to use when reading from or writing to the prompt cache. -- `prompt_cache_options: optional object { mode, ttl }` +- `prompt_cache_options: optional object { mode, ttl } or null` Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](/docs/guides/prompt-caching) for current details. @@ -24374,7 +24374,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"30m"` -- `prompt_cache_retention: optional "in_memory" or "24h"` +- `prompt_cache_retention: optional "in_memory" or "24h" or null` How long to retain a prompt cache entry created by this request. @@ -24382,7 +24382,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"24h"` -- `service_tier: optional "auto" or "default" or "fast" or 2 more` +- `service_tier: optional "auto" or "default" or "fast" or 2 more or null` Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier. - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. @@ -24659,11 +24659,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -24693,11 +24693,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -24741,7 +24741,7 @@ Learn when and how to compact long-running conversations in the [conversation st The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -24821,7 +24821,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. @@ -24924,7 +24924,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -24932,7 +24932,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -25079,7 +25079,7 @@ Learn when and how to compact long-running conversations in the [conversation st Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -25125,7 +25125,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -25159,11 +25159,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -25173,7 +25173,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -25185,11 +25185,11 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -25207,7 +25207,7 @@ Learn when and how to compact long-running conversations in the [conversation st The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -25422,11 +25422,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -25443,23 +25443,23 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -25484,7 +25484,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -25492,7 +25492,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -25557,12 +25557,12 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -25652,7 +25652,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -25710,7 +25710,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -25757,7 +25757,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -25872,7 +25872,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -25880,7 +25880,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -25894,7 +25894,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -26020,7 +26020,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26096,7 +26096,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26108,15 +26108,15 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -26134,7 +26134,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26202,7 +26202,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -26214,7 +26214,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -26246,7 +26246,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -26256,19 +26256,19 @@ Learn when and how to compact long-running conversations in the [conversation st - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -26282,7 +26282,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26346,11 +26346,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -26360,7 +26360,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26372,11 +26372,11 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -26394,7 +26394,7 @@ Learn when and how to compact long-running conversations in the [conversation st The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -26609,11 +26609,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -26630,23 +26630,23 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -26671,7 +26671,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26679,7 +26679,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -26744,12 +26744,12 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -26839,7 +26839,7 @@ Learn when and how to compact long-running conversations in the [conversation st An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -26865,7 +26865,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -26912,7 +26912,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -27027,7 +27027,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -27035,7 +27035,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -27057,7 +27057,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -27133,7 +27133,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -27145,15 +27145,15 @@ Learn when and how to compact long-running conversations in the [conversation st Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -27171,7 +27171,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -27239,7 +27239,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -27251,7 +27251,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -27283,7 +27283,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -27293,19 +27293,19 @@ Learn when and how to compact long-running conversations in the [conversation st - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -27319,7 +27319,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -27425,11 +27425,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -27529,7 +27529,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -27537,7 +27537,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -27614,7 +27614,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -27622,11 +27622,11 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -27712,7 +27712,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -27752,7 +27752,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -27768,7 +27768,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -27790,7 +27790,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -27819,11 +27819,11 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -27880,7 +27880,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -27888,7 +27888,7 @@ Learn when and how to compact long-running conversations in the [conversation st A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -27935,7 +27935,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -27971,7 +27971,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -28011,7 +28011,7 @@ Learn when and how to compact long-running conversations in the [conversation st The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -28080,7 +28080,7 @@ Learn when and how to compact long-running conversations in the [conversation st A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28145,15 +28145,15 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28196,7 +28196,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28218,7 +28218,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -28273,7 +28273,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -28281,7 +28281,7 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -28334,7 +28334,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28368,15 +28368,15 @@ Learn when and how to compact long-running conversations in the [conversation st - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -28400,7 +28400,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28426,7 +28426,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28434,7 +28434,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -28458,11 +28458,11 @@ Learn when and how to compact long-running conversations in the [conversation st - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -28470,7 +28470,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -28520,7 +28520,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -28556,7 +28556,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -28628,7 +28628,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -28740,7 +28740,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -28798,7 +28798,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -28822,7 +28822,7 @@ Learn when and how to compact long-running conversations in the [conversation st The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -28850,11 +28850,11 @@ Learn when and how to compact long-running conversations in the [conversation st The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -28864,7 +28864,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28872,7 +28872,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -28902,7 +28902,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28932,7 +28932,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28940,7 +28940,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -28970,7 +28970,7 @@ Learn when and how to compact long-running conversations in the [conversation st - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -28978,16 +28978,16 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -29031,7 +29031,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -29039,7 +29039,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -29106,7 +29106,7 @@ Learn when and how to compact long-running conversations in the [conversation st The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -29114,7 +29114,7 @@ Learn when and how to compact long-running conversations in the [conversation st The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -29322,12 +29322,12 @@ as input for the model's response. ### Body Parameters -- `background: optional boolean` +- `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). -- `context_management: optional array of object { type, compact_threshold }` +- `context_management: optional array of object { type, compact_threshold } or null` Context management configuration for this request. @@ -29335,11 +29335,11 @@ as input for the model's response. The context management entry type. Currently only 'compaction' is supported. - - `compact_threshold: optional number` + - `compact_threshold: optional number or null` Token threshold at which compaction should be triggered for this entry. -- `conversation: optional string or BetaResponseConversationParam` +- `conversation: optional string or BetaResponseConversationParam or null` The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. @@ -29356,7 +29356,7 @@ as input for the model's response. The unique ID of the conversation. -- `include: optional array of BetaResponseIncludable` +- `include: optional array of BetaResponseIncludable or null` Specify additional output data to include in the model response. Currently supported values are: @@ -29474,11 +29474,11 @@ as input for the model's response. - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -29516,7 +29516,7 @@ as input for the model's response. The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -29551,7 +29551,7 @@ as input for the model's response. - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -29588,7 +29588,7 @@ as input for the model's response. - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -29792,7 +29792,7 @@ as input for the model's response. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -29800,7 +29800,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -29844,7 +29844,7 @@ as input for the model's response. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -29852,11 +29852,11 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -29907,11 +29907,11 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -29968,7 +29968,7 @@ as input for the model's response. The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -29976,7 +29976,7 @@ as input for the model's response. A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -30023,7 +30023,7 @@ as input for the model's response. - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -30059,7 +30059,7 @@ as input for the model's response. The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -30099,7 +30099,7 @@ as input for the model's response. The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -30168,7 +30168,7 @@ as input for the model's response. A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30209,11 +30209,11 @@ as input for the model's response. - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -30221,15 +30221,15 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30237,7 +30237,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -30303,7 +30303,7 @@ as input for the model's response. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -30343,7 +30343,7 @@ as input for the model's response. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30378,7 +30378,7 @@ as input for the model's response. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30386,7 +30386,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -30455,7 +30455,7 @@ as input for the model's response. - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -30475,7 +30475,7 @@ as input for the model's response. - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -30487,15 +30487,15 @@ as input for the model's response. - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -30525,23 +30525,23 @@ as input for the model's response. - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -30557,11 +30557,11 @@ as input for the model's response. - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30569,7 +30569,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -30593,15 +30593,15 @@ as input for the model's response. - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -30655,11 +30655,11 @@ as input for the model's response. - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30699,11 +30699,11 @@ as input for the model's response. - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30829,11 +30829,11 @@ as input for the model's response. - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30853,11 +30853,11 @@ as input for the model's response. - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -30865,7 +30865,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -30877,7 +30877,7 @@ as input for the model's response. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -30901,11 +30901,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -30915,7 +30915,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -30927,11 +30927,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -30949,7 +30949,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -31164,11 +31164,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -31185,23 +31185,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -31226,7 +31226,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31234,7 +31234,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -31299,12 +31299,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -31394,7 +31394,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -31452,7 +31452,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31499,7 +31499,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -31614,7 +31614,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31622,7 +31622,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -31636,7 +31636,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -31762,7 +31762,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31838,7 +31838,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31850,15 +31850,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -31876,7 +31876,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -31944,7 +31944,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -31956,7 +31956,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -31988,7 +31988,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -31998,19 +31998,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -32024,7 +32024,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32038,11 +32038,11 @@ as input for the model's response. - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -32050,7 +32050,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -32062,7 +32062,7 @@ as input for the model's response. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -32092,11 +32092,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -32106,7 +32106,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32118,11 +32118,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -32140,7 +32140,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -32355,11 +32355,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -32376,23 +32376,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -32417,7 +32417,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32425,7 +32425,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -32490,12 +32490,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -32585,7 +32585,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -32611,7 +32611,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32658,7 +32658,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -32773,7 +32773,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32781,7 +32781,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -32803,7 +32803,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32879,7 +32879,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32891,15 +32891,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -32917,7 +32917,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -32985,7 +32985,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -32997,7 +32997,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -33029,7 +33029,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -33039,19 +33039,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -33065,7 +33065,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -33079,11 +33079,11 @@ as input for the model's response. - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33122,7 +33122,7 @@ as input for the model's response. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33144,7 +33144,7 @@ as input for the model's response. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -33175,11 +33175,11 @@ as input for the model's response. - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33195,7 +33195,7 @@ as input for the model's response. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -33217,7 +33217,7 @@ as input for the model's response. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33233,7 +33233,7 @@ as input for the model's response. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -33241,7 +33241,7 @@ as input for the model's response. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -33294,7 +33294,7 @@ as input for the model's response. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33328,15 +33328,15 @@ as input for the model's response. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -33360,7 +33360,7 @@ as input for the model's response. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33386,7 +33386,7 @@ as input for the model's response. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33394,7 +33394,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -33416,11 +33416,11 @@ as input for the model's response. Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -33434,11 +33434,11 @@ as input for the model's response. - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33446,7 +33446,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -33470,7 +33470,7 @@ as input for the model's response. - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -33478,7 +33478,7 @@ as input for the model's response. - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -33542,11 +33542,11 @@ as input for the model's response. - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33554,7 +33554,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -33578,11 +33578,11 @@ as input for the model's response. - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -33668,11 +33668,11 @@ as input for the model's response. - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33680,7 +33680,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -33726,11 +33726,11 @@ as input for the model's response. - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33738,7 +33738,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -33762,7 +33762,7 @@ as input for the model's response. - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -33790,11 +33790,11 @@ as input for the model's response. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -33804,7 +33804,7 @@ as input for the model's response. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33812,7 +33812,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -33842,7 +33842,7 @@ as input for the model's response. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33868,11 +33868,11 @@ as input for the model's response. - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33880,7 +33880,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -33910,7 +33910,7 @@ as input for the model's response. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33918,16 +33918,16 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -33988,7 +33988,7 @@ as input for the model's response. The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -33996,7 +33996,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -34046,7 +34046,7 @@ as input for the model's response. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -34054,7 +34054,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -34088,7 +34088,7 @@ as input for the model's response. - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -34104,7 +34104,7 @@ as input for the model's response. The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -34112,7 +34112,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -34142,7 +34142,7 @@ as input for the model's response. - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -34178,7 +34178,7 @@ as input for the model's response. - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -34186,7 +34186,7 @@ as input for the model's response. The canonical name of the agent that produced this item. -- `instructions: optional string` +- `instructions: optional string or null` A system (or developer) message inserted into the model's context. @@ -34194,15 +34194,15 @@ as input for the model's response. response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -- `max_output_tokens: optional number` +- `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). -- `max_tool_calls: optional number` +- `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. -- `metadata: optional map[string]` +- `metadata: optional map[string] or null` 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 @@ -34417,7 +34417,7 @@ as input for the model's response. - `string` -- `moderation: optional object { model, policy }` +- `moderation: optional object { model, policy } or null` Configuration for running moderation on the input and output of this response. @@ -34425,11 +34425,11 @@ as input for the model's response. The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'. - - `policy: optional object { input, output }` + - `policy: optional object { input, output } or null` The policy to apply to moderated response input and output. - - `input: optional object { mode }` + - `input: optional object { mode } or null` The moderation policy for the response input. @@ -34439,7 +34439,7 @@ as input for the model's response. - `"block"` - - `output: optional object { mode }` + - `output: optional object { mode } or null` The moderation policy for the response output. @@ -34449,7 +34449,7 @@ as input for the model's response. - `"block"` -- `multi_agent: optional object { enabled, max_concurrent_subagents }` +- `multi_agent: optional object { enabled, max_concurrent_subagents } or null` Configuration for server-hosted multi-agent execution. @@ -34462,17 +34462,17 @@ as input for the model's response. `max_concurrent_subagents` sets the maximum number of subagents that can be active simultaneously across the entire agent tree. It includes all descendants—children, grandchildren, and deeper subagents—but excludes the root agent. The API does not impose a fixed upper bound on this setting. The default is `3`, which is recommended for most workloads. Multi-agent runs also have no fixed limit on tree depth or the total number of subagents created during a run. -- `parallel_tool_calls: optional boolean` +- `parallel_tool_calls: optional boolean or null` Whether to allow the model to run tool calls in parallel. -- `previous_response_id: optional string` +- `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. -- `prompt: optional BetaResponsePrompt` +- `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -34481,7 +34481,7 @@ as input for the model's response. The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -34501,11 +34501,11 @@ as input for the model's response. A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. -- `prompt_cache_key: optional string` +- `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -34527,7 +34527,7 @@ as input for the model's response. - `"30m"` -- `prompt_cache_retention: optional "in_memory" or "24h"` +- `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -34546,14 +34546,14 @@ as input for the model's response. - `"24h"` -- `reasoning: optional object { context, effort, generate_summary, 2 more }` +- `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -34569,7 +34569,7 @@ as input for the model's response. - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -34593,7 +34593,7 @@ as input for the model's response. - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -34625,7 +34625,7 @@ as input for the model's response. - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -34639,12 +34639,12 @@ as input for the model's response. - `"detailed"` -- `safety_identifier: optional string` +- `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). -- `service_tier: optional "auto" or "default" or "flex" or 3 more` +- `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -34668,19 +34668,19 @@ as input for the model's response. - `"fast"` -- `store: optional boolean` +- `store: optional boolean or null` Whether to store the generated model response for later retrieval via API. -- `stream: optional boolean` +- `stream: optional boolean or null` If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](/docs/api-reference/responses-streaming) for more information. -- `stream_options: optional object { include_obfuscation }` +- `stream_options: optional object { include_obfuscation } or null` Options for streaming responses. Only set this when you set `stream: true`. @@ -34694,7 +34694,7 @@ as input for the model's response. false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. -- `temperature: optional number` +- `temperature: optional number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -34759,7 +34759,7 @@ as input for the model's response. A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -34780,7 +34780,7 @@ as input for the model's response. - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -34917,7 +34917,7 @@ as input for the model's response. - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -34991,11 +34991,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -35005,7 +35005,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35017,11 +35017,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -35039,7 +35039,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -35254,11 +35254,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -35275,23 +35275,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -35316,7 +35316,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35324,7 +35324,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -35389,12 +35389,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -35484,7 +35484,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -35510,7 +35510,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35557,7 +35557,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -35672,7 +35672,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35680,7 +35680,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -35702,7 +35702,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35778,7 +35778,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35790,15 +35790,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -35816,7 +35816,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35884,7 +35884,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -35896,7 +35896,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -35928,7 +35928,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -35938,19 +35938,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -35964,7 +35964,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -35972,14 +35972,14 @@ as input for the model's response. - `"programmatic"` -- `top_logprobs: optional number` +- `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. -- `top_p: optional number` +- `top_p: optional number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -35988,7 +35988,7 @@ as input for the model's response. We generally recommend altering this or `temperature` but not both. -- `truncation: optional "auto" or "disabled"` +- `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -36020,7 +36020,7 @@ as input for the model's response. Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -36072,7 +36072,7 @@ as input for the model's response. A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -36084,7 +36084,7 @@ as input for the model's response. - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -36170,11 +36170,11 @@ as input for the model's response. - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -36212,7 +36212,7 @@ as input for the model's response. The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -36247,7 +36247,7 @@ as input for the model's response. - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -36284,7 +36284,7 @@ as input for the model's response. - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -36488,7 +36488,7 @@ as input for the model's response. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -36496,7 +36496,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -36540,7 +36540,7 @@ as input for the model's response. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -36548,11 +36548,11 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -36603,11 +36603,11 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -36664,7 +36664,7 @@ as input for the model's response. The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -36672,7 +36672,7 @@ as input for the model's response. A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -36719,7 +36719,7 @@ as input for the model's response. - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -36755,7 +36755,7 @@ as input for the model's response. The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -36795,7 +36795,7 @@ as input for the model's response. The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -36864,7 +36864,7 @@ as input for the model's response. A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -36905,11 +36905,11 @@ as input for the model's response. - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -36917,15 +36917,15 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -36933,7 +36933,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -36999,7 +36999,7 @@ as input for the model's response. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -37039,7 +37039,7 @@ as input for the model's response. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37074,7 +37074,7 @@ as input for the model's response. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37082,7 +37082,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -37151,7 +37151,7 @@ as input for the model's response. - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -37171,7 +37171,7 @@ as input for the model's response. - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -37183,15 +37183,15 @@ as input for the model's response. - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -37221,23 +37221,23 @@ as input for the model's response. - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -37253,11 +37253,11 @@ as input for the model's response. - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37265,7 +37265,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -37289,15 +37289,15 @@ as input for the model's response. - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -37351,11 +37351,11 @@ as input for the model's response. - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37395,11 +37395,11 @@ as input for the model's response. - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37525,11 +37525,11 @@ as input for the model's response. - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37549,11 +37549,11 @@ as input for the model's response. - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -37561,7 +37561,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -37573,7 +37573,7 @@ as input for the model's response. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -37597,11 +37597,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -37611,7 +37611,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -37623,11 +37623,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -37645,7 +37645,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -37860,11 +37860,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -37881,23 +37881,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -37922,7 +37922,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -37930,7 +37930,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -37995,12 +37995,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -38090,7 +38090,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -38148,7 +38148,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38195,7 +38195,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -38310,7 +38310,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38318,7 +38318,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -38332,7 +38332,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -38458,7 +38458,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38534,7 +38534,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38546,15 +38546,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -38572,7 +38572,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38640,7 +38640,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -38652,7 +38652,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -38684,7 +38684,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -38694,19 +38694,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -38720,7 +38720,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38734,11 +38734,11 @@ as input for the model's response. - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -38746,7 +38746,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -38758,7 +38758,7 @@ as input for the model's response. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -38788,11 +38788,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -38802,7 +38802,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -38814,11 +38814,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -38836,7 +38836,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -39051,11 +39051,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -39072,23 +39072,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -39113,7 +39113,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39121,7 +39121,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -39186,12 +39186,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -39281,7 +39281,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -39307,7 +39307,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39354,7 +39354,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -39469,7 +39469,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39477,7 +39477,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -39499,7 +39499,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39575,7 +39575,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39587,15 +39587,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -39613,7 +39613,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39681,7 +39681,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -39693,7 +39693,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -39725,7 +39725,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -39735,19 +39735,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -39761,7 +39761,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -39775,11 +39775,11 @@ as input for the model's response. - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -39818,7 +39818,7 @@ as input for the model's response. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -39840,7 +39840,7 @@ as input for the model's response. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -39871,11 +39871,11 @@ as input for the model's response. - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -39891,7 +39891,7 @@ as input for the model's response. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -39913,7 +39913,7 @@ as input for the model's response. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -39929,7 +39929,7 @@ as input for the model's response. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -39937,7 +39937,7 @@ as input for the model's response. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -39990,7 +39990,7 @@ as input for the model's response. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40024,15 +40024,15 @@ as input for the model's response. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -40056,7 +40056,7 @@ as input for the model's response. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40082,7 +40082,7 @@ as input for the model's response. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40090,7 +40090,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -40112,11 +40112,11 @@ as input for the model's response. Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -40130,11 +40130,11 @@ as input for the model's response. - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40142,7 +40142,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40166,7 +40166,7 @@ as input for the model's response. - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -40174,7 +40174,7 @@ as input for the model's response. - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -40238,11 +40238,11 @@ as input for the model's response. - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40250,7 +40250,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40274,11 +40274,11 @@ as input for the model's response. - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -40364,11 +40364,11 @@ as input for the model's response. - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40376,7 +40376,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40422,11 +40422,11 @@ as input for the model's response. - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40434,7 +40434,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40458,7 +40458,7 @@ as input for the model's response. - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -40486,11 +40486,11 @@ as input for the model's response. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -40500,7 +40500,7 @@ as input for the model's response. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40508,7 +40508,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -40538,7 +40538,7 @@ as input for the model's response. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40564,11 +40564,11 @@ as input for the model's response. - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40576,7 +40576,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -40606,7 +40606,7 @@ as input for the model's response. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40614,16 +40614,16 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -40684,7 +40684,7 @@ as input for the model's response. The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40692,7 +40692,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40742,7 +40742,7 @@ as input for the model's response. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40750,7 +40750,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -40784,7 +40784,7 @@ as input for the model's response. - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40800,7 +40800,7 @@ as input for the model's response. The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40808,7 +40808,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -40838,7 +40838,7 @@ as input for the model's response. - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40874,7 +40874,7 @@ as input for the model's response. - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -40882,7 +40882,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -41152,7 +41152,7 @@ as input for the model's response. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41160,11 +41160,11 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -41221,7 +41221,7 @@ as input for the model's response. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41229,7 +41229,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -41316,7 +41316,7 @@ as input for the model's response. - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41324,7 +41324,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -41444,11 +41444,11 @@ as input for the model's response. - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -41662,7 +41662,7 @@ as input for the model's response. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -41702,7 +41702,7 @@ as input for the model's response. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41731,11 +41731,11 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -41765,7 +41765,7 @@ as input for the model's response. Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41815,15 +41815,15 @@ as input for the model's response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41866,7 +41866,7 @@ as input for the model's response. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -41888,7 +41888,7 @@ as input for the model's response. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -41983,7 +41983,7 @@ as input for the model's response. Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -42029,7 +42029,7 @@ as input for the model's response. The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -42063,11 +42063,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -42077,7 +42077,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42089,11 +42089,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -42111,7 +42111,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -42326,11 +42326,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -42347,23 +42347,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -42388,7 +42388,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42396,7 +42396,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -42461,12 +42461,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -42556,7 +42556,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -42582,7 +42582,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42629,7 +42629,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -42744,7 +42744,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42752,7 +42752,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -42774,7 +42774,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42850,7 +42850,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42862,15 +42862,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -42888,7 +42888,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -42956,7 +42956,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -42968,7 +42968,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -43000,7 +43000,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -43010,19 +43010,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -43036,7 +43036,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43100,11 +43100,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -43114,7 +43114,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43126,11 +43126,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -43148,7 +43148,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -43363,11 +43363,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -43384,23 +43384,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -43425,7 +43425,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43433,7 +43433,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -43498,12 +43498,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -43593,7 +43593,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -43619,7 +43619,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43666,7 +43666,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -43781,7 +43781,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43789,7 +43789,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -43811,7 +43811,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43887,7 +43887,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43899,15 +43899,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -43925,7 +43925,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -43993,7 +43993,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -44005,7 +44005,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -44037,7 +44037,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -44047,19 +44047,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -44073,7 +44073,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -44133,7 +44133,7 @@ as input for the model's response. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -44155,7 +44155,7 @@ as input for the model's response. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44171,7 +44171,7 @@ as input for the model's response. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -44179,7 +44179,7 @@ as input for the model's response. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -44232,7 +44232,7 @@ as input for the model's response. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44266,15 +44266,15 @@ as input for the model's response. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -44298,7 +44298,7 @@ as input for the model's response. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44324,7 +44324,7 @@ as input for the model's response. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44332,7 +44332,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -44356,11 +44356,11 @@ as input for the model's response. - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -44368,7 +44368,7 @@ as input for the model's response. The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -44418,7 +44418,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -44454,7 +44454,7 @@ as input for the model's response. The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -44526,7 +44526,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -44638,7 +44638,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -44696,7 +44696,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -44720,7 +44720,7 @@ as input for the model's response. The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -44750,7 +44750,7 @@ as input for the model's response. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44758,16 +44758,16 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -44809,11 +44809,11 @@ as input for the model's response. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -44823,7 +44823,7 @@ as input for the model's response. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44831,7 +44831,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -44861,7 +44861,7 @@ as input for the model's response. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44891,7 +44891,7 @@ as input for the model's response. - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44899,7 +44899,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -44929,7 +44929,7 @@ as input for the model's response. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -44937,7 +44937,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -45013,7 +45013,7 @@ as input for the model's response. - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -45021,7 +45021,7 @@ as input for the model's response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -45053,7 +45053,7 @@ as input for the model's response. Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -45182,7 +45182,7 @@ as input for the model's response. - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -45256,11 +45256,11 @@ as input for the model's response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -45270,7 +45270,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -45282,11 +45282,11 @@ as input for the model's response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -45304,7 +45304,7 @@ as input for the model's response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -45519,11 +45519,11 @@ as input for the model's response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -45540,23 +45540,23 @@ as input for the model's response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -45581,7 +45581,7 @@ as input for the model's response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -45589,7 +45589,7 @@ as input for the model's response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -45654,12 +45654,12 @@ as input for the model's response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -45749,7 +45749,7 @@ as input for the model's response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -45775,7 +45775,7 @@ as input for the model's response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -45822,7 +45822,7 @@ as input for the model's response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -45937,7 +45937,7 @@ as input for the model's response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -45945,7 +45945,7 @@ as input for the model's response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -45967,7 +45967,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -46043,7 +46043,7 @@ as input for the model's response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -46055,15 +46055,15 @@ as input for the model's response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -46081,7 +46081,7 @@ as input for the model's response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -46149,7 +46149,7 @@ as input for the model's response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -46161,7 +46161,7 @@ as input for the model's response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -46193,7 +46193,7 @@ as input for the model's response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -46203,19 +46203,19 @@ as input for the model's response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -46229,7 +46229,7 @@ as input for the model's response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -46237,7 +46237,7 @@ as input for the model's response. - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -46246,17 +46246,17 @@ as input for the model's response. We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -46264,15 +46264,15 @@ as input for the model's response. The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -46388,19 +46388,19 @@ as input for the model's response. - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -46409,7 +46409,7 @@ as input for the model's response. The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -46429,11 +46429,11 @@ as input for the model's response. A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -46455,7 +46455,7 @@ as input for the model's response. - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -46474,14 +46474,14 @@ as input for the model's response. - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -46497,7 +46497,7 @@ as input for the model's response. - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -46521,7 +46521,7 @@ as input for the model's response. - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -46553,7 +46553,7 @@ as input for the model's response. - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -46567,12 +46567,12 @@ as input for the model's response. - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -46673,7 +46673,7 @@ as input for the model's response. A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -46694,7 +46694,7 @@ as input for the model's response. - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -46707,14 +46707,14 @@ as input for the model's response. - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -47839,7 +47839,7 @@ Retrieves a model response with the given ID. Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -47891,7 +47891,7 @@ Retrieves a model response with the given ID. A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -47903,7 +47903,7 @@ Retrieves a model response with the given ID. - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -47989,11 +47989,11 @@ Retrieves a model response with the given ID. - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -48031,7 +48031,7 @@ Retrieves a model response with the given ID. The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -48066,7 +48066,7 @@ Retrieves a model response with the given ID. - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -48103,7 +48103,7 @@ Retrieves a model response with the given ID. - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48307,7 +48307,7 @@ Retrieves a model response with the given ID. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48315,7 +48315,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -48359,7 +48359,7 @@ Retrieves a model response with the given ID. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48367,11 +48367,11 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -48422,11 +48422,11 @@ Retrieves a model response with the given ID. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -48483,7 +48483,7 @@ Retrieves a model response with the given ID. The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -48491,7 +48491,7 @@ Retrieves a model response with the given ID. A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -48538,7 +48538,7 @@ Retrieves a model response with the given ID. - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -48574,7 +48574,7 @@ Retrieves a model response with the given ID. The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -48614,7 +48614,7 @@ Retrieves a model response with the given ID. The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -48683,7 +48683,7 @@ Retrieves a model response with the given ID. A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48724,11 +48724,11 @@ Retrieves a model response with the given ID. - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -48736,15 +48736,15 @@ Retrieves a model response with the given ID. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48752,7 +48752,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -48818,7 +48818,7 @@ Retrieves a model response with the given ID. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -48858,7 +48858,7 @@ Retrieves a model response with the given ID. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48893,7 +48893,7 @@ Retrieves a model response with the given ID. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -48901,7 +48901,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -48970,7 +48970,7 @@ Retrieves a model response with the given ID. - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -48990,7 +48990,7 @@ Retrieves a model response with the given ID. - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -49002,15 +49002,15 @@ Retrieves a model response with the given ID. - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -49040,23 +49040,23 @@ Retrieves a model response with the given ID. - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -49072,11 +49072,11 @@ Retrieves a model response with the given ID. - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -49084,7 +49084,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -49108,15 +49108,15 @@ Retrieves a model response with the given ID. - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -49170,11 +49170,11 @@ Retrieves a model response with the given ID. - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -49214,11 +49214,11 @@ Retrieves a model response with the given ID. - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -49344,11 +49344,11 @@ Retrieves a model response with the given ID. - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -49368,11 +49368,11 @@ Retrieves a model response with the given ID. - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -49380,7 +49380,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -49392,7 +49392,7 @@ Retrieves a model response with the given ID. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -49416,11 +49416,11 @@ Retrieves a model response with the given ID. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -49430,7 +49430,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -49442,11 +49442,11 @@ Retrieves a model response with the given ID. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -49464,7 +49464,7 @@ Retrieves a model response with the given ID. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -49679,11 +49679,11 @@ Retrieves a model response with the given ID. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -49700,23 +49700,23 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -49741,7 +49741,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -49749,7 +49749,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -49814,12 +49814,12 @@ Retrieves a model response with the given ID. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -49909,7 +49909,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -49967,7 +49967,7 @@ Retrieves a model response with the given ID. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50014,7 +50014,7 @@ Retrieves a model response with the given ID. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -50129,7 +50129,7 @@ Retrieves a model response with the given ID. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50137,7 +50137,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -50151,7 +50151,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -50277,7 +50277,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50353,7 +50353,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50365,15 +50365,15 @@ Retrieves a model response with the given ID. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -50391,7 +50391,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50459,7 +50459,7 @@ Retrieves a model response with the given ID. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -50471,7 +50471,7 @@ Retrieves a model response with the given ID. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -50503,7 +50503,7 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -50513,19 +50513,19 @@ Retrieves a model response with the given ID. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -50539,7 +50539,7 @@ Retrieves a model response with the given ID. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50553,11 +50553,11 @@ Retrieves a model response with the given ID. - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -50565,7 +50565,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -50577,7 +50577,7 @@ Retrieves a model response with the given ID. - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -50607,11 +50607,11 @@ Retrieves a model response with the given ID. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -50621,7 +50621,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50633,11 +50633,11 @@ Retrieves a model response with the given ID. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -50655,7 +50655,7 @@ Retrieves a model response with the given ID. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -50870,11 +50870,11 @@ Retrieves a model response with the given ID. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -50891,23 +50891,23 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -50932,7 +50932,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -50940,7 +50940,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -51005,12 +51005,12 @@ Retrieves a model response with the given ID. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -51100,7 +51100,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -51126,7 +51126,7 @@ Retrieves a model response with the given ID. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51173,7 +51173,7 @@ Retrieves a model response with the given ID. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -51288,7 +51288,7 @@ Retrieves a model response with the given ID. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51296,7 +51296,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -51318,7 +51318,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51394,7 +51394,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51406,15 +51406,15 @@ Retrieves a model response with the given ID. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -51432,7 +51432,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51500,7 +51500,7 @@ Retrieves a model response with the given ID. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -51512,7 +51512,7 @@ Retrieves a model response with the given ID. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -51544,7 +51544,7 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -51554,19 +51554,19 @@ Retrieves a model response with the given ID. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -51580,7 +51580,7 @@ Retrieves a model response with the given ID. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -51594,11 +51594,11 @@ Retrieves a model response with the given ID. - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51637,7 +51637,7 @@ Retrieves a model response with the given ID. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51659,7 +51659,7 @@ Retrieves a model response with the given ID. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -51690,11 +51690,11 @@ Retrieves a model response with the given ID. - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51710,7 +51710,7 @@ Retrieves a model response with the given ID. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -51732,7 +51732,7 @@ Retrieves a model response with the given ID. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51748,7 +51748,7 @@ Retrieves a model response with the given ID. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -51756,7 +51756,7 @@ Retrieves a model response with the given ID. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -51809,7 +51809,7 @@ Retrieves a model response with the given ID. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51843,15 +51843,15 @@ Retrieves a model response with the given ID. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -51875,7 +51875,7 @@ Retrieves a model response with the given ID. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51901,7 +51901,7 @@ Retrieves a model response with the given ID. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51909,7 +51909,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -51931,11 +51931,11 @@ Retrieves a model response with the given ID. Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -51949,11 +51949,11 @@ Retrieves a model response with the given ID. - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -51961,7 +51961,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -51985,7 +51985,7 @@ Retrieves a model response with the given ID. - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -51993,7 +51993,7 @@ Retrieves a model response with the given ID. - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -52057,11 +52057,11 @@ Retrieves a model response with the given ID. - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52069,7 +52069,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -52093,11 +52093,11 @@ Retrieves a model response with the given ID. - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -52183,11 +52183,11 @@ Retrieves a model response with the given ID. - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52195,7 +52195,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -52241,11 +52241,11 @@ Retrieves a model response with the given ID. - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52253,7 +52253,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -52277,7 +52277,7 @@ Retrieves a model response with the given ID. - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -52305,11 +52305,11 @@ Retrieves a model response with the given ID. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -52319,7 +52319,7 @@ Retrieves a model response with the given ID. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52327,7 +52327,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -52357,7 +52357,7 @@ Retrieves a model response with the given ID. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52383,11 +52383,11 @@ Retrieves a model response with the given ID. - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52395,7 +52395,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -52425,7 +52425,7 @@ Retrieves a model response with the given ID. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52433,16 +52433,16 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -52503,7 +52503,7 @@ Retrieves a model response with the given ID. The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52511,7 +52511,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -52561,7 +52561,7 @@ Retrieves a model response with the given ID. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52569,7 +52569,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -52603,7 +52603,7 @@ Retrieves a model response with the given ID. - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52619,7 +52619,7 @@ Retrieves a model response with the given ID. The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52627,7 +52627,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -52657,7 +52657,7 @@ Retrieves a model response with the given ID. - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52693,7 +52693,7 @@ Retrieves a model response with the given ID. - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52701,7 +52701,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -52971,7 +52971,7 @@ Retrieves a model response with the given ID. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -52979,11 +52979,11 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -53040,7 +53040,7 @@ Retrieves a model response with the given ID. The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53048,7 +53048,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -53135,7 +53135,7 @@ Retrieves a model response with the given ID. - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53143,7 +53143,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -53263,11 +53263,11 @@ Retrieves a model response with the given ID. - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -53481,7 +53481,7 @@ Retrieves a model response with the given ID. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -53521,7 +53521,7 @@ Retrieves a model response with the given ID. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53550,11 +53550,11 @@ Retrieves a model response with the given ID. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -53584,7 +53584,7 @@ Retrieves a model response with the given ID. Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53634,15 +53634,15 @@ Retrieves a model response with the given ID. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53685,7 +53685,7 @@ Retrieves a model response with the given ID. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -53707,7 +53707,7 @@ Retrieves a model response with the given ID. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -53802,7 +53802,7 @@ Retrieves a model response with the given ID. Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -53848,7 +53848,7 @@ Retrieves a model response with the given ID. The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -53882,11 +53882,11 @@ Retrieves a model response with the given ID. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -53896,7 +53896,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -53908,11 +53908,11 @@ Retrieves a model response with the given ID. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -53930,7 +53930,7 @@ Retrieves a model response with the given ID. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -54145,11 +54145,11 @@ Retrieves a model response with the given ID. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -54166,23 +54166,23 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -54207,7 +54207,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54215,7 +54215,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -54280,12 +54280,12 @@ Retrieves a model response with the given ID. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -54375,7 +54375,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -54401,7 +54401,7 @@ Retrieves a model response with the given ID. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54448,7 +54448,7 @@ Retrieves a model response with the given ID. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -54563,7 +54563,7 @@ Retrieves a model response with the given ID. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54571,7 +54571,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -54593,7 +54593,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54669,7 +54669,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54681,15 +54681,15 @@ Retrieves a model response with the given ID. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -54707,7 +54707,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54775,7 +54775,7 @@ Retrieves a model response with the given ID. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -54787,7 +54787,7 @@ Retrieves a model response with the given ID. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -54819,7 +54819,7 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -54829,19 +54829,19 @@ Retrieves a model response with the given ID. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -54855,7 +54855,7 @@ Retrieves a model response with the given ID. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54919,11 +54919,11 @@ Retrieves a model response with the given ID. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -54933,7 +54933,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -54945,11 +54945,11 @@ Retrieves a model response with the given ID. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -54967,7 +54967,7 @@ Retrieves a model response with the given ID. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -55182,11 +55182,11 @@ Retrieves a model response with the given ID. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -55203,23 +55203,23 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -55244,7 +55244,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55252,7 +55252,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -55317,12 +55317,12 @@ Retrieves a model response with the given ID. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -55412,7 +55412,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -55438,7 +55438,7 @@ Retrieves a model response with the given ID. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55485,7 +55485,7 @@ Retrieves a model response with the given ID. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -55600,7 +55600,7 @@ Retrieves a model response with the given ID. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55608,7 +55608,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -55630,7 +55630,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55706,7 +55706,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55718,15 +55718,15 @@ Retrieves a model response with the given ID. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -55744,7 +55744,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55812,7 +55812,7 @@ Retrieves a model response with the given ID. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -55824,7 +55824,7 @@ Retrieves a model response with the given ID. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -55856,7 +55856,7 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -55866,19 +55866,19 @@ Retrieves a model response with the given ID. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -55892,7 +55892,7 @@ Retrieves a model response with the given ID. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -55952,7 +55952,7 @@ Retrieves a model response with the given ID. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -55974,7 +55974,7 @@ Retrieves a model response with the given ID. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -55990,7 +55990,7 @@ Retrieves a model response with the given ID. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -55998,7 +55998,7 @@ Retrieves a model response with the given ID. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -56051,7 +56051,7 @@ Retrieves a model response with the given ID. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56085,15 +56085,15 @@ Retrieves a model response with the given ID. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -56117,7 +56117,7 @@ Retrieves a model response with the given ID. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56143,7 +56143,7 @@ Retrieves a model response with the given ID. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56151,7 +56151,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -56175,11 +56175,11 @@ Retrieves a model response with the given ID. - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -56187,7 +56187,7 @@ Retrieves a model response with the given ID. The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -56237,7 +56237,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56273,7 +56273,7 @@ Retrieves a model response with the given ID. The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -56345,7 +56345,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56457,7 +56457,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56515,7 +56515,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56539,7 +56539,7 @@ Retrieves a model response with the given ID. The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -56569,7 +56569,7 @@ Retrieves a model response with the given ID. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56577,16 +56577,16 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -56628,11 +56628,11 @@ Retrieves a model response with the given ID. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -56642,7 +56642,7 @@ Retrieves a model response with the given ID. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56650,7 +56650,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -56680,7 +56680,7 @@ Retrieves a model response with the given ID. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56710,7 +56710,7 @@ Retrieves a model response with the given ID. - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56718,7 +56718,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -56748,7 +56748,7 @@ Retrieves a model response with the given ID. The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56756,7 +56756,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56832,7 +56832,7 @@ Retrieves a model response with the given ID. - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -56840,7 +56840,7 @@ Retrieves a model response with the given ID. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -56872,7 +56872,7 @@ Retrieves a model response with the given ID. Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -57001,7 +57001,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -57075,11 +57075,11 @@ Retrieves a model response with the given ID. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -57089,7 +57089,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57101,11 +57101,11 @@ Retrieves a model response with the given ID. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -57123,7 +57123,7 @@ Retrieves a model response with the given ID. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -57338,11 +57338,11 @@ Retrieves a model response with the given ID. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -57359,23 +57359,23 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -57400,7 +57400,7 @@ Retrieves a model response with the given ID. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57408,7 +57408,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -57473,12 +57473,12 @@ Retrieves a model response with the given ID. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -57568,7 +57568,7 @@ Retrieves a model response with the given ID. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -57594,7 +57594,7 @@ Retrieves a model response with the given ID. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57641,7 +57641,7 @@ Retrieves a model response with the given ID. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -57756,7 +57756,7 @@ Retrieves a model response with the given ID. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57764,7 +57764,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -57786,7 +57786,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57862,7 +57862,7 @@ Retrieves a model response with the given ID. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57874,15 +57874,15 @@ Retrieves a model response with the given ID. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -57900,7 +57900,7 @@ Retrieves a model response with the given ID. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -57968,7 +57968,7 @@ Retrieves a model response with the given ID. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -57980,7 +57980,7 @@ Retrieves a model response with the given ID. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -58012,7 +58012,7 @@ Retrieves a model response with the given ID. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -58022,19 +58022,19 @@ Retrieves a model response with the given ID. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -58048,7 +58048,7 @@ Retrieves a model response with the given ID. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -58056,7 +58056,7 @@ Retrieves a model response with the given ID. - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -58065,17 +58065,17 @@ Retrieves a model response with the given ID. We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -58083,15 +58083,15 @@ Retrieves a model response with the given ID. The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -58207,19 +58207,19 @@ Retrieves a model response with the given ID. - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -58228,7 +58228,7 @@ Retrieves a model response with the given ID. The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -58248,11 +58248,11 @@ Retrieves a model response with the given ID. A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -58274,7 +58274,7 @@ Retrieves a model response with the given ID. - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -58293,14 +58293,14 @@ Retrieves a model response with the given ID. - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -58316,7 +58316,7 @@ Retrieves a model response with the given ID. - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -58340,7 +58340,7 @@ Retrieves a model response with the given ID. - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -58372,7 +58372,7 @@ Retrieves a model response with the given ID. - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -58386,12 +58386,12 @@ Retrieves a model response with the given ID. - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -58492,7 +58492,7 @@ Retrieves a model response with the given ID. A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -58513,7 +58513,7 @@ Retrieves a model response with the given ID. - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -58526,14 +58526,14 @@ Retrieves a model response with the given ID. - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -59108,11 +59108,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -59142,11 +59142,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -59190,7 +59190,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -59270,7 +59270,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. @@ -59373,7 +59373,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -59381,7 +59381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -59528,7 +59528,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -59574,7 +59574,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -59608,11 +59608,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -59622,7 +59622,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -59634,11 +59634,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -59656,7 +59656,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -59871,11 +59871,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -59892,23 +59892,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -59933,7 +59933,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -59941,7 +59941,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -60006,12 +60006,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -60101,7 +60101,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -60159,7 +60159,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60206,7 +60206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -60321,7 +60321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60329,7 +60329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -60343,7 +60343,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -60469,7 +60469,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60545,7 +60545,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60557,15 +60557,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -60583,7 +60583,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60651,7 +60651,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -60663,7 +60663,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -60695,7 +60695,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -60705,19 +60705,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -60731,7 +60731,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60795,11 +60795,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -60809,7 +60809,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -60821,11 +60821,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -60843,7 +60843,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -61058,11 +61058,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -61079,23 +61079,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -61120,7 +61120,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61128,7 +61128,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -61193,12 +61193,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -61288,7 +61288,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -61314,7 +61314,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61361,7 +61361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -61476,7 +61476,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61484,7 +61484,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -61506,7 +61506,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61582,7 +61582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61594,15 +61594,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -61620,7 +61620,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61688,7 +61688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -61700,7 +61700,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -61732,7 +61732,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -61742,19 +61742,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -61768,7 +61768,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -61874,11 +61874,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -61978,7 +61978,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -61986,7 +61986,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -62063,7 +62063,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62071,11 +62071,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -62161,7 +62161,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -62201,7 +62201,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62217,7 +62217,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -62239,7 +62239,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62268,11 +62268,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -62329,7 +62329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -62337,7 +62337,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -62384,7 +62384,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -62420,7 +62420,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -62460,7 +62460,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -62529,7 +62529,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62594,15 +62594,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62645,7 +62645,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62667,7 +62667,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -62722,7 +62722,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -62730,7 +62730,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -62783,7 +62783,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62817,15 +62817,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -62849,7 +62849,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62875,7 +62875,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -62883,7 +62883,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -62907,11 +62907,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -62919,7 +62919,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -62969,7 +62969,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63005,7 +63005,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -63077,7 +63077,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63189,7 +63189,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63247,7 +63247,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63271,7 +63271,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -63299,11 +63299,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -63313,7 +63313,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63321,7 +63321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -63351,7 +63351,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63381,7 +63381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63389,7 +63389,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -63419,7 +63419,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63427,16 +63427,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -63480,7 +63480,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63488,7 +63488,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63555,7 +63555,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -63563,7 +63563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -63662,7 +63662,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -63670,7 +63670,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -63717,7 +63717,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -63753,7 +63753,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -63793,7 +63793,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -63860,7 +63860,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -63868,7 +63868,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -63915,7 +63915,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -63951,7 +63951,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -63991,7 +63991,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -64033,7 +64033,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -64281,11 +64281,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -64323,7 +64323,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -64358,7 +64358,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -64488,7 +64488,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -64540,7 +64540,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -64552,7 +64552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -64638,11 +64638,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -64680,7 +64680,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -64715,7 +64715,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -64752,7 +64752,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -64956,7 +64956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -64964,7 +64964,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -65008,7 +65008,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65016,11 +65016,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -65071,11 +65071,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -65132,7 +65132,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -65140,7 +65140,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -65187,7 +65187,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -65223,7 +65223,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -65263,7 +65263,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -65332,7 +65332,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65373,11 +65373,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -65385,15 +65385,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65401,7 +65401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -65467,7 +65467,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -65507,7 +65507,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65542,7 +65542,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65550,7 +65550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -65619,7 +65619,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -65639,7 +65639,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -65651,15 +65651,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -65689,23 +65689,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -65721,11 +65721,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65733,7 +65733,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -65757,15 +65757,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -65819,11 +65819,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65863,11 +65863,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -65993,11 +65993,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -66017,11 +66017,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -66029,7 +66029,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -66041,7 +66041,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -66065,11 +66065,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -66079,7 +66079,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -66091,11 +66091,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -66113,7 +66113,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -66328,11 +66328,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -66349,23 +66349,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -66390,7 +66390,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -66398,7 +66398,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -66463,12 +66463,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -66558,7 +66558,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -66616,7 +66616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -66663,7 +66663,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -66778,7 +66778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -66786,7 +66786,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -66800,7 +66800,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -66926,7 +66926,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67002,7 +67002,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67014,15 +67014,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -67040,7 +67040,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67108,7 +67108,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -67120,7 +67120,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -67152,7 +67152,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -67162,19 +67162,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -67188,7 +67188,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67202,11 +67202,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -67214,7 +67214,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -67226,7 +67226,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -67256,11 +67256,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -67270,7 +67270,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67282,11 +67282,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -67304,7 +67304,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -67519,11 +67519,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -67540,23 +67540,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -67581,7 +67581,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67589,7 +67589,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -67654,12 +67654,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -67749,7 +67749,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -67775,7 +67775,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67822,7 +67822,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -67937,7 +67937,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -67945,7 +67945,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -67967,7 +67967,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -68043,7 +68043,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -68055,15 +68055,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -68081,7 +68081,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -68149,7 +68149,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -68161,7 +68161,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -68193,7 +68193,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -68203,19 +68203,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -68229,7 +68229,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -68243,11 +68243,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68286,7 +68286,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68308,7 +68308,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -68339,11 +68339,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68359,7 +68359,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -68381,7 +68381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68397,7 +68397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -68405,7 +68405,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -68458,7 +68458,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68492,15 +68492,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -68524,7 +68524,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68550,7 +68550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68558,7 +68558,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -68580,11 +68580,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -68598,11 +68598,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68610,7 +68610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -68634,7 +68634,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -68642,7 +68642,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -68706,11 +68706,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68718,7 +68718,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -68742,11 +68742,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -68832,11 +68832,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68844,7 +68844,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -68890,11 +68890,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68902,7 +68902,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -68926,7 +68926,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -68954,11 +68954,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -68968,7 +68968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -68976,7 +68976,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -69006,7 +69006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69032,11 +69032,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69044,7 +69044,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -69074,7 +69074,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69082,16 +69082,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -69152,7 +69152,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69160,7 +69160,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -69210,7 +69210,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69218,7 +69218,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -69252,7 +69252,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69268,7 +69268,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69276,7 +69276,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -69306,7 +69306,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69342,7 +69342,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69350,7 +69350,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -69620,7 +69620,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69628,11 +69628,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -69689,7 +69689,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69697,7 +69697,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -69784,7 +69784,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -69792,7 +69792,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -69912,11 +69912,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -70130,7 +70130,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -70170,7 +70170,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -70199,11 +70199,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -70233,7 +70233,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -70283,15 +70283,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -70334,7 +70334,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -70356,7 +70356,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -70451,7 +70451,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -70497,7 +70497,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -70531,11 +70531,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -70545,7 +70545,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -70557,11 +70557,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -70579,7 +70579,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -70794,11 +70794,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -70815,23 +70815,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -70856,7 +70856,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -70864,7 +70864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -70929,12 +70929,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -71024,7 +71024,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -71050,7 +71050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71097,7 +71097,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -71212,7 +71212,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71220,7 +71220,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -71242,7 +71242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71318,7 +71318,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71330,15 +71330,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -71356,7 +71356,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71424,7 +71424,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -71436,7 +71436,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -71468,7 +71468,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -71478,19 +71478,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -71504,7 +71504,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71568,11 +71568,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -71582,7 +71582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71594,11 +71594,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -71616,7 +71616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -71831,11 +71831,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -71852,23 +71852,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -71893,7 +71893,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -71901,7 +71901,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -71966,12 +71966,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -72061,7 +72061,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -72087,7 +72087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72134,7 +72134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -72249,7 +72249,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72257,7 +72257,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -72279,7 +72279,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72355,7 +72355,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72367,15 +72367,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -72393,7 +72393,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72461,7 +72461,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -72473,7 +72473,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -72505,7 +72505,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -72515,19 +72515,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -72541,7 +72541,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -72601,7 +72601,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -72623,7 +72623,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -72639,7 +72639,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -72647,7 +72647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -72700,7 +72700,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -72734,15 +72734,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -72766,7 +72766,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -72792,7 +72792,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -72800,7 +72800,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -72824,11 +72824,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -72836,7 +72836,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -72886,7 +72886,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -72922,7 +72922,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -72994,7 +72994,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -73106,7 +73106,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -73164,7 +73164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -73188,7 +73188,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -73218,7 +73218,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73226,16 +73226,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -73277,11 +73277,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -73291,7 +73291,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73299,7 +73299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -73329,7 +73329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73359,7 +73359,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73367,7 +73367,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -73397,7 +73397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73405,7 +73405,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -73481,7 +73481,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -73489,7 +73489,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -73521,7 +73521,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -73650,7 +73650,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -73724,11 +73724,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -73738,7 +73738,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -73750,11 +73750,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -73772,7 +73772,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -73987,11 +73987,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -74008,23 +74008,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -74049,7 +74049,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74057,7 +74057,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -74122,12 +74122,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -74217,7 +74217,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -74243,7 +74243,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74290,7 +74290,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -74405,7 +74405,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74413,7 +74413,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -74435,7 +74435,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74511,7 +74511,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74523,15 +74523,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -74549,7 +74549,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74617,7 +74617,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -74629,7 +74629,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -74661,7 +74661,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -74671,19 +74671,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -74697,7 +74697,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -74705,7 +74705,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -74714,17 +74714,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -74732,15 +74732,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -74856,19 +74856,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -74877,7 +74877,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -74897,11 +74897,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -74923,7 +74923,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -74942,14 +74942,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -74965,7 +74965,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -74989,7 +74989,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -75021,7 +75021,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -75035,12 +75035,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -75141,7 +75141,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -75162,7 +75162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -75175,14 +75175,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -75260,7 +75260,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75284,7 +75284,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75312,7 +75312,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75336,7 +75336,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75372,7 +75372,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75408,7 +75408,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75440,7 +75440,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75472,7 +75472,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75504,7 +75504,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.interpreting"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -75530,7 +75530,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -75582,7 +75582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -75594,7 +75594,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -75680,11 +75680,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -75722,7 +75722,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -75757,7 +75757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -75794,7 +75794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -75998,7 +75998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76006,7 +76006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -76050,7 +76050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76058,11 +76058,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -76113,11 +76113,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -76174,7 +76174,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -76182,7 +76182,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -76229,7 +76229,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -76265,7 +76265,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -76305,7 +76305,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -76374,7 +76374,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76415,11 +76415,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -76427,15 +76427,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76443,7 +76443,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -76509,7 +76509,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -76549,7 +76549,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76584,7 +76584,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76592,7 +76592,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -76661,7 +76661,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -76681,7 +76681,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -76693,15 +76693,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -76731,23 +76731,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -76763,11 +76763,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76775,7 +76775,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -76799,15 +76799,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -76861,11 +76861,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -76905,11 +76905,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -77035,11 +77035,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -77059,11 +77059,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -77071,7 +77071,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -77083,7 +77083,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -77107,11 +77107,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -77121,7 +77121,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -77133,11 +77133,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -77155,7 +77155,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -77370,11 +77370,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -77391,23 +77391,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -77432,7 +77432,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -77440,7 +77440,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -77505,12 +77505,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -77600,7 +77600,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -77658,7 +77658,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -77705,7 +77705,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -77820,7 +77820,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -77828,7 +77828,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -77842,7 +77842,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -77968,7 +77968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78044,7 +78044,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78056,15 +78056,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -78082,7 +78082,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78150,7 +78150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -78162,7 +78162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -78194,7 +78194,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -78204,19 +78204,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -78230,7 +78230,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78244,11 +78244,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -78256,7 +78256,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -78268,7 +78268,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -78298,11 +78298,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -78312,7 +78312,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78324,11 +78324,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -78346,7 +78346,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -78561,11 +78561,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -78582,23 +78582,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -78623,7 +78623,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78631,7 +78631,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -78696,12 +78696,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -78791,7 +78791,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -78817,7 +78817,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78864,7 +78864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -78979,7 +78979,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -78987,7 +78987,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -79009,7 +79009,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -79085,7 +79085,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -79097,15 +79097,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -79123,7 +79123,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -79191,7 +79191,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -79203,7 +79203,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -79235,7 +79235,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -79245,19 +79245,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -79271,7 +79271,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -79285,11 +79285,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79328,7 +79328,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79350,7 +79350,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -79381,11 +79381,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79401,7 +79401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -79423,7 +79423,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79439,7 +79439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -79447,7 +79447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -79500,7 +79500,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79534,15 +79534,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -79566,7 +79566,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79592,7 +79592,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79600,7 +79600,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -79622,11 +79622,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -79640,11 +79640,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79652,7 +79652,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -79676,7 +79676,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -79684,7 +79684,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -79748,11 +79748,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79760,7 +79760,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -79784,11 +79784,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -79874,11 +79874,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79886,7 +79886,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -79932,11 +79932,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -79944,7 +79944,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -79968,7 +79968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -79996,11 +79996,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -80010,7 +80010,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80018,7 +80018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -80048,7 +80048,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80074,11 +80074,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80086,7 +80086,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -80116,7 +80116,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80124,16 +80124,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -80194,7 +80194,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80202,7 +80202,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -80252,7 +80252,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80260,7 +80260,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -80294,7 +80294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80310,7 +80310,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80318,7 +80318,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -80348,7 +80348,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80384,7 +80384,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80392,7 +80392,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -80662,7 +80662,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80670,11 +80670,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -80731,7 +80731,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80739,7 +80739,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -80826,7 +80826,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -80834,7 +80834,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -80954,11 +80954,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -81172,7 +81172,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -81212,7 +81212,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -81241,11 +81241,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -81275,7 +81275,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -81325,15 +81325,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -81376,7 +81376,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -81398,7 +81398,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -81493,7 +81493,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -81539,7 +81539,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -81573,11 +81573,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -81587,7 +81587,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -81599,11 +81599,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -81621,7 +81621,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -81836,11 +81836,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -81857,23 +81857,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -81898,7 +81898,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -81906,7 +81906,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -81971,12 +81971,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -82066,7 +82066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -82092,7 +82092,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82139,7 +82139,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -82254,7 +82254,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82262,7 +82262,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -82284,7 +82284,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82360,7 +82360,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82372,15 +82372,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -82398,7 +82398,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82466,7 +82466,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -82478,7 +82478,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -82510,7 +82510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -82520,19 +82520,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -82546,7 +82546,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82610,11 +82610,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -82624,7 +82624,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82636,11 +82636,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -82658,7 +82658,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -82873,11 +82873,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -82894,23 +82894,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -82935,7 +82935,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -82943,7 +82943,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -83008,12 +83008,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -83103,7 +83103,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -83129,7 +83129,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83176,7 +83176,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -83291,7 +83291,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83299,7 +83299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -83321,7 +83321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83397,7 +83397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83409,15 +83409,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -83435,7 +83435,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83503,7 +83503,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -83515,7 +83515,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -83547,7 +83547,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -83557,19 +83557,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -83583,7 +83583,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -83643,7 +83643,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -83665,7 +83665,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -83681,7 +83681,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -83689,7 +83689,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -83742,7 +83742,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -83776,15 +83776,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -83808,7 +83808,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -83834,7 +83834,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -83842,7 +83842,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -83866,11 +83866,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -83878,7 +83878,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -83928,7 +83928,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -83964,7 +83964,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -84036,7 +84036,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -84148,7 +84148,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -84206,7 +84206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -84230,7 +84230,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -84260,7 +84260,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84268,16 +84268,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -84319,11 +84319,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -84333,7 +84333,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84341,7 +84341,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -84371,7 +84371,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84401,7 +84401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84409,7 +84409,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -84439,7 +84439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84447,7 +84447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -84523,7 +84523,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -84531,7 +84531,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -84563,7 +84563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -84692,7 +84692,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -84766,11 +84766,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -84780,7 +84780,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -84792,11 +84792,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -84814,7 +84814,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -85029,11 +85029,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -85050,23 +85050,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -85091,7 +85091,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85099,7 +85099,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -85164,12 +85164,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -85259,7 +85259,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -85285,7 +85285,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85332,7 +85332,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -85447,7 +85447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85455,7 +85455,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -85477,7 +85477,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85553,7 +85553,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85565,15 +85565,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -85591,7 +85591,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85659,7 +85659,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -85671,7 +85671,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -85703,7 +85703,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -85713,19 +85713,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -85739,7 +85739,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -85747,7 +85747,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -85756,17 +85756,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -85774,15 +85774,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -85898,19 +85898,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -85919,7 +85919,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -85939,11 +85939,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -85965,7 +85965,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -85984,14 +85984,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -86007,7 +86007,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -86031,7 +86031,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -86063,7 +86063,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -86077,12 +86077,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -86183,7 +86183,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -86204,7 +86204,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -86217,14 +86217,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -86292,7 +86292,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -86387,11 +86387,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -86429,7 +86429,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -86799,7 +86799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -86997,7 +86997,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -87033,7 +87033,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -87085,7 +87085,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -87097,7 +87097,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -87183,11 +87183,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -87225,7 +87225,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -87260,7 +87260,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -87297,7 +87297,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -87501,7 +87501,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -87509,7 +87509,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -87553,7 +87553,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -87561,11 +87561,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -87616,11 +87616,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -87677,7 +87677,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -87685,7 +87685,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -87732,7 +87732,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -87768,7 +87768,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -87808,7 +87808,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -87877,7 +87877,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -87918,11 +87918,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -87930,15 +87930,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -87946,7 +87946,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -88012,7 +88012,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -88052,7 +88052,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88087,7 +88087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88095,7 +88095,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -88164,7 +88164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -88184,7 +88184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -88196,15 +88196,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -88234,23 +88234,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -88266,11 +88266,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88278,7 +88278,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -88302,15 +88302,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -88364,11 +88364,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88408,11 +88408,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88538,11 +88538,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88562,11 +88562,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -88574,7 +88574,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -88586,7 +88586,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -88610,11 +88610,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -88624,7 +88624,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -88636,11 +88636,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -88658,7 +88658,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -88873,11 +88873,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -88894,23 +88894,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -88935,7 +88935,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -88943,7 +88943,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -89008,12 +89008,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -89103,7 +89103,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -89161,7 +89161,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89208,7 +89208,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -89323,7 +89323,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89331,7 +89331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -89345,7 +89345,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -89471,7 +89471,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89547,7 +89547,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89559,15 +89559,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -89585,7 +89585,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89653,7 +89653,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -89665,7 +89665,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -89697,7 +89697,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -89707,19 +89707,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -89733,7 +89733,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89747,11 +89747,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -89759,7 +89759,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -89771,7 +89771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -89801,11 +89801,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -89815,7 +89815,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -89827,11 +89827,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -89849,7 +89849,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -90064,11 +90064,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -90085,23 +90085,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -90126,7 +90126,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90134,7 +90134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -90199,12 +90199,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -90294,7 +90294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -90320,7 +90320,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90367,7 +90367,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -90482,7 +90482,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90490,7 +90490,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -90512,7 +90512,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90588,7 +90588,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90600,15 +90600,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -90626,7 +90626,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90694,7 +90694,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -90706,7 +90706,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -90738,7 +90738,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -90748,19 +90748,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -90774,7 +90774,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -90788,11 +90788,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -90831,7 +90831,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -90853,7 +90853,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -90884,11 +90884,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -90904,7 +90904,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -90926,7 +90926,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -90942,7 +90942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -90950,7 +90950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -91003,7 +91003,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91037,15 +91037,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -91069,7 +91069,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91095,7 +91095,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91103,7 +91103,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -91125,11 +91125,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -91143,11 +91143,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91155,7 +91155,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91179,7 +91179,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -91187,7 +91187,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -91251,11 +91251,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91263,7 +91263,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91287,11 +91287,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -91377,11 +91377,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91389,7 +91389,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91435,11 +91435,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91447,7 +91447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91471,7 +91471,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -91499,11 +91499,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -91513,7 +91513,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91521,7 +91521,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -91551,7 +91551,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91577,11 +91577,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91589,7 +91589,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -91619,7 +91619,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91627,16 +91627,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -91697,7 +91697,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91705,7 +91705,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91755,7 +91755,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91763,7 +91763,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -91797,7 +91797,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91813,7 +91813,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91821,7 +91821,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -91851,7 +91851,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91887,7 +91887,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -91895,7 +91895,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -92165,7 +92165,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92173,11 +92173,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -92234,7 +92234,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92242,7 +92242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -92329,7 +92329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92337,7 +92337,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -92457,11 +92457,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -92675,7 +92675,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -92715,7 +92715,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92744,11 +92744,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -92778,7 +92778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92828,15 +92828,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92879,7 +92879,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -92901,7 +92901,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -92996,7 +92996,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -93042,7 +93042,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -93076,11 +93076,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -93090,7 +93090,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93102,11 +93102,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -93124,7 +93124,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -93339,11 +93339,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -93360,23 +93360,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -93401,7 +93401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93409,7 +93409,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -93474,12 +93474,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -93569,7 +93569,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -93595,7 +93595,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93642,7 +93642,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -93757,7 +93757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93765,7 +93765,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -93787,7 +93787,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93863,7 +93863,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93875,15 +93875,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -93901,7 +93901,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -93969,7 +93969,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -93981,7 +93981,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -94013,7 +94013,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -94023,19 +94023,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -94049,7 +94049,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94113,11 +94113,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -94127,7 +94127,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94139,11 +94139,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -94161,7 +94161,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -94376,11 +94376,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -94397,23 +94397,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -94438,7 +94438,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94446,7 +94446,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -94511,12 +94511,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -94606,7 +94606,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -94632,7 +94632,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94679,7 +94679,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -94794,7 +94794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94802,7 +94802,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -94824,7 +94824,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94900,7 +94900,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -94912,15 +94912,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -94938,7 +94938,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -95006,7 +95006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -95018,7 +95018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -95050,7 +95050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -95060,19 +95060,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -95086,7 +95086,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -95146,7 +95146,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -95168,7 +95168,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95184,7 +95184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -95192,7 +95192,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -95245,7 +95245,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95279,15 +95279,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -95311,7 +95311,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95337,7 +95337,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95345,7 +95345,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -95369,11 +95369,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -95381,7 +95381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -95431,7 +95431,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -95467,7 +95467,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -95539,7 +95539,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -95651,7 +95651,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -95709,7 +95709,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -95733,7 +95733,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -95763,7 +95763,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95771,16 +95771,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -95822,11 +95822,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -95836,7 +95836,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95844,7 +95844,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -95874,7 +95874,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95904,7 +95904,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95912,7 +95912,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -95942,7 +95942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -95950,7 +95950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -96026,7 +96026,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -96034,7 +96034,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -96066,7 +96066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -96195,7 +96195,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -96269,11 +96269,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -96283,7 +96283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -96295,11 +96295,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -96317,7 +96317,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -96532,11 +96532,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -96553,23 +96553,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -96594,7 +96594,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -96602,7 +96602,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -96667,12 +96667,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -96762,7 +96762,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -96788,7 +96788,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -96835,7 +96835,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -96950,7 +96950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -96958,7 +96958,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -96980,7 +96980,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -97056,7 +97056,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -97068,15 +97068,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -97094,7 +97094,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -97162,7 +97162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -97174,7 +97174,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -97206,7 +97206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -97216,19 +97216,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -97242,7 +97242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -97250,7 +97250,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -97259,17 +97259,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -97277,15 +97277,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -97401,19 +97401,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -97422,7 +97422,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -97442,11 +97442,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -97468,7 +97468,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -97487,14 +97487,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -97510,7 +97510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -97534,7 +97534,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -97566,7 +97566,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -97580,12 +97580,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -97686,7 +97686,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -97707,7 +97707,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -97720,14 +97720,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -97795,7 +97795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.created"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -97831,7 +97831,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -97867,7 +97867,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -97935,7 +97935,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Emitted when an error occurs. - - `code: string` + - `code: string or null` The error code. @@ -97943,7 +97943,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The error message. - - `param: string` + - `param: string or null` The error parameter. @@ -97957,7 +97957,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -97983,7 +97983,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -98035,7 +98035,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -98047,7 +98047,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -98133,11 +98133,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -98175,7 +98175,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -98210,7 +98210,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -98247,7 +98247,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -98451,7 +98451,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -98459,7 +98459,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -98503,7 +98503,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -98511,11 +98511,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -98566,11 +98566,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -98627,7 +98627,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -98635,7 +98635,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -98682,7 +98682,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -98718,7 +98718,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -98758,7 +98758,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -98827,7 +98827,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -98868,11 +98868,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -98880,15 +98880,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -98896,7 +98896,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -98962,7 +98962,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -99002,7 +99002,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99037,7 +99037,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99045,7 +99045,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -99114,7 +99114,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -99134,7 +99134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -99146,15 +99146,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -99184,23 +99184,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -99216,11 +99216,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99228,7 +99228,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -99252,15 +99252,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -99314,11 +99314,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99358,11 +99358,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99488,11 +99488,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99512,11 +99512,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -99524,7 +99524,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -99536,7 +99536,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -99560,11 +99560,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -99574,7 +99574,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -99586,11 +99586,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -99608,7 +99608,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -99823,11 +99823,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -99844,23 +99844,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -99885,7 +99885,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -99893,7 +99893,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -99958,12 +99958,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -100053,7 +100053,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -100111,7 +100111,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100158,7 +100158,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -100273,7 +100273,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100281,7 +100281,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -100295,7 +100295,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -100421,7 +100421,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100497,7 +100497,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100509,15 +100509,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -100535,7 +100535,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100603,7 +100603,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -100615,7 +100615,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -100647,7 +100647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -100657,19 +100657,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -100683,7 +100683,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100697,11 +100697,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -100709,7 +100709,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -100721,7 +100721,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -100751,11 +100751,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -100765,7 +100765,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -100777,11 +100777,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -100799,7 +100799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -101014,11 +101014,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -101035,23 +101035,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -101076,7 +101076,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101084,7 +101084,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -101149,12 +101149,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -101244,7 +101244,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -101270,7 +101270,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101317,7 +101317,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -101432,7 +101432,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101440,7 +101440,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -101462,7 +101462,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101538,7 +101538,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101550,15 +101550,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -101576,7 +101576,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101644,7 +101644,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -101656,7 +101656,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -101688,7 +101688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -101698,19 +101698,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -101724,7 +101724,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -101738,11 +101738,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -101781,7 +101781,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -101803,7 +101803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -101834,11 +101834,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -101854,7 +101854,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -101876,7 +101876,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -101892,7 +101892,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -101900,7 +101900,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -101953,7 +101953,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -101987,15 +101987,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -102019,7 +102019,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102045,7 +102045,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102053,7 +102053,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -102075,11 +102075,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -102093,11 +102093,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102105,7 +102105,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102129,7 +102129,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -102137,7 +102137,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -102201,11 +102201,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102213,7 +102213,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102237,11 +102237,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -102327,11 +102327,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102339,7 +102339,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102385,11 +102385,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102397,7 +102397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102421,7 +102421,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -102449,11 +102449,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -102463,7 +102463,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102471,7 +102471,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -102501,7 +102501,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102527,11 +102527,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102539,7 +102539,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -102569,7 +102569,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102577,16 +102577,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -102647,7 +102647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102655,7 +102655,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102705,7 +102705,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102713,7 +102713,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -102747,7 +102747,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102763,7 +102763,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102771,7 +102771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -102801,7 +102801,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102837,7 +102837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -102845,7 +102845,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -103115,7 +103115,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103123,11 +103123,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -103184,7 +103184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103192,7 +103192,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -103279,7 +103279,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103287,7 +103287,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -103407,11 +103407,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -103625,7 +103625,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -103665,7 +103665,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103694,11 +103694,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -103728,7 +103728,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103778,15 +103778,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103829,7 +103829,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -103851,7 +103851,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -103946,7 +103946,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -103992,7 +103992,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -104026,11 +104026,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -104040,7 +104040,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104052,11 +104052,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -104074,7 +104074,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -104289,11 +104289,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -104310,23 +104310,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -104351,7 +104351,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104359,7 +104359,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -104424,12 +104424,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -104519,7 +104519,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -104545,7 +104545,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104592,7 +104592,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -104707,7 +104707,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104715,7 +104715,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -104737,7 +104737,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104813,7 +104813,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104825,15 +104825,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -104851,7 +104851,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -104919,7 +104919,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -104931,7 +104931,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -104963,7 +104963,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -104973,19 +104973,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -104999,7 +104999,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105063,11 +105063,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -105077,7 +105077,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105089,11 +105089,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -105111,7 +105111,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -105326,11 +105326,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -105347,23 +105347,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -105388,7 +105388,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105396,7 +105396,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -105461,12 +105461,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -105556,7 +105556,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -105582,7 +105582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105629,7 +105629,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -105744,7 +105744,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105752,7 +105752,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -105774,7 +105774,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105850,7 +105850,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105862,15 +105862,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -105888,7 +105888,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -105956,7 +105956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -105968,7 +105968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -106000,7 +106000,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -106010,19 +106010,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -106036,7 +106036,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -106096,7 +106096,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -106118,7 +106118,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106134,7 +106134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -106142,7 +106142,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -106195,7 +106195,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106229,15 +106229,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -106261,7 +106261,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106287,7 +106287,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106295,7 +106295,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -106319,11 +106319,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -106331,7 +106331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -106381,7 +106381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -106417,7 +106417,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -106489,7 +106489,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -106601,7 +106601,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -106659,7 +106659,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -106683,7 +106683,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -106713,7 +106713,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106721,16 +106721,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -106772,11 +106772,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -106786,7 +106786,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106794,7 +106794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -106824,7 +106824,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106854,7 +106854,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106862,7 +106862,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -106892,7 +106892,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106900,7 +106900,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -106976,7 +106976,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -106984,7 +106984,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -107016,7 +107016,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -107145,7 +107145,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -107219,11 +107219,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -107233,7 +107233,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -107245,11 +107245,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -107267,7 +107267,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -107482,11 +107482,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -107503,23 +107503,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -107544,7 +107544,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -107552,7 +107552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -107617,12 +107617,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -107712,7 +107712,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -107738,7 +107738,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -107785,7 +107785,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -107900,7 +107900,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -107908,7 +107908,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -107930,7 +107930,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -108006,7 +108006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -108018,15 +108018,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -108044,7 +108044,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -108112,7 +108112,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -108124,7 +108124,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -108156,7 +108156,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -108166,19 +108166,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -108192,7 +108192,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -108200,7 +108200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -108209,17 +108209,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -108227,15 +108227,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -108351,19 +108351,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -108372,7 +108372,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -108392,11 +108392,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -108418,7 +108418,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -108437,14 +108437,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -108460,7 +108460,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -108484,7 +108484,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -108516,7 +108516,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -108530,12 +108530,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -108636,7 +108636,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -108657,7 +108657,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -108670,14 +108670,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -108745,7 +108745,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -108777,7 +108777,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -108809,7 +108809,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -108841,7 +108841,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -108903,7 +108903,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -108952,7 +108952,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -108988,7 +108988,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109026,7 +109026,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109100,7 +109100,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109132,7 +109132,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.generating"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109164,7 +109164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109204,7 +109204,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.partial_image"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -109230,7 +109230,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -109282,7 +109282,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -109294,7 +109294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -109380,11 +109380,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -109422,7 +109422,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -109457,7 +109457,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -109494,7 +109494,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -109698,7 +109698,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -109706,7 +109706,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -109750,7 +109750,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -109758,11 +109758,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -109813,11 +109813,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -109874,7 +109874,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -109882,7 +109882,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -109929,7 +109929,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -109965,7 +109965,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -110005,7 +110005,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -110074,7 +110074,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110115,11 +110115,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -110127,15 +110127,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110143,7 +110143,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -110209,7 +110209,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -110249,7 +110249,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110284,7 +110284,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110292,7 +110292,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -110361,7 +110361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -110381,7 +110381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -110393,15 +110393,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -110431,23 +110431,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -110463,11 +110463,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110475,7 +110475,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -110499,15 +110499,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -110561,11 +110561,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110605,11 +110605,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110735,11 +110735,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110759,11 +110759,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -110771,7 +110771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -110783,7 +110783,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -110807,11 +110807,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -110821,7 +110821,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -110833,11 +110833,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -110855,7 +110855,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -111070,11 +111070,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -111091,23 +111091,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -111132,7 +111132,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111140,7 +111140,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -111205,12 +111205,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -111300,7 +111300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -111358,7 +111358,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111405,7 +111405,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -111520,7 +111520,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111528,7 +111528,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -111542,7 +111542,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -111668,7 +111668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111744,7 +111744,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111756,15 +111756,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -111782,7 +111782,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111850,7 +111850,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -111862,7 +111862,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -111894,7 +111894,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -111904,19 +111904,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -111930,7 +111930,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -111944,11 +111944,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -111956,7 +111956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -111968,7 +111968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -111998,11 +111998,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -112012,7 +112012,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112024,11 +112024,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -112046,7 +112046,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -112261,11 +112261,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -112282,23 +112282,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -112323,7 +112323,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112331,7 +112331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -112396,12 +112396,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -112491,7 +112491,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -112517,7 +112517,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112564,7 +112564,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -112679,7 +112679,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112687,7 +112687,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -112709,7 +112709,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112785,7 +112785,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112797,15 +112797,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -112823,7 +112823,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112891,7 +112891,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -112903,7 +112903,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -112935,7 +112935,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -112945,19 +112945,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -112971,7 +112971,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -112985,11 +112985,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113028,7 +113028,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113050,7 +113050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -113081,11 +113081,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113101,7 +113101,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -113123,7 +113123,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113139,7 +113139,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -113147,7 +113147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -113200,7 +113200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113234,15 +113234,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -113266,7 +113266,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113292,7 +113292,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113300,7 +113300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -113322,11 +113322,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -113340,11 +113340,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113352,7 +113352,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113376,7 +113376,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -113384,7 +113384,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -113448,11 +113448,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113460,7 +113460,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113484,11 +113484,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -113574,11 +113574,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113586,7 +113586,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113632,11 +113632,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113644,7 +113644,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113668,7 +113668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -113696,11 +113696,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -113710,7 +113710,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113718,7 +113718,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -113748,7 +113748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113774,11 +113774,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113786,7 +113786,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -113816,7 +113816,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113824,16 +113824,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -113894,7 +113894,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113902,7 +113902,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113952,7 +113952,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -113960,7 +113960,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -113994,7 +113994,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114010,7 +114010,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114018,7 +114018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -114048,7 +114048,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114084,7 +114084,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114092,7 +114092,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -114362,7 +114362,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114370,11 +114370,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -114431,7 +114431,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114439,7 +114439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -114526,7 +114526,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114534,7 +114534,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -114654,11 +114654,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -114872,7 +114872,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -114912,7 +114912,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -114941,11 +114941,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -114975,7 +114975,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -115025,15 +115025,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -115076,7 +115076,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -115098,7 +115098,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -115193,7 +115193,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -115239,7 +115239,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -115273,11 +115273,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -115287,7 +115287,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -115299,11 +115299,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -115321,7 +115321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -115536,11 +115536,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -115557,23 +115557,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -115598,7 +115598,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -115606,7 +115606,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -115671,12 +115671,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -115766,7 +115766,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -115792,7 +115792,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -115839,7 +115839,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -115954,7 +115954,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -115962,7 +115962,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -115984,7 +115984,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116060,7 +116060,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116072,15 +116072,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -116098,7 +116098,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116166,7 +116166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -116178,7 +116178,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -116210,7 +116210,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -116220,19 +116220,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -116246,7 +116246,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116310,11 +116310,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -116324,7 +116324,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116336,11 +116336,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -116358,7 +116358,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -116573,11 +116573,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -116594,23 +116594,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -116635,7 +116635,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116643,7 +116643,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -116708,12 +116708,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -116803,7 +116803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -116829,7 +116829,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116876,7 +116876,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -116991,7 +116991,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -116999,7 +116999,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -117021,7 +117021,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -117097,7 +117097,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -117109,15 +117109,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -117135,7 +117135,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -117203,7 +117203,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -117215,7 +117215,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -117247,7 +117247,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -117257,19 +117257,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -117283,7 +117283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -117343,7 +117343,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -117365,7 +117365,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -117381,7 +117381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -117389,7 +117389,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -117442,7 +117442,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -117476,15 +117476,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -117508,7 +117508,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -117534,7 +117534,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -117542,7 +117542,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -117566,11 +117566,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -117578,7 +117578,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -117628,7 +117628,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -117664,7 +117664,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -117736,7 +117736,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -117848,7 +117848,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -117906,7 +117906,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -117930,7 +117930,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -117960,7 +117960,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -117968,16 +117968,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -118019,11 +118019,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -118033,7 +118033,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -118041,7 +118041,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -118071,7 +118071,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -118101,7 +118101,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -118109,7 +118109,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -118139,7 +118139,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -118147,7 +118147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -118223,7 +118223,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -118231,7 +118231,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -118263,7 +118263,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -118392,7 +118392,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -118466,11 +118466,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -118480,7 +118480,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -118492,11 +118492,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -118514,7 +118514,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -118729,11 +118729,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -118750,23 +118750,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -118791,7 +118791,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -118799,7 +118799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -118864,12 +118864,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -118959,7 +118959,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -118985,7 +118985,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119032,7 +119032,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -119147,7 +119147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119155,7 +119155,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -119177,7 +119177,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119253,7 +119253,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119265,15 +119265,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -119291,7 +119291,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119359,7 +119359,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -119371,7 +119371,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -119403,7 +119403,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -119413,19 +119413,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -119439,7 +119439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -119447,7 +119447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -119456,17 +119456,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -119474,15 +119474,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -119598,19 +119598,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -119619,7 +119619,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -119639,11 +119639,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -119665,7 +119665,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -119684,14 +119684,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -119707,7 +119707,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -119731,7 +119731,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -119763,7 +119763,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -119777,12 +119777,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -119883,7 +119883,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -119904,7 +119904,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -119917,14 +119917,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -119992,7 +119992,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -120049,7 +120049,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -120101,7 +120101,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -120113,7 +120113,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -120199,11 +120199,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -120241,7 +120241,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -120276,7 +120276,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -120313,7 +120313,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -120517,7 +120517,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -120525,7 +120525,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -120569,7 +120569,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -120577,11 +120577,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -120632,11 +120632,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -120693,7 +120693,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -120701,7 +120701,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -120748,7 +120748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -120784,7 +120784,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -120824,7 +120824,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -120893,7 +120893,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -120934,11 +120934,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -120946,15 +120946,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -120962,7 +120962,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -121028,7 +121028,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -121068,7 +121068,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121103,7 +121103,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121111,7 +121111,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -121180,7 +121180,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -121200,7 +121200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -121212,15 +121212,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -121250,23 +121250,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -121282,11 +121282,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121294,7 +121294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -121318,15 +121318,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -121380,11 +121380,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121424,11 +121424,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121554,11 +121554,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121578,11 +121578,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -121590,7 +121590,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -121602,7 +121602,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -121626,11 +121626,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -121640,7 +121640,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -121652,11 +121652,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -121674,7 +121674,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -121889,11 +121889,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -121910,23 +121910,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -121951,7 +121951,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -121959,7 +121959,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -122024,12 +122024,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -122119,7 +122119,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -122177,7 +122177,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122224,7 +122224,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -122339,7 +122339,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122347,7 +122347,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -122361,7 +122361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -122487,7 +122487,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122563,7 +122563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122575,15 +122575,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -122601,7 +122601,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122669,7 +122669,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -122681,7 +122681,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -122713,7 +122713,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -122723,19 +122723,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -122749,7 +122749,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122763,11 +122763,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -122775,7 +122775,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -122787,7 +122787,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -122817,11 +122817,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -122831,7 +122831,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -122843,11 +122843,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -122865,7 +122865,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -123080,11 +123080,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -123101,23 +123101,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -123142,7 +123142,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123150,7 +123150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -123215,12 +123215,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -123310,7 +123310,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -123336,7 +123336,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123383,7 +123383,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -123498,7 +123498,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123506,7 +123506,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -123528,7 +123528,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123604,7 +123604,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123616,15 +123616,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -123642,7 +123642,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123710,7 +123710,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -123722,7 +123722,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -123754,7 +123754,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -123764,19 +123764,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -123790,7 +123790,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -123804,11 +123804,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -123847,7 +123847,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -123869,7 +123869,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -123900,11 +123900,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -123920,7 +123920,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -123942,7 +123942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -123958,7 +123958,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -123966,7 +123966,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -124019,7 +124019,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124053,15 +124053,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -124085,7 +124085,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124111,7 +124111,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124119,7 +124119,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -124141,11 +124141,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -124159,11 +124159,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124171,7 +124171,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124195,7 +124195,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -124203,7 +124203,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -124267,11 +124267,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124279,7 +124279,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124303,11 +124303,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -124393,11 +124393,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124405,7 +124405,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124451,11 +124451,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124463,7 +124463,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124487,7 +124487,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -124515,11 +124515,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -124529,7 +124529,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124537,7 +124537,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -124567,7 +124567,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124593,11 +124593,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124605,7 +124605,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -124635,7 +124635,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124643,16 +124643,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -124713,7 +124713,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124721,7 +124721,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124771,7 +124771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124779,7 +124779,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -124813,7 +124813,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124829,7 +124829,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124837,7 +124837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -124867,7 +124867,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124903,7 +124903,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -124911,7 +124911,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -125181,7 +125181,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125189,11 +125189,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -125250,7 +125250,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125258,7 +125258,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -125345,7 +125345,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125353,7 +125353,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -125473,11 +125473,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -125691,7 +125691,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -125731,7 +125731,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125760,11 +125760,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -125794,7 +125794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125844,15 +125844,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125895,7 +125895,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -125917,7 +125917,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -126012,7 +126012,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -126058,7 +126058,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -126092,11 +126092,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -126106,7 +126106,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126118,11 +126118,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -126140,7 +126140,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -126355,11 +126355,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -126376,23 +126376,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -126417,7 +126417,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126425,7 +126425,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -126490,12 +126490,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -126585,7 +126585,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -126611,7 +126611,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126658,7 +126658,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -126773,7 +126773,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126781,7 +126781,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -126803,7 +126803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126879,7 +126879,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126891,15 +126891,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -126917,7 +126917,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -126985,7 +126985,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -126997,7 +126997,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -127029,7 +127029,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -127039,19 +127039,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -127065,7 +127065,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127129,11 +127129,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -127143,7 +127143,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127155,11 +127155,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -127177,7 +127177,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -127392,11 +127392,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -127413,23 +127413,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -127454,7 +127454,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127462,7 +127462,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -127527,12 +127527,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -127622,7 +127622,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -127648,7 +127648,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127695,7 +127695,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -127810,7 +127810,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127818,7 +127818,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -127840,7 +127840,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127916,7 +127916,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -127928,15 +127928,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -127954,7 +127954,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -128022,7 +128022,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -128034,7 +128034,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -128066,7 +128066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -128076,19 +128076,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -128102,7 +128102,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -128162,7 +128162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -128184,7 +128184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128200,7 +128200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -128208,7 +128208,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -128261,7 +128261,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128295,15 +128295,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -128327,7 +128327,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128353,7 +128353,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128361,7 +128361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -128385,11 +128385,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -128397,7 +128397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -128447,7 +128447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -128483,7 +128483,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -128555,7 +128555,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -128667,7 +128667,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -128725,7 +128725,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -128749,7 +128749,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -128779,7 +128779,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128787,16 +128787,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -128838,11 +128838,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -128852,7 +128852,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128860,7 +128860,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -128890,7 +128890,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128920,7 +128920,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128928,7 +128928,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -128958,7 +128958,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -128966,7 +128966,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -129042,7 +129042,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -129050,7 +129050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -129082,7 +129082,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -129211,7 +129211,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -129285,11 +129285,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -129299,7 +129299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -129311,11 +129311,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -129333,7 +129333,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -129548,11 +129548,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -129569,23 +129569,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -129610,7 +129610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -129618,7 +129618,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -129683,12 +129683,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -129778,7 +129778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -129804,7 +129804,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -129851,7 +129851,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -129966,7 +129966,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -129974,7 +129974,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -129996,7 +129996,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -130072,7 +130072,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -130084,15 +130084,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -130110,7 +130110,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -130178,7 +130178,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -130190,7 +130190,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -130222,7 +130222,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -130232,19 +130232,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -130258,7 +130258,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -130266,7 +130266,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -130275,17 +130275,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -130293,15 +130293,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -130417,19 +130417,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -130438,7 +130438,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -130458,11 +130458,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -130484,7 +130484,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -130503,14 +130503,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -130526,7 +130526,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -130550,7 +130550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -130582,7 +130582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -130596,12 +130596,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -130702,7 +130702,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -130723,7 +130723,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -130736,14 +130736,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -130811,7 +130811,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.incomplete"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -130925,11 +130925,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -130967,7 +130967,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -131002,7 +131002,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -131039,7 +131039,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131243,7 +131243,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131251,7 +131251,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -131295,7 +131295,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131303,11 +131303,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -131358,11 +131358,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -131419,7 +131419,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -131427,7 +131427,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -131474,7 +131474,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -131510,7 +131510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -131550,7 +131550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -131619,7 +131619,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131660,11 +131660,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -131672,15 +131672,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131688,7 +131688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -131754,7 +131754,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -131794,7 +131794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131829,7 +131829,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -131837,7 +131837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -131906,7 +131906,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -131926,7 +131926,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -131938,15 +131938,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -131976,23 +131976,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -132008,11 +132008,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -132020,7 +132020,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -132044,15 +132044,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -132106,11 +132106,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -132150,11 +132150,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -132280,11 +132280,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -132304,11 +132304,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -132316,7 +132316,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -132328,7 +132328,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -132352,11 +132352,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -132366,7 +132366,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -132378,11 +132378,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -132400,7 +132400,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -132615,11 +132615,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -132636,23 +132636,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -132677,7 +132677,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -132685,7 +132685,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -132750,12 +132750,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -132845,7 +132845,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -132903,7 +132903,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -132950,7 +132950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -133065,7 +133065,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133073,7 +133073,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -133087,7 +133087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -133213,7 +133213,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133289,7 +133289,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133301,15 +133301,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -133327,7 +133327,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133395,7 +133395,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -133407,7 +133407,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -133439,7 +133439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -133449,19 +133449,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -133475,7 +133475,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133489,11 +133489,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -133501,7 +133501,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -133513,7 +133513,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -133543,11 +133543,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -133557,7 +133557,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133569,11 +133569,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -133591,7 +133591,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -133806,11 +133806,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -133827,23 +133827,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -133868,7 +133868,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -133876,7 +133876,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -133941,12 +133941,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -134036,7 +134036,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -134062,7 +134062,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134109,7 +134109,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -134224,7 +134224,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134232,7 +134232,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -134254,7 +134254,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134330,7 +134330,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134342,15 +134342,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -134368,7 +134368,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134436,7 +134436,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -134448,7 +134448,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -134480,7 +134480,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -134490,19 +134490,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -134516,7 +134516,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -134530,11 +134530,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134573,7 +134573,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134595,7 +134595,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -134626,11 +134626,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134646,7 +134646,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -134668,7 +134668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134684,7 +134684,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -134692,7 +134692,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -134745,7 +134745,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134779,15 +134779,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -134811,7 +134811,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134837,7 +134837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134845,7 +134845,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -134867,11 +134867,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -134885,11 +134885,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -134897,7 +134897,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -134921,7 +134921,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -134929,7 +134929,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -134993,11 +134993,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135005,7 +135005,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -135029,11 +135029,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -135119,11 +135119,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135131,7 +135131,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -135177,11 +135177,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135189,7 +135189,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -135213,7 +135213,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -135241,11 +135241,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -135255,7 +135255,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135263,7 +135263,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -135293,7 +135293,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135319,11 +135319,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135331,7 +135331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -135361,7 +135361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135369,16 +135369,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -135439,7 +135439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135447,7 +135447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -135497,7 +135497,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135505,7 +135505,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -135539,7 +135539,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135555,7 +135555,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135563,7 +135563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -135593,7 +135593,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135629,7 +135629,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -135743,11 +135743,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -135785,7 +135785,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -135820,7 +135820,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -135857,7 +135857,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136061,7 +136061,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136069,7 +136069,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -136113,7 +136113,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136121,11 +136121,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -136176,11 +136176,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -136237,7 +136237,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -136245,7 +136245,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -136292,7 +136292,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -136328,7 +136328,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -136368,7 +136368,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -136437,7 +136437,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136478,11 +136478,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -136490,15 +136490,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136506,7 +136506,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -136572,7 +136572,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -136612,7 +136612,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136647,7 +136647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136655,7 +136655,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -136724,7 +136724,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -136744,7 +136744,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -136756,15 +136756,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -136794,23 +136794,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -136826,11 +136826,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136838,7 +136838,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -136862,15 +136862,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -136924,11 +136924,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -136968,11 +136968,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -137098,11 +137098,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -137122,11 +137122,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -137134,7 +137134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -137146,7 +137146,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -137170,11 +137170,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -137184,7 +137184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -137196,11 +137196,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -137218,7 +137218,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -137433,11 +137433,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -137454,23 +137454,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -137495,7 +137495,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -137503,7 +137503,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -137568,12 +137568,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -137663,7 +137663,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -137721,7 +137721,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -137768,7 +137768,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -137883,7 +137883,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -137891,7 +137891,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -137905,7 +137905,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -138031,7 +138031,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138107,7 +138107,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138119,15 +138119,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -138145,7 +138145,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138213,7 +138213,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -138225,7 +138225,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -138257,7 +138257,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -138267,19 +138267,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -138293,7 +138293,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138307,11 +138307,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -138319,7 +138319,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -138331,7 +138331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -138361,11 +138361,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -138375,7 +138375,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138387,11 +138387,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -138409,7 +138409,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -138624,11 +138624,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -138645,23 +138645,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -138686,7 +138686,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138694,7 +138694,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -138759,12 +138759,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -138854,7 +138854,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -138880,7 +138880,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -138927,7 +138927,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -139042,7 +139042,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -139050,7 +139050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -139072,7 +139072,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -139148,7 +139148,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -139160,15 +139160,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -139186,7 +139186,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -139254,7 +139254,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -139266,7 +139266,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -139298,7 +139298,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -139308,19 +139308,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -139334,7 +139334,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -139348,11 +139348,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139391,7 +139391,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139413,7 +139413,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -139444,11 +139444,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139464,7 +139464,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -139486,7 +139486,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139502,7 +139502,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -139510,7 +139510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -139563,7 +139563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139597,15 +139597,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -139629,7 +139629,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139655,7 +139655,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139663,7 +139663,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -139685,11 +139685,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -139703,11 +139703,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139715,7 +139715,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -139739,7 +139739,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -139747,7 +139747,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -139811,11 +139811,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139823,7 +139823,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -139847,11 +139847,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -139937,11 +139937,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -139949,7 +139949,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -139995,11 +139995,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140007,7 +140007,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -140031,7 +140031,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -140059,11 +140059,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -140073,7 +140073,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140081,7 +140081,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -140111,7 +140111,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140137,11 +140137,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140149,7 +140149,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -140179,7 +140179,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140187,16 +140187,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -140257,7 +140257,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140265,7 +140265,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -140315,7 +140315,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140323,7 +140323,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -140357,7 +140357,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140373,7 +140373,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140381,7 +140381,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -140411,7 +140411,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140447,7 +140447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -140553,11 +140553,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -140595,7 +140595,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -140643,7 +140643,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -140687,23 +140687,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -140737,11 +140737,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -140767,7 +140767,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -140779,15 +140779,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -140850,11 +140850,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -140892,7 +140892,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -140973,11 +140973,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -141015,7 +141015,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -141053,7 +141053,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -141114,7 +141114,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -141164,7 +141164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141200,7 +141200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141232,7 +141232,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141264,7 +141264,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141296,7 +141296,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141328,7 +141328,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141360,7 +141360,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141392,7 +141392,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -141605,7 +141605,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -141613,7 +141613,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -141657,7 +141657,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -141665,11 +141665,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -141726,7 +141726,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -141734,7 +141734,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -141838,11 +141838,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -141880,7 +141880,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -141919,7 +141919,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -141927,7 +141927,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -142047,11 +142047,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -142265,7 +142265,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -142305,7 +142305,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -142334,11 +142334,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -142395,7 +142395,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -142403,7 +142403,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -142450,7 +142450,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -142486,7 +142486,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -142526,7 +142526,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -142595,7 +142595,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -142660,15 +142660,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -142711,7 +142711,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -142733,7 +142733,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -142828,7 +142828,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -142874,7 +142874,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -142908,11 +142908,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -142922,7 +142922,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -142934,11 +142934,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -142956,7 +142956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -143171,11 +143171,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -143192,23 +143192,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -143233,7 +143233,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143241,7 +143241,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -143306,12 +143306,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -143401,7 +143401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -143459,7 +143459,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143506,7 +143506,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -143621,7 +143621,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143629,7 +143629,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -143643,7 +143643,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -143769,7 +143769,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143845,7 +143845,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143857,15 +143857,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -143883,7 +143883,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -143951,7 +143951,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -143963,7 +143963,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -143995,7 +143995,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -144005,19 +144005,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -144031,7 +144031,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144095,11 +144095,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -144109,7 +144109,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144121,11 +144121,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -144143,7 +144143,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -144358,11 +144358,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -144379,23 +144379,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -144420,7 +144420,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144428,7 +144428,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -144493,12 +144493,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -144588,7 +144588,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -144614,7 +144614,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144661,7 +144661,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -144776,7 +144776,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144784,7 +144784,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -144806,7 +144806,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144882,7 +144882,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144894,15 +144894,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -144920,7 +144920,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -144988,7 +144988,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -145000,7 +145000,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -145032,7 +145032,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -145042,19 +145042,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -145068,7 +145068,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -145128,7 +145128,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -145150,7 +145150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145166,7 +145166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -145174,7 +145174,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -145227,7 +145227,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145261,15 +145261,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -145293,7 +145293,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145319,7 +145319,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145327,7 +145327,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -145351,11 +145351,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -145363,7 +145363,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -145413,7 +145413,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -145449,7 +145449,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -145521,7 +145521,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -145633,7 +145633,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -145691,7 +145691,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -145715,7 +145715,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -145745,7 +145745,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145753,16 +145753,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -145804,11 +145804,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -145818,7 +145818,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145826,7 +145826,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -145856,7 +145856,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145886,7 +145886,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145894,7 +145894,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -145924,7 +145924,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -145932,7 +145932,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -146008,7 +146008,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146016,7 +146016,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -146233,7 +146233,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146241,7 +146241,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -146285,7 +146285,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146293,11 +146293,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -146354,7 +146354,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146362,7 +146362,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -146466,11 +146466,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -146508,7 +146508,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -146547,7 +146547,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146555,7 +146555,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -146675,11 +146675,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -146893,7 +146893,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -146933,7 +146933,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -146962,11 +146962,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -147023,7 +147023,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -147031,7 +147031,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -147078,7 +147078,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -147114,7 +147114,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -147154,7 +147154,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -147223,7 +147223,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -147288,15 +147288,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -147339,7 +147339,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -147361,7 +147361,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -147456,7 +147456,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -147502,7 +147502,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -147536,11 +147536,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -147550,7 +147550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -147562,11 +147562,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -147584,7 +147584,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -147799,11 +147799,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -147820,23 +147820,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -147861,7 +147861,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -147869,7 +147869,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -147934,12 +147934,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -148029,7 +148029,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -148087,7 +148087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148134,7 +148134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -148249,7 +148249,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148257,7 +148257,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -148271,7 +148271,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -148397,7 +148397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148473,7 +148473,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148485,15 +148485,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -148511,7 +148511,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148579,7 +148579,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -148591,7 +148591,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -148623,7 +148623,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -148633,19 +148633,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -148659,7 +148659,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148723,11 +148723,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -148737,7 +148737,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -148749,11 +148749,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -148771,7 +148771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -148986,11 +148986,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -149007,23 +149007,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -149048,7 +149048,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149056,7 +149056,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -149121,12 +149121,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -149216,7 +149216,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -149242,7 +149242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149289,7 +149289,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -149404,7 +149404,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149412,7 +149412,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -149434,7 +149434,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149510,7 +149510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149522,15 +149522,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -149548,7 +149548,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149616,7 +149616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -149628,7 +149628,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -149660,7 +149660,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -149670,19 +149670,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -149696,7 +149696,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -149756,7 +149756,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -149778,7 +149778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -149794,7 +149794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -149802,7 +149802,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -149855,7 +149855,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -149889,15 +149889,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -149921,7 +149921,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -149947,7 +149947,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -149955,7 +149955,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -149979,11 +149979,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -149991,7 +149991,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -150041,7 +150041,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150077,7 +150077,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -150149,7 +150149,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150261,7 +150261,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150319,7 +150319,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150343,7 +150343,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -150373,7 +150373,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150381,16 +150381,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -150432,11 +150432,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -150446,7 +150446,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150454,7 +150454,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -150484,7 +150484,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150514,7 +150514,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150522,7 +150522,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -150552,7 +150552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150560,7 +150560,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150636,7 +150636,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150644,7 +150644,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -150686,7 +150686,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -150883,7 +150883,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150891,7 +150891,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -150935,7 +150935,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -150943,11 +150943,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -151004,7 +151004,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -151012,7 +151012,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -151116,11 +151116,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -151158,7 +151158,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -151197,7 +151197,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -151205,7 +151205,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -151325,11 +151325,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -151543,7 +151543,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -151583,7 +151583,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -151612,11 +151612,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -151673,7 +151673,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -151681,7 +151681,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -151728,7 +151728,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -151764,7 +151764,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -151804,7 +151804,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -151873,7 +151873,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -151938,15 +151938,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -151989,7 +151989,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -152011,7 +152011,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -152106,7 +152106,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -152152,7 +152152,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -152186,11 +152186,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -152200,7 +152200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -152212,11 +152212,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -152234,7 +152234,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -152449,11 +152449,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -152470,23 +152470,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -152511,7 +152511,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -152519,7 +152519,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -152584,12 +152584,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -152679,7 +152679,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -152737,7 +152737,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -152784,7 +152784,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -152899,7 +152899,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -152907,7 +152907,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -152921,7 +152921,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -153047,7 +153047,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153123,7 +153123,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153135,15 +153135,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -153161,7 +153161,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153229,7 +153229,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -153241,7 +153241,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -153273,7 +153273,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -153283,19 +153283,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -153309,7 +153309,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153373,11 +153373,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -153387,7 +153387,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153399,11 +153399,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -153421,7 +153421,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -153636,11 +153636,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -153657,23 +153657,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -153698,7 +153698,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153706,7 +153706,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -153771,12 +153771,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -153866,7 +153866,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -153892,7 +153892,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -153939,7 +153939,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -154054,7 +154054,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -154062,7 +154062,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -154084,7 +154084,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -154160,7 +154160,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -154172,15 +154172,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -154198,7 +154198,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -154266,7 +154266,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -154278,7 +154278,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -154310,7 +154310,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -154320,19 +154320,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -154346,7 +154346,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -154406,7 +154406,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -154428,7 +154428,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -154444,7 +154444,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -154452,7 +154452,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -154505,7 +154505,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -154539,15 +154539,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -154571,7 +154571,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -154597,7 +154597,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -154605,7 +154605,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -154629,11 +154629,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -154641,7 +154641,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -154691,7 +154691,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -154727,7 +154727,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -154799,7 +154799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -154911,7 +154911,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -154969,7 +154969,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -154993,7 +154993,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -155023,7 +155023,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155031,16 +155031,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -155082,11 +155082,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -155096,7 +155096,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155104,7 +155104,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -155134,7 +155134,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155164,7 +155164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155172,7 +155172,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -155202,7 +155202,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155210,7 +155210,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -155286,7 +155286,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155294,7 +155294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -155336,7 +155336,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -155525,7 +155525,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -155533,7 +155533,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -155727,7 +155727,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.annotation.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -155746,7 +155746,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -155800,11 +155800,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -155842,7 +155842,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -155864,7 +155864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"explicit"` - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. @@ -155886,7 +155886,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -155938,7 +155938,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -155950,7 +155950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -156036,11 +156036,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -156078,7 +156078,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -156113,7 +156113,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -156150,7 +156150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156354,7 +156354,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156362,7 +156362,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -156406,7 +156406,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156414,11 +156414,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -156469,11 +156469,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -156530,7 +156530,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -156538,7 +156538,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -156585,7 +156585,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -156621,7 +156621,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -156661,7 +156661,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -156730,7 +156730,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156771,11 +156771,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -156783,15 +156783,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156799,7 +156799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -156865,7 +156865,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -156905,7 +156905,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156940,7 +156940,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -156948,7 +156948,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -157017,7 +157017,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -157037,7 +157037,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -157049,15 +157049,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -157087,23 +157087,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -157119,11 +157119,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -157131,7 +157131,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -157155,15 +157155,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -157217,11 +157217,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -157261,11 +157261,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -157391,11 +157391,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -157415,11 +157415,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -157427,7 +157427,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -157439,7 +157439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -157463,11 +157463,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -157477,7 +157477,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -157489,11 +157489,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -157511,7 +157511,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -157726,11 +157726,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -157747,23 +157747,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -157788,7 +157788,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -157796,7 +157796,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -157861,12 +157861,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -157956,7 +157956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -158014,7 +158014,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158061,7 +158061,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -158176,7 +158176,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158184,7 +158184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -158198,7 +158198,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -158324,7 +158324,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158400,7 +158400,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158412,15 +158412,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -158438,7 +158438,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158506,7 +158506,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -158518,7 +158518,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -158550,7 +158550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -158560,19 +158560,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -158586,7 +158586,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158600,11 +158600,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -158612,7 +158612,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -158624,7 +158624,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -158654,11 +158654,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -158668,7 +158668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158680,11 +158680,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -158702,7 +158702,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -158917,11 +158917,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -158938,23 +158938,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -158979,7 +158979,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -158987,7 +158987,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -159052,12 +159052,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -159147,7 +159147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -159173,7 +159173,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159220,7 +159220,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -159335,7 +159335,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159343,7 +159343,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -159365,7 +159365,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159441,7 +159441,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159453,15 +159453,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -159479,7 +159479,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159547,7 +159547,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -159559,7 +159559,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -159591,7 +159591,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -159601,19 +159601,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -159627,7 +159627,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -159641,11 +159641,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159684,7 +159684,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159706,7 +159706,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -159737,11 +159737,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159757,7 +159757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -159779,7 +159779,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159795,7 +159795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -159803,7 +159803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -159856,7 +159856,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159890,15 +159890,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -159922,7 +159922,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159948,7 +159948,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -159956,7 +159956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -159978,11 +159978,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -159996,11 +159996,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160008,7 +160008,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160032,7 +160032,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -160040,7 +160040,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -160104,11 +160104,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160116,7 +160116,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160140,11 +160140,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -160230,11 +160230,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160242,7 +160242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160288,11 +160288,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160300,7 +160300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160324,7 +160324,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -160352,11 +160352,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -160366,7 +160366,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160374,7 +160374,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -160404,7 +160404,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160430,11 +160430,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160442,7 +160442,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -160472,7 +160472,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160480,16 +160480,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -160550,7 +160550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160558,7 +160558,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160608,7 +160608,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160616,7 +160616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -160650,7 +160650,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160666,7 +160666,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160674,7 +160674,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -160704,7 +160704,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160740,7 +160740,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -160748,7 +160748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -161018,7 +161018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161026,11 +161026,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -161087,7 +161087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161095,7 +161095,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -161182,7 +161182,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161190,7 +161190,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -161310,11 +161310,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -161528,7 +161528,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -161568,7 +161568,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161597,11 +161597,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -161631,7 +161631,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161681,15 +161681,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161732,7 +161732,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -161754,7 +161754,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -161849,7 +161849,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -161895,7 +161895,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -161929,11 +161929,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -161943,7 +161943,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -161955,11 +161955,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -161977,7 +161977,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -162192,11 +162192,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -162213,23 +162213,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -162254,7 +162254,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162262,7 +162262,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -162327,12 +162327,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -162422,7 +162422,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -162448,7 +162448,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162495,7 +162495,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -162610,7 +162610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162618,7 +162618,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -162640,7 +162640,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162716,7 +162716,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162728,15 +162728,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -162754,7 +162754,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162822,7 +162822,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -162834,7 +162834,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -162866,7 +162866,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -162876,19 +162876,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -162902,7 +162902,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162966,11 +162966,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -162980,7 +162980,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -162992,11 +162992,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -163014,7 +163014,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -163229,11 +163229,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -163250,23 +163250,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -163291,7 +163291,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163299,7 +163299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -163364,12 +163364,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -163459,7 +163459,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -163485,7 +163485,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163532,7 +163532,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -163647,7 +163647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163655,7 +163655,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -163677,7 +163677,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163753,7 +163753,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163765,15 +163765,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -163791,7 +163791,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163859,7 +163859,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -163871,7 +163871,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -163903,7 +163903,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -163913,19 +163913,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -163939,7 +163939,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -163999,7 +163999,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -164021,7 +164021,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164037,7 +164037,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -164045,7 +164045,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -164098,7 +164098,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164132,15 +164132,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -164164,7 +164164,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164190,7 +164190,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164198,7 +164198,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -164222,11 +164222,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -164234,7 +164234,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -164284,7 +164284,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164320,7 +164320,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -164392,7 +164392,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164504,7 +164504,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164562,7 +164562,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164586,7 +164586,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -164616,7 +164616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164624,16 +164624,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -164675,11 +164675,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -164689,7 +164689,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164697,7 +164697,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -164727,7 +164727,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164757,7 +164757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164765,7 +164765,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -164795,7 +164795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164803,7 +164803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164879,7 +164879,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -164887,7 +164887,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -164919,7 +164919,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -165048,7 +165048,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -165122,11 +165122,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -165136,7 +165136,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165148,11 +165148,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -165170,7 +165170,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -165385,11 +165385,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -165406,23 +165406,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -165447,7 +165447,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165455,7 +165455,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -165520,12 +165520,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -165615,7 +165615,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -165641,7 +165641,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165688,7 +165688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -165803,7 +165803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165811,7 +165811,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -165833,7 +165833,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165909,7 +165909,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -165921,15 +165921,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -165947,7 +165947,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -166015,7 +166015,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -166027,7 +166027,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -166059,7 +166059,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -166069,19 +166069,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -166095,7 +166095,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -166103,7 +166103,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -166112,17 +166112,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -166130,15 +166130,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -166254,19 +166254,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -166275,7 +166275,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -166295,11 +166295,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -166321,7 +166321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -166340,14 +166340,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -166363,7 +166363,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -166387,7 +166387,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -166419,7 +166419,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -166433,12 +166433,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -166539,7 +166539,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -166560,7 +166560,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -166573,14 +166573,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -166648,7 +166648,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.queued"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166698,7 +166698,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166748,7 +166748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166795,7 +166795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166835,7 +166835,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166875,7 +166875,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166915,7 +166915,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166955,7 +166955,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -166995,7 +166995,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167046,7 +167046,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167068,7 +167068,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167094,7 +167094,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167116,7 +167116,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167150,7 +167150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167184,7 +167184,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167214,7 +167214,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167244,7 +167244,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167274,7 +167274,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.interpreting"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -167298,7 +167298,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -167350,7 +167350,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -167362,7 +167362,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -167448,11 +167448,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -167490,7 +167490,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -167525,7 +167525,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -167562,7 +167562,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -167766,7 +167766,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -167774,7 +167774,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -167818,7 +167818,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -167826,11 +167826,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -167881,11 +167881,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -167942,7 +167942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -167950,7 +167950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -167997,7 +167997,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -168033,7 +168033,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -168073,7 +168073,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -168142,7 +168142,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168183,11 +168183,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -168195,15 +168195,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168211,7 +168211,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -168277,7 +168277,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -168317,7 +168317,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168352,7 +168352,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168360,7 +168360,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -168429,7 +168429,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -168449,7 +168449,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -168461,15 +168461,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -168499,23 +168499,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -168531,11 +168531,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168543,7 +168543,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -168567,15 +168567,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -168629,11 +168629,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168673,11 +168673,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168803,11 +168803,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168827,11 +168827,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -168839,7 +168839,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -168851,7 +168851,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -168875,11 +168875,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -168889,7 +168889,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -168901,11 +168901,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -168923,7 +168923,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -169138,11 +169138,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -169159,23 +169159,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -169200,7 +169200,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169208,7 +169208,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -169273,12 +169273,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -169368,7 +169368,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -169426,7 +169426,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169473,7 +169473,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -169588,7 +169588,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169596,7 +169596,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -169610,7 +169610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -169736,7 +169736,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169812,7 +169812,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169824,15 +169824,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -169850,7 +169850,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -169918,7 +169918,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -169930,7 +169930,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -169962,7 +169962,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -169972,19 +169972,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -169998,7 +169998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170012,11 +170012,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -170024,7 +170024,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -170036,7 +170036,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -170066,11 +170066,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -170080,7 +170080,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170092,11 +170092,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -170114,7 +170114,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -170329,11 +170329,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -170350,23 +170350,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -170391,7 +170391,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170399,7 +170399,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -170464,12 +170464,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -170559,7 +170559,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -170585,7 +170585,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170632,7 +170632,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -170747,7 +170747,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170755,7 +170755,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -170777,7 +170777,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170853,7 +170853,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170865,15 +170865,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -170891,7 +170891,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -170959,7 +170959,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -170971,7 +170971,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -171003,7 +171003,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -171013,19 +171013,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -171039,7 +171039,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -171053,11 +171053,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171096,7 +171096,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171118,7 +171118,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -171149,11 +171149,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171169,7 +171169,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -171191,7 +171191,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171207,7 +171207,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -171215,7 +171215,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -171268,7 +171268,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171302,15 +171302,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -171334,7 +171334,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171360,7 +171360,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171368,7 +171368,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -171390,11 +171390,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -171408,11 +171408,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171420,7 +171420,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -171444,7 +171444,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -171452,7 +171452,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -171516,11 +171516,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171528,7 +171528,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -171552,11 +171552,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -171642,11 +171642,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171654,7 +171654,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -171700,11 +171700,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171712,7 +171712,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -171736,7 +171736,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -171764,11 +171764,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -171778,7 +171778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171786,7 +171786,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -171816,7 +171816,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171842,11 +171842,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171854,7 +171854,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -171884,7 +171884,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171892,16 +171892,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -171962,7 +171962,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -171970,7 +171970,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -172020,7 +172020,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172028,7 +172028,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -172062,7 +172062,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172078,7 +172078,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172086,7 +172086,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -172116,7 +172116,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172152,7 +172152,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172160,7 +172160,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -172430,7 +172430,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172438,11 +172438,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -172499,7 +172499,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172507,7 +172507,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -172594,7 +172594,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -172602,7 +172602,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -172722,11 +172722,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -172940,7 +172940,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -172980,7 +172980,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -173009,11 +173009,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -173043,7 +173043,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -173093,15 +173093,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -173144,7 +173144,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -173166,7 +173166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -173261,7 +173261,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -173307,7 +173307,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -173341,11 +173341,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -173355,7 +173355,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -173367,11 +173367,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -173389,7 +173389,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -173604,11 +173604,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -173625,23 +173625,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -173666,7 +173666,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -173674,7 +173674,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -173739,12 +173739,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -173834,7 +173834,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -173860,7 +173860,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -173907,7 +173907,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -174022,7 +174022,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174030,7 +174030,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -174052,7 +174052,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174128,7 +174128,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174140,15 +174140,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -174166,7 +174166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174234,7 +174234,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -174246,7 +174246,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -174278,7 +174278,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -174288,19 +174288,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -174314,7 +174314,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174378,11 +174378,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -174392,7 +174392,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174404,11 +174404,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -174426,7 +174426,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -174641,11 +174641,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -174662,23 +174662,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -174703,7 +174703,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174711,7 +174711,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -174776,12 +174776,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -174871,7 +174871,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -174897,7 +174897,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -174944,7 +174944,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -175059,7 +175059,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -175067,7 +175067,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -175089,7 +175089,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -175165,7 +175165,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -175177,15 +175177,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -175203,7 +175203,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -175271,7 +175271,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -175283,7 +175283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -175315,7 +175315,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -175325,19 +175325,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -175351,7 +175351,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -175411,7 +175411,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -175433,7 +175433,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -175449,7 +175449,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -175457,7 +175457,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -175510,7 +175510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -175544,15 +175544,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -175576,7 +175576,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -175602,7 +175602,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -175610,7 +175610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -175634,11 +175634,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -175646,7 +175646,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -175696,7 +175696,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -175732,7 +175732,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -175804,7 +175804,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -175916,7 +175916,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -175974,7 +175974,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -175998,7 +175998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -176028,7 +176028,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176036,16 +176036,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -176087,11 +176087,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -176101,7 +176101,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176109,7 +176109,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -176139,7 +176139,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176169,7 +176169,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176177,7 +176177,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -176207,7 +176207,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176215,7 +176215,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -176291,7 +176291,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -176299,7 +176299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -176331,7 +176331,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -176460,7 +176460,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -176534,11 +176534,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -176548,7 +176548,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -176560,11 +176560,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -176582,7 +176582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -176797,11 +176797,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -176818,23 +176818,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -176859,7 +176859,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -176867,7 +176867,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -176932,12 +176932,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -177027,7 +177027,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -177053,7 +177053,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177100,7 +177100,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -177215,7 +177215,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177223,7 +177223,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -177245,7 +177245,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177321,7 +177321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177333,15 +177333,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -177359,7 +177359,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177427,7 +177427,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -177439,7 +177439,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -177471,7 +177471,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -177481,19 +177481,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -177507,7 +177507,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -177515,7 +177515,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -177524,17 +177524,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -177542,15 +177542,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -177666,19 +177666,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -177687,7 +177687,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -177707,11 +177707,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -177733,7 +177733,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -177752,14 +177752,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -177775,7 +177775,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -177799,7 +177799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -177831,7 +177831,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -177845,12 +177845,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -177951,7 +177951,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -177972,7 +177972,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -177985,14 +177985,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -178060,7 +178060,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178120,7 +178120,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178180,7 +178180,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178206,7 +178206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.created"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178218,7 +178218,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Emitted when an error occurs. - - `code: string` + - `code: string or null` The error code. @@ -178226,7 +178226,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The error message. - - `param: string` + - `param: string or null` The error parameter. @@ -178240,7 +178240,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178270,7 +178270,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178300,7 +178300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178330,7 +178330,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178364,7 +178364,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178400,7 +178400,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178426,7 +178426,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178452,7 +178452,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178478,7 +178478,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.incomplete"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178617,7 +178617,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178647,7 +178647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178695,7 +178695,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178743,7 +178743,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178788,7 +178788,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178826,7 +178826,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178864,7 +178864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178902,7 +178902,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178940,7 +178940,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -178978,7 +178978,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179040,7 +179040,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179102,7 +179102,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179132,7 +179132,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179162,7 +179162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179192,7 +179192,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179222,7 +179222,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179252,7 +179252,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.generating"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179282,7 +179282,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179320,7 +179320,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.partial_image"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179354,7 +179354,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179388,7 +179388,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179418,7 +179418,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179448,7 +179448,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179478,7 +179478,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179508,7 +179508,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179538,7 +179538,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179568,7 +179568,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179610,7 +179610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.annotation.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179636,7 +179636,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.queued"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179670,7 +179670,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179704,7 +179704,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179774,7 +179774,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -179795,7 +179795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -179864,7 +179864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -179928,7 +179928,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -180000,7 +180000,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -180032,7 +180032,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -180064,7 +180064,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -180094,12 +180094,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.create"` - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `context_management: optional array of object { type, compact_threshold }` + - `context_management: optional array of object { type, compact_threshold } or null` Context management configuration for this request. @@ -180107,11 +180107,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The context management entry type. Currently only 'compaction' is supported. - - `compact_threshold: optional number` + - `compact_threshold: optional number or null` Token threshold at which compaction should be triggered for this entry. - - `conversation: optional string or BetaResponseConversationParam` + - `conversation: optional string or BetaResponseConversationParam or null` The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. @@ -180128,7 +180128,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation. - - `include: optional array of BetaResponseIncludable` + - `include: optional array of BetaResponseIncludable or null` Specify additional output data to include in the model response. Currently supported values are: @@ -180246,11 +180246,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -180288,7 +180288,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -180323,7 +180323,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -180360,7 +180360,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -180564,7 +180564,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -180572,7 +180572,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -180616,7 +180616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -180624,11 +180624,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -180679,11 +180679,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -180740,7 +180740,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -180748,7 +180748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -180795,7 +180795,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -180831,7 +180831,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -180871,7 +180871,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -180940,7 +180940,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -180981,11 +180981,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -180993,15 +180993,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181009,7 +181009,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -181075,7 +181075,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -181115,7 +181115,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181150,7 +181150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181158,7 +181158,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -181227,7 +181227,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -181247,7 +181247,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -181259,15 +181259,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -181297,23 +181297,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -181329,11 +181329,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181341,7 +181341,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -181365,15 +181365,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -181427,11 +181427,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181471,11 +181471,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181601,11 +181601,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181625,11 +181625,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -181637,7 +181637,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -181649,7 +181649,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -181673,11 +181673,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -181687,7 +181687,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -181699,11 +181699,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -181721,7 +181721,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -181936,11 +181936,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -181957,23 +181957,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -181998,7 +181998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182006,7 +182006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -182071,12 +182071,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -182166,7 +182166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -182224,7 +182224,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182271,7 +182271,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -182386,7 +182386,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182394,7 +182394,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -182408,7 +182408,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -182534,7 +182534,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182610,7 +182610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182622,15 +182622,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -182648,7 +182648,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182716,7 +182716,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -182728,7 +182728,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -182760,7 +182760,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -182770,19 +182770,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -182796,7 +182796,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182810,11 +182810,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -182822,7 +182822,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -182834,7 +182834,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -182864,11 +182864,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -182878,7 +182878,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -182890,11 +182890,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -182912,7 +182912,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -183127,11 +183127,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -183148,23 +183148,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -183189,7 +183189,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183197,7 +183197,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -183262,12 +183262,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -183357,7 +183357,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -183383,7 +183383,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183430,7 +183430,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -183545,7 +183545,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183553,7 +183553,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -183575,7 +183575,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183651,7 +183651,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183663,15 +183663,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -183689,7 +183689,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183757,7 +183757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -183769,7 +183769,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -183801,7 +183801,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -183811,19 +183811,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -183837,7 +183837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -183851,11 +183851,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -183894,7 +183894,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -183916,7 +183916,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -183947,11 +183947,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -183967,7 +183967,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -183989,7 +183989,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184005,7 +184005,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -184013,7 +184013,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -184066,7 +184066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184100,15 +184100,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -184132,7 +184132,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184158,7 +184158,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184166,7 +184166,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -184188,11 +184188,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -184206,11 +184206,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184218,7 +184218,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184242,7 +184242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -184250,7 +184250,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -184314,11 +184314,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184326,7 +184326,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184350,11 +184350,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -184440,11 +184440,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184452,7 +184452,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184498,11 +184498,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184510,7 +184510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184534,7 +184534,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -184562,11 +184562,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -184576,7 +184576,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184584,7 +184584,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -184614,7 +184614,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184640,11 +184640,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184652,7 +184652,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -184682,7 +184682,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184690,16 +184690,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -184760,7 +184760,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184768,7 +184768,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184818,7 +184818,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184826,7 +184826,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -184860,7 +184860,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184876,7 +184876,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184884,7 +184884,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -184914,7 +184914,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184950,7 +184950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -184958,7 +184958,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `instructions: optional string` + - `instructions: optional string or null` A system (or developer) message inserted into the model's context. @@ -184966,15 +184966,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `metadata: optional map[string]` + - `metadata: optional map[string] or null` 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 @@ -185189,7 +185189,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `string` - - `moderation: optional object { model, policy }` + - `moderation: optional object { model, policy } or null` Configuration for running moderation on the input and output of this response. @@ -185197,11 +185197,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'. - - `policy: optional object { input, output }` + - `policy: optional object { input, output } or null` The policy to apply to moderated response input and output. - - `input: optional object { mode }` + - `input: optional object { mode } or null` The moderation policy for the response input. @@ -185211,7 +185211,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"block"` - - `output: optional object { mode }` + - `output: optional object { mode } or null` The moderation policy for the response output. @@ -185221,7 +185221,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"block"` - - `multi_agent: optional object { enabled, max_concurrent_subagents }` + - `multi_agent: optional object { enabled, max_concurrent_subagents } or null` Configuration for server-hosted multi-agent execution. @@ -185234,17 +185234,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ `max_concurrent_subagents` sets the maximum number of subagents that can be active simultaneously across the entire agent tree. It includes all descendants—children, grandchildren, and deeper subagents—but excludes the root agent. The API does not impose a fixed upper bound on this setting. The default is `3`, which is recommended for most workloads. Multi-agent runs also have no fixed limit on tree depth or the total number of subagents created during a run. - - `parallel_tool_calls: optional boolean` + - `parallel_tool_calls: optional boolean or null` Whether to allow the model to run tool calls in parallel. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -185253,7 +185253,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -185273,11 +185273,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -185299,7 +185299,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -185318,14 +185318,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -185341,7 +185341,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -185365,7 +185365,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -185397,7 +185397,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -185411,12 +185411,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -185440,19 +185440,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"fast"` - - `store: optional boolean` + - `store: optional boolean or null` Whether to store the generated model response for later retrieval via API. - - `stream: optional boolean` + - `stream: optional boolean or null` If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](/docs/api-reference/responses-streaming) for more information. - - `stream_options: optional object { include_obfuscation }` + - `stream_options: optional object { include_obfuscation } or null` Options for streaming responses. Only set this when you set `stream: true`. @@ -185466,7 +185466,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. - - `temperature: optional number` + - `temperature: optional number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -185531,7 +185531,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -185552,7 +185552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -185689,7 +185689,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -185763,11 +185763,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -185777,7 +185777,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -185789,11 +185789,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -185811,7 +185811,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -186026,11 +186026,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -186047,23 +186047,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -186088,7 +186088,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186096,7 +186096,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -186161,12 +186161,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -186256,7 +186256,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -186282,7 +186282,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186329,7 +186329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -186444,7 +186444,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186452,7 +186452,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -186474,7 +186474,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186550,7 +186550,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186562,15 +186562,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -186588,7 +186588,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186656,7 +186656,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -186668,7 +186668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -186700,7 +186700,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -186710,19 +186710,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -186736,7 +186736,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -186744,14 +186744,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `top_p: optional number` + - `top_p: optional number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -186760,7 +186760,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -186819,7 +186819,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -186882,7 +186882,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -186890,11 +186890,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -186945,11 +186945,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -186979,7 +186979,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187005,11 +187005,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -187017,15 +187017,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187033,7 +187033,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -187099,7 +187099,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -187139,7 +187139,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187174,7 +187174,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187182,7 +187182,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -187255,11 +187255,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187267,7 +187267,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -187291,15 +187291,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -187353,11 +187353,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187397,11 +187397,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187527,11 +187527,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187551,11 +187551,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -187563,7 +187563,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -187575,7 +187575,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -187599,11 +187599,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -187613,7 +187613,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -187625,11 +187625,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -187647,7 +187647,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -187862,11 +187862,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -187883,23 +187883,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -187924,7 +187924,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -187932,7 +187932,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -187997,12 +187997,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -188092,7 +188092,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -188118,7 +188118,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188165,7 +188165,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -188280,7 +188280,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188288,7 +188288,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -188310,7 +188310,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188386,7 +188386,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188398,15 +188398,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -188424,7 +188424,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188492,7 +188492,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -188504,7 +188504,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -188536,7 +188536,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -188546,19 +188546,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -188572,7 +188572,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188586,11 +188586,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -188598,7 +188598,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -188610,7 +188610,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -188640,11 +188640,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -188654,7 +188654,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188666,11 +188666,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -188688,7 +188688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -188903,11 +188903,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -188924,23 +188924,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -188965,7 +188965,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -188973,7 +188973,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -189038,12 +189038,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -189133,7 +189133,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -189159,7 +189159,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189206,7 +189206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -189321,7 +189321,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189329,7 +189329,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -189351,7 +189351,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189427,7 +189427,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189439,15 +189439,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -189465,7 +189465,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189533,7 +189533,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -189545,7 +189545,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -189577,7 +189577,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -189587,19 +189587,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -189613,7 +189613,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -189627,11 +189627,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189670,7 +189670,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189692,7 +189692,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -189723,11 +189723,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189743,7 +189743,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -189765,7 +189765,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189781,7 +189781,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -189789,7 +189789,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -189842,7 +189842,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189876,15 +189876,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -189908,7 +189908,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189934,7 +189934,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189942,7 +189942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -189964,11 +189964,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -189982,11 +189982,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -189994,7 +189994,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190018,7 +190018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -190026,7 +190026,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -190066,11 +190066,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190078,7 +190078,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190102,11 +190102,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -190192,11 +190192,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190204,7 +190204,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190250,11 +190250,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190262,7 +190262,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190286,7 +190286,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -190314,11 +190314,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -190328,7 +190328,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190336,7 +190336,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -190366,7 +190366,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190392,11 +190392,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190404,7 +190404,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -190434,7 +190434,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190442,16 +190442,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -190512,7 +190512,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190520,7 +190520,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190570,7 +190570,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190578,7 +190578,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -190612,7 +190612,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190628,7 +190628,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190636,7 +190636,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -190666,7 +190666,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190702,7 +190702,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -190744,7 +190744,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190766,7 +190766,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190792,7 +190792,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190814,7 +190814,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.audio.transcript.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190848,7 +190848,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190882,7 +190882,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call_code.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190912,7 +190912,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190942,7 +190942,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190972,7 +190972,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.code_interpreter_call.interpreting"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -190996,7 +190996,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Unix timestamp (in seconds) of when this Response was created. - - `error: BetaResponseError` + - `error: BetaResponseError or null` An error object returned when the model fails to generate a Response. @@ -191048,7 +191048,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A human-readable description of the error. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details about why the response is incomplete. @@ -191060,7 +191060,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"content_filter"` - - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` + - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` A system (or developer) message inserted into the model's context. @@ -191146,11 +191146,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -191188,7 +191188,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -191223,7 +191223,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -191260,7 +191260,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -191464,7 +191464,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -191472,7 +191472,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -191516,7 +191516,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -191524,11 +191524,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -191579,11 +191579,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -191640,7 +191640,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -191648,7 +191648,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -191695,7 +191695,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -191731,7 +191731,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -191771,7 +191771,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -191840,7 +191840,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -191881,11 +191881,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -191893,15 +191893,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -191909,7 +191909,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -191975,7 +191975,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -192015,7 +192015,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192050,7 +192050,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192058,7 +192058,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -192127,7 +192127,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -192147,7 +192147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -192159,15 +192159,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -192197,23 +192197,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -192229,11 +192229,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192241,7 +192241,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -192265,15 +192265,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -192327,11 +192327,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192371,11 +192371,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192501,11 +192501,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192525,11 +192525,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -192537,7 +192537,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -192549,7 +192549,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -192573,11 +192573,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -192587,7 +192587,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -192599,11 +192599,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -192621,7 +192621,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -192836,11 +192836,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -192857,23 +192857,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -192898,7 +192898,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -192906,7 +192906,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -192971,12 +192971,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -193066,7 +193066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -193124,7 +193124,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193171,7 +193171,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -193286,7 +193286,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193294,7 +193294,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -193308,7 +193308,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -193434,7 +193434,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193510,7 +193510,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193522,15 +193522,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -193548,7 +193548,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193616,7 +193616,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -193628,7 +193628,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -193660,7 +193660,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -193670,19 +193670,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -193696,7 +193696,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193710,11 +193710,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -193722,7 +193722,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -193734,7 +193734,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -193764,11 +193764,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -193778,7 +193778,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -193790,11 +193790,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -193812,7 +193812,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -194027,11 +194027,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -194048,23 +194048,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -194089,7 +194089,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194097,7 +194097,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -194162,12 +194162,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -194257,7 +194257,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -194283,7 +194283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194330,7 +194330,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -194445,7 +194445,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194453,7 +194453,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -194475,7 +194475,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194551,7 +194551,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194563,15 +194563,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -194589,7 +194589,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194657,7 +194657,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -194669,7 +194669,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -194701,7 +194701,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -194711,19 +194711,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -194737,7 +194737,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -194751,11 +194751,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -194794,7 +194794,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -194816,7 +194816,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -194847,11 +194847,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -194867,7 +194867,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -194889,7 +194889,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -194905,7 +194905,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -194913,7 +194913,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -194966,7 +194966,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195000,15 +195000,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -195032,7 +195032,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195058,7 +195058,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195066,7 +195066,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -195088,11 +195088,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -195106,11 +195106,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195118,7 +195118,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195142,7 +195142,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -195150,7 +195150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -195214,11 +195214,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195226,7 +195226,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195250,11 +195250,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -195340,11 +195340,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195352,7 +195352,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195398,11 +195398,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195410,7 +195410,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195434,7 +195434,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -195462,11 +195462,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -195476,7 +195476,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195484,7 +195484,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -195514,7 +195514,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195540,11 +195540,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195552,7 +195552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -195582,7 +195582,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195590,16 +195590,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -195660,7 +195660,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195668,7 +195668,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195718,7 +195718,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195726,7 +195726,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -195760,7 +195760,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195776,7 +195776,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195784,7 +195784,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -195814,7 +195814,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195850,7 +195850,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -195858,7 +195858,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `metadata: map[string]` + - `metadata: map[string] or null` 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 @@ -196128,7 +196128,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196136,11 +196136,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -196197,7 +196197,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196205,7 +196205,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -196292,7 +196292,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196300,7 +196300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -196420,11 +196420,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -196638,7 +196638,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -196678,7 +196678,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196707,11 +196707,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -196741,7 +196741,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196791,15 +196791,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196842,7 +196842,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -196864,7 +196864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -196959,7 +196959,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -197005,7 +197005,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -197039,11 +197039,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -197053,7 +197053,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197065,11 +197065,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -197087,7 +197087,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -197302,11 +197302,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -197323,23 +197323,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -197364,7 +197364,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197372,7 +197372,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -197437,12 +197437,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -197532,7 +197532,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -197558,7 +197558,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197605,7 +197605,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -197720,7 +197720,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197728,7 +197728,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -197750,7 +197750,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197826,7 +197826,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197838,15 +197838,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -197864,7 +197864,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -197932,7 +197932,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -197944,7 +197944,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -197976,7 +197976,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -197986,19 +197986,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -198012,7 +198012,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198076,11 +198076,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -198090,7 +198090,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198102,11 +198102,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -198124,7 +198124,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -198339,11 +198339,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -198360,23 +198360,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -198401,7 +198401,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198409,7 +198409,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -198474,12 +198474,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -198569,7 +198569,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -198595,7 +198595,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198642,7 +198642,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -198757,7 +198757,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198765,7 +198765,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -198787,7 +198787,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198863,7 +198863,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198875,15 +198875,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -198901,7 +198901,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -198969,7 +198969,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -198981,7 +198981,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -199013,7 +199013,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -199023,19 +199023,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -199049,7 +199049,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -199109,7 +199109,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -199131,7 +199131,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199147,7 +199147,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -199155,7 +199155,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -199208,7 +199208,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199242,15 +199242,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -199274,7 +199274,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199300,7 +199300,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199308,7 +199308,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -199332,11 +199332,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -199344,7 +199344,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -199394,7 +199394,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -199430,7 +199430,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -199502,7 +199502,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -199614,7 +199614,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -199672,7 +199672,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -199696,7 +199696,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -199726,7 +199726,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199734,16 +199734,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -199785,11 +199785,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -199799,7 +199799,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199807,7 +199807,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -199837,7 +199837,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199867,7 +199867,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199875,7 +199875,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -199905,7 +199905,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199913,7 +199913,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -199989,7 +199989,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -199997,7 +199997,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -200029,7 +200029,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether to allow the model to run tool calls in parallel. - - `temperature: number` + - `temperature: number or null` What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. @@ -200158,7 +200158,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -200232,11 +200232,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -200246,7 +200246,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -200258,11 +200258,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -200280,7 +200280,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -200495,11 +200495,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -200516,23 +200516,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -200557,7 +200557,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -200565,7 +200565,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -200630,12 +200630,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -200725,7 +200725,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -200751,7 +200751,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -200798,7 +200798,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -200913,7 +200913,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -200921,7 +200921,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -200943,7 +200943,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -201019,7 +201019,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -201031,15 +201031,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -201057,7 +201057,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -201125,7 +201125,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -201137,7 +201137,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -201169,7 +201169,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -201179,19 +201179,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -201205,7 +201205,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -201213,7 +201213,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `top_p: number` + - `top_p: number or null` An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability @@ -201222,17 +201222,17 @@ curl https://api.openai.com/v1/responses/resp_123 \ We generally recommend altering this or `temperature` but not both. - - `background: optional boolean` + - `background: optional boolean or null` Whether to run the model response in the background. [Learn more](/docs/guides/background). - - `completed_at: optional number` + - `completed_at: optional number or null` Unix timestamp (in seconds) of when this Response was completed. Only present when the status is `completed`. - - `conversation: optional object { id }` + - `conversation: optional object { id } or null` The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation. @@ -201240,15 +201240,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the conversation that this response was associated with. - - `max_output_tokens: optional number` + - `max_output_tokens: optional number or null` An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). - - `max_tool_calls: optional number` + - `max_tool_calls: optional number or null` The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. - - `moderation: optional object { input, output }` + - `moderation: optional object { input, output } or null` Moderation results for the response input and output, if moderated completions were requested. @@ -201364,19 +201364,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `output_text: optional string` + - `output_text: optional string or null` SDK-only convenience property that contains the aggregated text output from all `output_text` items in the `output` array, if any are present. Supported in the Python and JavaScript SDKs. - - `previous_response_id: optional string` + - `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. - - `prompt: optional BetaResponsePrompt` + - `prompt: optional BetaResponsePrompt or null` Reference to a prompt template and its variables. [Learn more](/docs/guides/text?api-mode=responses#reusable-prompts). @@ -201385,7 +201385,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique identifier of the prompt template to use. - - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile]` + - `variables: optional map[string or BetaResponseInputText or BetaResponseInputImage or BetaResponseInputFile] or null` Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other @@ -201405,11 +201405,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ A file input to the model. - - `version: optional string` + - `version: optional string or null` Optional version of the prompt template. - - `prompt_cache_key: optional string` + - `prompt_cache_key: optional string or null` Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). @@ -201431,7 +201431,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"30m"` - - `prompt_cache_retention: optional "in_memory" or "24h"` + - `prompt_cache_retention: optional "in_memory" or "24h" or null` Deprecated. Use `prompt_cache_options.ttl` instead. @@ -201450,14 +201450,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"24h"` - - `reasoning: optional object { context, effort, generate_summary, 2 more }` + - `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -201473,7 +201473,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -201497,7 +201497,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -201529,7 +201529,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -201543,12 +201543,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"detailed"` - - `safety_identifier: optional string` + - `safety_identifier: optional string or null` A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). - - `service_tier: optional "auto" or "default" or "flex" or 3 more` + - `service_tier: optional "auto" or "default" or "flex" or 3 more or null` Specifies the processing type used for serving the request. @@ -201649,7 +201649,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -201670,7 +201670,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -201683,14 +201683,14 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `top_logprobs: optional number` + - `top_logprobs: optional number or null` An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. - - `truncation: optional "auto" or "disabled"` + - `truncation: optional "auto" or "disabled" or null` The truncation strategy to use for the model response. @@ -201758,7 +201758,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201818,7 +201818,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201878,7 +201878,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.content_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201904,7 +201904,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.created"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201916,7 +201916,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Emitted when an error occurs. - - `code: string` + - `code: string or null` The error code. @@ -201924,7 +201924,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The error message. - - `param: string` + - `param: string or null` The error parameter. @@ -201938,7 +201938,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"error"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201968,7 +201968,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -201998,7 +201998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202028,7 +202028,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.file_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202062,7 +202062,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202098,7 +202098,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.function_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202124,7 +202124,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202150,7 +202150,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202176,7 +202176,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.incomplete"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202315,7 +202315,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202345,7 +202345,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_item.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202393,7 +202393,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202441,7 +202441,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_part.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202486,7 +202486,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202524,7 +202524,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_summary_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202562,7 +202562,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202600,7 +202600,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.reasoning_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202638,7 +202638,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202676,7 +202676,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.refusal.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202738,7 +202738,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202800,7 +202800,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202830,7 +202830,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202860,7 +202860,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202890,7 +202890,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.web_search_call.searching"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202920,7 +202920,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202950,7 +202950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.generating"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -202980,7 +202980,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203018,7 +203018,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.image_generation_call.partial_image"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203052,7 +203052,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203086,7 +203086,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call_arguments.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203116,7 +203116,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203146,7 +203146,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203176,7 +203176,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_call.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203206,7 +203206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.completed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203236,7 +203236,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.failed"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203266,7 +203266,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.mcp_list_tools.in_progress"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203308,7 +203308,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.output_text.annotation.added"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203334,7 +203334,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.queued"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203368,7 +203368,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.delta"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203402,7 +203402,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"response.custom_tool_call_input.done"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that owns this multi-agent streaming event. @@ -203489,7 +203489,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203552,7 +203552,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203560,11 +203560,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -203615,11 +203615,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -203649,7 +203649,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203675,11 +203675,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -203687,15 +203687,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203703,7 +203703,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -203769,7 +203769,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -203809,7 +203809,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203844,7 +203844,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203852,7 +203852,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -203925,11 +203925,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -203937,7 +203937,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -203961,15 +203961,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -204023,11 +204023,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -204067,11 +204067,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -204197,11 +204197,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -204221,11 +204221,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -204233,7 +204233,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -204245,7 +204245,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -204269,11 +204269,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -204283,7 +204283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -204295,11 +204295,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -204317,7 +204317,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -204532,11 +204532,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -204553,23 +204553,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -204594,7 +204594,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -204602,7 +204602,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -204667,12 +204667,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -204762,7 +204762,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -204788,7 +204788,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -204835,7 +204835,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -204950,7 +204950,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -204958,7 +204958,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -204980,7 +204980,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205056,7 +205056,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205068,15 +205068,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -205094,7 +205094,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205162,7 +205162,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -205174,7 +205174,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -205206,7 +205206,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -205216,19 +205216,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -205242,7 +205242,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205256,11 +205256,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -205268,7 +205268,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -205280,7 +205280,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -205310,11 +205310,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -205324,7 +205324,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205336,11 +205336,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -205358,7 +205358,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -205573,11 +205573,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -205594,23 +205594,23 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -205635,7 +205635,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205643,7 +205643,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -205708,12 +205708,12 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -205803,7 +205803,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -205829,7 +205829,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205876,7 +205876,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -205991,7 +205991,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -205999,7 +205999,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -206021,7 +206021,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -206097,7 +206097,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -206109,15 +206109,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -206135,7 +206135,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -206203,7 +206203,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -206215,7 +206215,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -206247,7 +206247,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -206257,19 +206257,19 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -206283,7 +206283,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -206297,11 +206297,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206340,7 +206340,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206362,7 +206362,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -206393,11 +206393,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206413,7 +206413,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -206435,7 +206435,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206451,7 +206451,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -206459,7 +206459,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -206512,7 +206512,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206546,15 +206546,15 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -206578,7 +206578,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206604,7 +206604,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206612,7 +206612,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -206634,11 +206634,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -206652,11 +206652,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206664,7 +206664,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -206688,7 +206688,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -206696,7 +206696,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -206736,11 +206736,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206748,7 +206748,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -206772,11 +206772,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -206862,11 +206862,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206874,7 +206874,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -206920,11 +206920,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -206932,7 +206932,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -206956,7 +206956,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -206984,11 +206984,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -206998,7 +206998,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207006,7 +207006,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -207036,7 +207036,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207062,11 +207062,11 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207074,7 +207074,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -207104,7 +207104,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207112,16 +207112,16 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -207182,7 +207182,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207190,7 +207190,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -207240,7 +207240,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207248,7 +207248,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -207282,7 +207282,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207298,7 +207298,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207306,7 +207306,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -207336,7 +207336,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207372,7 +207372,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207516,7 +207516,7 @@ curl https://api.openai.com/v1/responses/resp_123 \ - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -207717,11 +207717,11 @@ Returns a list of input items for a given response. - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -207759,7 +207759,7 @@ Returns a list of input items for a given response. The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -207797,7 +207797,7 @@ Returns a list of input items for a given response. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -207995,7 +207995,7 @@ Returns a list of input items for a given response. - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208003,7 +208003,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -208047,7 +208047,7 @@ Returns a list of input items for a given response. - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208055,11 +208055,11 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -208110,11 +208110,11 @@ Returns a list of input items for a given response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -208171,7 +208171,7 @@ Returns a list of input items for a given response. The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -208179,7 +208179,7 @@ Returns a list of input items for a given response. A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -208226,7 +208226,7 @@ Returns a list of input items for a given response. - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -208262,7 +208262,7 @@ Returns a list of input items for a given response. The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -208302,7 +208302,7 @@ Returns a list of input items for a given response. The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -208371,7 +208371,7 @@ Returns a list of input items for a given response. A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208436,15 +208436,15 @@ Returns a list of input items for a given response. The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208512,7 +208512,7 @@ Returns a list of input items for a given response. - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -208552,7 +208552,7 @@ Returns a list of input items for a given response. - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208595,7 +208595,7 @@ Returns a list of input items for a given response. - `"function_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208603,7 +208603,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -208683,7 +208683,7 @@ Returns a list of input items for a given response. - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -208691,7 +208691,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -208811,11 +208811,11 @@ Returns a list of input items for a given response. - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -208983,7 +208983,7 @@ Returns a list of input items for a given response. Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -209029,7 +209029,7 @@ Returns a list of input items for a given response. The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -209063,11 +209063,11 @@ Returns a list of input items for a given response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -209077,7 +209077,7 @@ Returns a list of input items for a given response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -209089,11 +209089,11 @@ Returns a list of input items for a given response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -209111,7 +209111,7 @@ Returns a list of input items for a given response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -209326,11 +209326,11 @@ Returns a list of input items for a given response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -209347,23 +209347,23 @@ Returns a list of input items for a given response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -209388,7 +209388,7 @@ Returns a list of input items for a given response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -209396,7 +209396,7 @@ Returns a list of input items for a given response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -209461,12 +209461,12 @@ Returns a list of input items for a given response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -209556,7 +209556,7 @@ Returns a list of input items for a given response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -209614,7 +209614,7 @@ Returns a list of input items for a given response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -209661,7 +209661,7 @@ Returns a list of input items for a given response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -209776,7 +209776,7 @@ Returns a list of input items for a given response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -209784,7 +209784,7 @@ Returns a list of input items for a given response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -209798,7 +209798,7 @@ Returns a list of input items for a given response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -209924,7 +209924,7 @@ Returns a list of input items for a given response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210000,7 +210000,7 @@ Returns a list of input items for a given response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210012,15 +210012,15 @@ Returns a list of input items for a given response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -210038,7 +210038,7 @@ Returns a list of input items for a given response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210106,7 +210106,7 @@ Returns a list of input items for a given response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -210118,7 +210118,7 @@ Returns a list of input items for a given response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -210150,7 +210150,7 @@ Returns a list of input items for a given response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -210160,19 +210160,19 @@ Returns a list of input items for a given response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -210186,7 +210186,7 @@ Returns a list of input items for a given response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210250,11 +210250,11 @@ Returns a list of input items for a given response. The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -210264,7 +210264,7 @@ Returns a list of input items for a given response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210276,11 +210276,11 @@ Returns a list of input items for a given response. Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -210298,7 +210298,7 @@ Returns a list of input items for a given response. The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -210513,11 +210513,11 @@ Returns a list of input items for a given response. - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -210534,23 +210534,23 @@ Returns a list of input items for a given response. - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -210575,7 +210575,7 @@ Returns a list of input items for a given response. - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210583,7 +210583,7 @@ Returns a list of input items for a given response. - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -210648,12 +210648,12 @@ Returns a list of input items for a given response. Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -210743,7 +210743,7 @@ Returns a list of input items for a given response. An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -210769,7 +210769,7 @@ Returns a list of input items for a given response. - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210816,7 +210816,7 @@ Returns a list of input items for a given response. - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -210931,7 +210931,7 @@ Returns a list of input items for a given response. - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -210939,7 +210939,7 @@ Returns a list of input items for a given response. - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -210961,7 +210961,7 @@ Returns a list of input items for a given response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -211037,7 +211037,7 @@ Returns a list of input items for a given response. - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -211049,15 +211049,15 @@ Returns a list of input items for a given response. Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -211075,7 +211075,7 @@ Returns a list of input items for a given response. - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -211143,7 +211143,7 @@ Returns a list of input items for a given response. - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -211155,7 +211155,7 @@ Returns a list of input items for a given response. - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -211187,7 +211187,7 @@ Returns a list of input items for a given response. - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -211197,19 +211197,19 @@ Returns a list of input items for a given response. - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -211223,7 +211223,7 @@ Returns a list of input items for a given response. - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -211276,7 +211276,7 @@ Returns a list of input items for a given response. - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -211298,7 +211298,7 @@ Returns a list of input items for a given response. - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -211421,7 +211421,7 @@ Returns a list of input items for a given response. The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -211443,7 +211443,7 @@ Returns a list of input items for a given response. - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -211459,7 +211459,7 @@ Returns a list of input items for a given response. The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -211467,7 +211467,7 @@ Returns a list of input items for a given response. The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -211520,7 +211520,7 @@ Returns a list of input items for a given response. - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -211554,15 +211554,15 @@ Returns a list of input items for a given response. - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -211586,7 +211586,7 @@ Returns a list of input items for a given response. - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -211612,7 +211612,7 @@ Returns a list of input items for a given response. - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -211620,7 +211620,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -211644,11 +211644,11 @@ Returns a list of input items for a given response. - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -211656,7 +211656,7 @@ Returns a list of input items for a given response. The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -211706,7 +211706,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -211742,7 +211742,7 @@ Returns a list of input items for a given response. The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -211814,7 +211814,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -211926,7 +211926,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -211984,7 +211984,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -212008,7 +212008,7 @@ Returns a list of input items for a given response. The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -212036,11 +212036,11 @@ Returns a list of input items for a given response. The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -212050,7 +212050,7 @@ Returns a list of input items for a given response. - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212058,7 +212058,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -212088,7 +212088,7 @@ Returns a list of input items for a given response. - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212118,7 +212118,7 @@ Returns a list of input items for a given response. - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212126,7 +212126,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -212156,7 +212156,7 @@ Returns a list of input items for a given response. - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212164,16 +212164,16 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -212226,7 +212226,7 @@ Returns a list of input items for a given response. - `"custom_tool_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212234,7 +212234,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -212314,7 +212314,7 @@ Returns a list of input items for a given response. - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212322,7 +212322,7 @@ Returns a list of input items for a given response. The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -212507,11 +212507,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -212549,7 +212549,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -212587,7 +212587,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212785,7 +212785,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212793,7 +212793,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -212837,7 +212837,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -212845,11 +212845,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -212900,11 +212900,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -212961,7 +212961,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -212969,7 +212969,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -213016,7 +213016,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -213052,7 +213052,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -213092,7 +213092,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -213161,7 +213161,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -213226,15 +213226,15 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -213302,7 +213302,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -213342,7 +213342,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -213385,7 +213385,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -213393,7 +213393,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -213473,7 +213473,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -213481,7 +213481,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -213601,11 +213601,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"original"` - - `file_id: string` + - `file_id: string or null` The identifier of an uploaded file that contains the screenshot. - - `image_url: string` + - `image_url: string or null` The URL of the screenshot image. @@ -213773,7 +213773,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Arguments used for the tool search call. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -213819,7 +213819,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The unique ID of the tool search output item. - - `call_id: string` + - `call_id: string or null` The unique ID of the tool search call generated by the model. @@ -213853,11 +213853,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -213867,7 +213867,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -213879,11 +213879,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -213901,7 +213901,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -214116,11 +214116,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -214137,23 +214137,23 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -214178,7 +214178,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214186,7 +214186,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -214251,12 +214251,12 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -214346,7 +214346,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -214404,7 +214404,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214451,7 +214451,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -214566,7 +214566,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214574,7 +214574,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -214588,7 +214588,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -214714,7 +214714,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214790,7 +214790,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214802,15 +214802,15 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -214828,7 +214828,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -214896,7 +214896,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -214908,7 +214908,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -214940,7 +214940,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -214950,19 +214950,19 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -214976,7 +214976,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215040,11 +215040,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -215054,7 +215054,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215066,11 +215066,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -215088,7 +215088,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -215303,11 +215303,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -215324,23 +215324,23 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -215365,7 +215365,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215373,7 +215373,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -215438,12 +215438,12 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -215533,7 +215533,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -215559,7 +215559,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215606,7 +215606,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -215721,7 +215721,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215729,7 +215729,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -215751,7 +215751,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215827,7 +215827,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215839,15 +215839,15 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -215865,7 +215865,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -215933,7 +215933,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -215945,7 +215945,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -215977,7 +215977,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -215987,19 +215987,19 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -216013,7 +216013,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -216066,7 +216066,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216088,7 +216088,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -216211,7 +216211,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -216233,7 +216233,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216249,7 +216249,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -216257,7 +216257,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -216310,7 +216310,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216344,15 +216344,15 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -216376,7 +216376,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216402,7 +216402,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216410,7 +216410,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -216434,11 +216434,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `commands: array of string` - - `max_output_length: number` + - `max_output_length: number or null` Optional maximum number of characters to return from each command. - - `timeout_ms: number` + - `timeout_ms: number or null` Optional timeout in milliseconds for the commands. @@ -216446,7 +216446,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The unique ID of the shell tool call generated by the model. - - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference` + - `environment: BetaResponseLocalEnvironment or BetaResponseContainerReference or null` Represents the use of a local environment to perform shell actions. @@ -216496,7 +216496,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -216532,7 +216532,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The unique ID of the shell tool call generated by the model. - - `max_output_length: number` + - `max_output_length: number or null` The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output. @@ -216604,7 +216604,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -216716,7 +216716,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -216774,7 +216774,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -216798,7 +216798,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The ID of the entity that created this tool call output. - - `output: optional string` + - `output: optional string or null` Optional textual output returned by the apply patch tool. @@ -216826,11 +216826,11 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -216840,7 +216840,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216848,7 +216848,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -216878,7 +216878,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216908,7 +216908,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp_approval_response"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216916,7 +216916,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -216946,7 +216946,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -216954,16 +216954,16 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -217016,7 +217016,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom_tool_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -217024,7 +217024,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -217104,7 +217104,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ - `"custom_tool_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -217112,7 +217112,7 @@ curl https://api.openai.com/v1/responses/resp_abc123/input_items \ The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -217176,7 +217176,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok ### Body Parameters -- `conversation: optional string or BetaResponseConversationParam` +- `conversation: optional string or BetaResponseConversationParam or null` The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. @@ -217193,7 +217193,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the conversation. -- `input: optional string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more` +- `input: optional string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null` Text, image, or file inputs to the model, used to generate a response @@ -217273,11 +217273,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"input_image"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. @@ -217315,7 +217315,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The content of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. @@ -217350,7 +217350,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"developer"` - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -217387,7 +217387,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"developer"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -217591,7 +217591,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"message"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -217599,7 +217599,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `phase: optional "commentary" or "final_answer"` + - `phase: optional "commentary" or "final_answer" or null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend @@ -217643,7 +217643,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"file_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -217651,11 +217651,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `results: optional array of object { attributes, file_id, filename, 2 more }` + - `results: optional array of object { attributes, file_id, filename, 2 more } or null` The results of the file search tool call. - - `attributes: optional map[string or number or boolean]` + - `attributes: optional map[string or number or boolean] or null` 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 @@ -217706,11 +217706,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. @@ -217767,7 +217767,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The y-coordinate where the click occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while clicking. @@ -217775,7 +217775,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok A double click action. - - `keys: array of string` + - `keys: array of string or null` The keys being held while double-clicking. @@ -217822,7 +217822,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"drag"` - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while dragging the mouse. @@ -217858,7 +217858,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The y-coordinate to move to. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while moving the mouse. @@ -217898,7 +217898,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The y-coordinate where the scroll occurred. - - `keys: optional array of string` + - `keys: optional array of string or null` The keys being held while scrolling. @@ -217967,7 +217967,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok A wait action. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218008,11 +218008,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"computer_call_output"` - - `id: optional string` + - `id: optional string or null` The ID of the computer tool call output. - - `acknowledged_safety_checks: optional array of object { id, code, message }` + - `acknowledged_safety_checks: optional array of object { id, code, message } or null` The safety checks reported by the API that have been acknowledged by the developer. @@ -218020,15 +218020,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The ID of the pending safety check. - - `code: optional string` + - `code: optional string or null` The type of the pending safety check. - - `message: optional string` + - `message: optional string or null` Details about the pending safety check. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218036,7 +218036,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. @@ -218102,7 +218102,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"open_page"` - - `url: optional string` + - `url: optional string or null` The URL opened by the model. @@ -218142,7 +218142,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"web_search_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218177,7 +218177,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the function tool call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218185,7 +218185,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -218254,7 +218254,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"input_text"` - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -218274,7 +218274,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"input_image"` - - `detail: optional "low" or "high" or "auto" or "original"` + - `detail: optional "low" or "high" or "auto" or "original" or null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. @@ -218286,15 +218286,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"original"` - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `image_url: optional string` + - `image_url: optional string or null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -218324,23 +218324,23 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `file_data: optional string` + - `file_data: optional string or null` The base64-encoded data of the file to be sent to the model. - - `file_id: optional string` + - `file_id: optional string or null` The ID of the file to be sent to the model. - - `file_url: optional string` + - `file_url: optional string or null` The URL of the file to be sent to the model. - - `filename: optional string` + - `filename: optional string or null` The name of the file to be sent to the model. - - `prompt_cache_breakpoint: optional object { mode }` + - `prompt_cache_breakpoint: optional object { mode } or null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. @@ -218356,11 +218356,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the function tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218368,7 +218368,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -218392,15 +218392,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program"` - - `name: optional string` + - `name: optional string or null` The name of the tool that produced the output. - - `namespace: optional string` + - `namespace: optional string or null` The namespace of the tool that produced the output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. @@ -218454,11 +218454,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"agent_message"` - - `id: optional string` + - `id: optional string or null` The unique ID of this agent message item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218498,11 +218498,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"multi_agent_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218628,11 +218628,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"multi_agent_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this multi-agent call output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218652,11 +218652,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"tool_search_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search call. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -218664,7 +218664,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -218676,7 +218676,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search call. @@ -218700,11 +218700,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -218714,7 +218714,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -218726,11 +218726,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -218748,7 +218748,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -218963,11 +218963,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -218984,23 +218984,23 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -219025,7 +219025,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219033,7 +219033,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -219098,12 +219098,12 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -219193,7 +219193,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -219251,7 +219251,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219298,7 +219298,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -219413,7 +219413,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219421,7 +219421,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -219435,7 +219435,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the container. @@ -219561,7 +219561,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219637,7 +219637,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219649,15 +219649,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -219675,7 +219675,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219743,7 +219743,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -219755,7 +219755,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -219787,7 +219787,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -219797,19 +219797,19 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -219823,7 +219823,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219837,11 +219837,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"tool_search_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of this tool search output. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -219849,7 +219849,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `call_id: optional string` + - `call_id: optional string or null` The unique ID of the tool search call generated by the model. @@ -219861,7 +219861,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"client"` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the tool search output. @@ -219891,11 +219891,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -219905,7 +219905,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -219917,11 +219917,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -219939,7 +219939,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -220154,11 +220154,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -220175,23 +220175,23 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -220216,7 +220216,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220224,7 +220224,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -220289,12 +220289,12 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -220384,7 +220384,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -220410,7 +220410,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220457,7 +220457,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -220572,7 +220572,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220580,7 +220580,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -220602,7 +220602,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220678,7 +220678,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220690,15 +220690,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -220716,7 +220716,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220784,7 +220784,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -220796,7 +220796,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -220828,7 +220828,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -220838,19 +220838,19 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -220864,7 +220864,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -220878,11 +220878,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"additional_tools"` - - `id: optional string` + - `id: optional string or null` The unique ID of this additional tools item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -220921,7 +220921,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"reasoning"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -220943,7 +220943,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"reasoning_text"` - - `encrypted_content: optional string` + - `encrypted_content: optional string or null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket @@ -220974,11 +220974,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"compaction"` - - `id: optional string` + - `id: optional string or null` The ID of the compaction item. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -220994,7 +220994,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the image generation call. - - `result: string` + - `result: string or null` The generated image encoded in base64. @@ -221016,7 +221016,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"image_generation_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221032,7 +221032,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the code interpreter tool call. - - `code: string` + - `code: string or null` The code to run, or null if not available. @@ -221040,7 +221040,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The ID of the container used to run the code. - - `outputs: array of object { logs, type } or object { type, url }` + - `outputs: array of object { logs, type } or object { type, url } or null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. @@ -221093,7 +221093,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"code_interpreter_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221127,15 +221127,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"exec"` - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Optional timeout in milliseconds for the command. - - `user: optional string` + - `user: optional string or null` Optional user to run the command as. - - `working_directory: optional string` + - `working_directory: optional string or null` Optional working directory to run the command in. @@ -221159,7 +221159,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"local_shell_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221185,7 +221185,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"local_shell_call_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221193,7 +221193,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. @@ -221215,11 +221215,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Ordered shell commands for the execution environment to run. - - `max_output_length: optional number` + - `max_output_length: optional number or null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - - `timeout_ms: optional number` + - `timeout_ms: optional number or null` Maximum wall-clock time in milliseconds to allow the shell commands to run. @@ -221233,11 +221233,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221245,7 +221245,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221269,7 +221269,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program"` - - `environment: optional BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaLocalEnvironment or BetaContainerReference or null` The environment to execute the shell commands in. @@ -221277,7 +221277,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `BetaContainerReference object { container_id, type }` - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. @@ -221341,11 +221341,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the shell tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221353,7 +221353,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221377,11 +221377,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program"` - - `max_output_length: optional number` + - `max_output_length: optional number or null` The maximum number of UTF-8 characters captured for this shell call's combined output. - - `status: optional "in_progress" or "completed" or "incomplete"` + - `status: optional "in_progress" or "completed" or "incomplete" or null` The status of the shell call output. @@ -221467,11 +221467,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"apply_patch_call"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221479,7 +221479,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221525,11 +221525,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"apply_patch_call_output"` - - `id: optional string` + - `id: optional string or null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221537,7 +221537,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221561,7 +221561,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program"` - - `output: optional string` + - `output: optional string or null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). @@ -221589,11 +221589,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The name of the tool. - - `annotations: optional unknown` + - `annotations: optional unknown or null` Additional annotations about the tool. - - `description: optional string` + - `description: optional string or null` The description of the tool. @@ -221603,7 +221603,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp_list_tools"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221611,7 +221611,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `error: optional string` + - `error: optional string or null` Error message if the server could not list tools. @@ -221641,7 +221641,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp_approval_request"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221667,11 +221667,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp_approval_response"` - - `id: optional string` + - `id: optional string or null` The unique ID of the approval response - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221679,7 +221679,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `reason: optional string` + - `reason: optional string or null` Optional reason for the decision. @@ -221709,7 +221709,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp_call"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221717,16 +221717,16 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `approval_request_id: optional string` + - `approval_request_id: optional string or null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - - `error: optional string` + - `error: optional string or null` The error from the tool call, if any. - - `output: optional string` + - `output: optional string or null` The output from the tool call. @@ -221787,7 +221787,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the custom tool call output in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221795,7 +221795,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221845,7 +221845,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The unique ID of the custom tool call in the OpenAI platform. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221853,7 +221853,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `caller: optional object { type } or object { caller_id, type }` + - `caller: optional object { type } or object { caller_id, type } or null` The execution context that produced this tool call. @@ -221887,7 +221887,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"compaction_trigger"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221903,7 +221903,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The ID of the item to reference. - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221911,7 +221911,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. - - `type: optional "item_reference"` + - `type: optional "item_reference" or null` The type of item to reference. Always `item_reference`. @@ -221941,7 +221941,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221977,7 +221977,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"program_output"` - - `agent: optional object { agent_name }` + - `agent: optional object { agent_name } or null` The agent that produced this item. @@ -221985,16 +221985,16 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The canonical name of the agent that produced this item. -- `instructions: optional string` +- `instructions: optional string or null` A system (or developer) message inserted into the model's context. When used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. -- `model: optional string` +- `model: optional string or null` Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](/docs/models) to browse and compare available models. -- `parallel_tool_calls: optional boolean` +- `parallel_tool_calls: optional boolean or null` Whether to allow the model to run tool calls in parallel. @@ -222012,15 +222012,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"pragmatic"` -- `previous_response_id: optional string` +- `previous_response_id: optional string or null` The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. -- `reasoning: optional object { context, effort, generate_summary, 2 more }` +- `reasoning: optional object { context, effort, generate_summary, 2 more } or null` **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). - - `context: optional "auto" or "current_turn" or "all_turns"` + - `context: optional "auto" or "current_turn" or "all_turns" or null` Controls which reasoning items are rendered back to the model on later turns. If omitted or set to `auto`, the model determines the context mode. The @@ -222036,7 +222036,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"all_turns"` - - `effort: optional "none" or "minimal" or "low" or 4 more` + - `effort: optional "none" or "minimal" or "low" or 4 more or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -222060,7 +222060,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"max"` - - `generate_summary: optional "auto" or "concise" or "detailed"` + - `generate_summary: optional "auto" or "concise" or "detailed" or null` **Deprecated:** use `summary` instead. @@ -222092,7 +222092,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"pro"` - - `summary: optional "auto" or "concise" or "detailed"` + - `summary: optional "auto" or "concise" or "detailed" or null` A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. @@ -222106,7 +222106,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"detailed"` -- `text: optional object { format, verbosity }` +- `text: optional object { format, verbosity } or null` Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: @@ -222166,7 +222166,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok A description of what the response format is for, used by the model to determine how to respond in the format. - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -222187,7 +222187,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"json_object"` - - `verbosity: optional "low" or "medium" or "high"` + - `verbosity: optional "low" or "medium" or "high" or null` Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. @@ -222200,7 +222200,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` -- `tool_choice: optional BetaToolChoiceOptions or BetaToolChoiceAllowed or BetaToolChoiceTypes or 6 more` +- `tool_choice: optional BetaToolChoiceOptions or BetaToolChoiceAllowed or BetaToolChoiceTypes or 6 more or null` Controls which tool the model should use, if any. @@ -222322,7 +222322,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp"` - - `name: optional string` + - `name: optional string or null` The name of the tool to call on the server. @@ -222368,7 +222368,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell"` -- `tools: optional array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 more` +- `tools: optional array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 more or null` An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter. @@ -222380,11 +222380,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The name of the function to call. - - `parameters: map[unknown]` + - `parameters: map[unknown] or null` A JSON schema object describing the parameters of the function. - - `strict: boolean` + - `strict: boolean or null` Whether strict parameter validation is enforced for this function tool. @@ -222394,7 +222394,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -222406,11 +222406,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function is deferred and loaded via tool search. - - `description: optional string` + - `description: optional string or null` A description of the function. Used by the model to determine whether or not to call the function. - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON schema object describing the JSON value encoded in string outputs for this function. @@ -222428,7 +222428,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok The IDs of the vector stores to search. - - `filters: optional object { key, type, value } or object { filters, type }` + - `filters: optional object { key, type, value } or object { filters, type } or null` A filter to apply. @@ -222643,11 +222643,11 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"web_search_2025_08_26"` - - `filters: optional object { allowed_domains }` + - `filters: optional object { allowed_domains } or null` Filters for the search. - - `allowed_domains: optional array of string` + - `allowed_domains: optional array of string or null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. @@ -222664,23 +222664,23 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { city, country, region, 2 more }` + - `user_location: optional object { city, country, region, 2 more } or null` The approximate location of the user. - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -222705,7 +222705,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"mcp"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -222713,7 +222713,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `allowed_tools: optional array of string or object { read_only, tool_names }` + - `allowed_tools: optional array of string or object { read_only, tool_names } or null` List of allowed tool names or a filter object. @@ -222778,12 +222778,12 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this MCP tool is deferred and discovered via tool search. - - `headers: optional map[string]` + - `headers: optional map[string] or null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - - `require_approval: optional object { always, never } or "always" or "never"` + - `require_approval: optional object { always, never } or "always" or "never" or null` Specify which of the MCP server's tools require approval. @@ -222873,7 +222873,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok An optional list of uploaded files to make available to your code. - - `memory_limit: optional "1g" or "4g" or "16g" or "64g"` + - `memory_limit: optional "1g" or "4g" or "16g" or "64g" or null` The memory limit for the code interpreter container. @@ -222899,7 +222899,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"code_interpreter"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -222946,7 +222946,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"auto"` - - `input_fidelity: optional "high" or "low"` + - `input_fidelity: optional "high" or "low" or null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`. @@ -223061,7 +223061,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"shell"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -223069,7 +223069,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"programmatic"` - - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference` + - `environment: optional BetaContainerAuto or BetaLocalEnvironment or BetaContainerReference or null` - `BetaContainerAuto object { type, file_ids, memory_limit, 2 more }` @@ -223091,7 +223091,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -223167,7 +223167,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"function"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -223179,15 +223179,15 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok Whether this function should be deferred and discovered via tool search. - - `description: optional string` + - `description: optional string or null` - - `output_schema: optional map[unknown]` + - `output_schema: optional map[unknown] or null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - - `parameters: optional unknown` + - `parameters: optional unknown or null` - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. @@ -223205,7 +223205,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"custom"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -223273,7 +223273,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"tool_search"` - - `description: optional string` + - `description: optional string or null` Description shown to the model for a client-executed tool search tool. @@ -223285,7 +223285,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"client"` - - `parameters: optional unknown` + - `parameters: optional unknown or null` Parameter schema for a client-executed tool search tool. @@ -223317,7 +223317,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"high"` - - `user_location: optional object { type, city, country, 2 more }` + - `user_location: optional object { type, city, country, 2 more } or null` The user's location. @@ -223327,19 +223327,19 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"approximate"` - - `city: optional string` + - `city: optional string or null` Free text input for the city of the user, e.g. `San Francisco`. - - `country: optional string` + - `country: optional string or null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - - `region: optional string` + - `region: optional string or null` Free text input for the region of the user, e.g. `California`. - - `timezone: optional string` + - `timezone: optional string or null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. @@ -223353,7 +223353,7 @@ Returns an object with `object` set to `response.input_tokens` and an `input_tok - `"apply_patch"` - - `allowed_callers: optional array of "direct" or "programmatic"` + - `allowed_callers: optional array of "direct" or "programmatic" or null` The tool invocation context(s). @@ -223530,7 +223530,7 @@ Create a thread. - `"assistant"` - - `attachments: optional array of object { file_id, tools }` + - `attachments: optional array of object { file_id, tools } or null` A list of files attached to the message, and the tools they should be added to. @@ -223558,7 +223558,7 @@ Create a thread. - `"file_search"` - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -223567,7 +223567,7 @@ Create a thread. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -223576,7 +223576,7 @@ Create a thread. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `tool_resources: optional object { code_interpreter, file_search }` +- `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -223634,7 +223634,7 @@ Create a thread. A list of [file](/docs/api-reference/files) 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. - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -223657,7 +223657,7 @@ Create a thread. The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -223672,7 +223672,7 @@ Create a thread. - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -223786,19 +223786,19 @@ Create a thread and run it in one request. The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. -- `instructions: optional string` +- `instructions: optional string or null` Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. -- `max_completion_tokens: optional number` +- `max_completion_tokens: optional number or null` 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. -- `max_prompt_tokens: optional number` +- `max_prompt_tokens: optional number or null` 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. -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -223807,7 +223807,7 @@ Create a thread and run it in one request. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `model: optional string or "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 35 more` +- `model: optional string or "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 35 more or null` The ID of the [Model](/docs/api-reference/models) 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. @@ -223897,7 +223897,7 @@ Create a thread and run it in one request. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. -- `response_format: optional AssistantResponseFormatOption` +- `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -223960,7 +223960,7 @@ Create a thread and run it in one request. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -223974,11 +223974,11 @@ Create a thread and run it in one request. - `"json_schema"` -- `stream: optional boolean` +- `stream: optional boolean or null` If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. -- `temperature: optional number` +- `temperature: optional number or null` 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. @@ -224080,7 +224080,7 @@ Create a thread and run it in one request. - `"assistant"` - - `attachments: optional array of object { file_id, tools }` + - `attachments: optional array of object { file_id, tools } or null` A list of files attached to the message, and the tools they should be added to. @@ -224108,7 +224108,7 @@ Create a thread and run it in one request. - `"file_search"` - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -224117,7 +224117,7 @@ Create a thread and run it in one request. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -224126,7 +224126,7 @@ Create a thread and run it in one request. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. - - `tool_resources: optional object { code_interpreter, file_search }` + - `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -224184,7 +224184,7 @@ Create a thread and run it in one request. A list of [file](/docs/api-reference/files) 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. - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -224193,7 +224193,7 @@ Create a thread and run it in one request. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `tool_choice: optional AssistantToolChoiceOption` +- `tool_choice: optional AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -224231,7 +224231,7 @@ Create a thread and run it in one request. The name of the function to call. -- `tool_resources: optional object { code_interpreter, file_search }` +- `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -224247,7 +224247,7 @@ Create a thread and run it in one request. The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. -- `tools: optional array of CodeInterpreterTool or FileSearchTool or FunctionTool` +- `tools: optional array of CodeInterpreterTool or FileSearchTool or FunctionTool or null` Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. @@ -224307,7 +224307,7 @@ Create a thread and run it in one request. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -224317,13 +224317,13 @@ Create a thread and run it in one request. - `"function"` -- `top_p: optional number` +- `top_p: optional number or null` 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. -- `truncation_strategy: optional object { type, last_messages }` +- `truncation_strategy: optional object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -224335,7 +224335,7 @@ Create a thread and run it in one request. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. @@ -224353,11 +224353,11 @@ Create a thread and run it in one request. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -224365,15 +224365,15 @@ Create a thread and run it in one request. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -224389,7 +224389,7 @@ Create a thread and run it in one request. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -224407,15 +224407,15 @@ Create a thread and run it in one request. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -224438,7 +224438,7 @@ Create a thread and run it in one request. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -224478,7 +224478,7 @@ Create a thread and run it in one request. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -224541,7 +224541,7 @@ Create a thread and run it in one request. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -224555,7 +224555,7 @@ Create a thread and run it in one request. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -224585,7 +224585,7 @@ Create a thread and run it in one request. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -224689,7 +224689,7 @@ Create a thread and run it in one request. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -224699,7 +224699,7 @@ Create a thread and run it in one request. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -224711,11 +224711,11 @@ Create a thread and run it in one request. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -224731,11 +224731,11 @@ Create a thread and run it in one request. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -225114,7 +225114,7 @@ Retrieves a thread. The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -225129,7 +225129,7 @@ Retrieves a thread. - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -225215,7 +225215,7 @@ Modifies a thread. ### Body Parameters -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -225224,7 +225224,7 @@ Modifies a thread. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `tool_resources: optional object { code_interpreter, file_search }` +- `tool_resources: optional object { code_interpreter, file_search } or null` 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. @@ -225254,7 +225254,7 @@ Modifies a thread. The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -225269,7 +225269,7 @@ Modifies a thread. - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -225417,7 +225417,7 @@ curl https://api.openai.com/v1/threads/thread_abc123 \ The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -225515,7 +225515,7 @@ curl https://api.openai.com/v1/threads/thread_abc123 \ The Unix timestamp (in seconds) for when the thread was created. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -225530,7 +225530,7 @@ curl https://api.openai.com/v1/threads/thread_abc123 \ - `"thread"` - - `tool_resources: object { code_interpreter, file_search }` + - `tool_resources: object { code_interpreter, file_search } or null` 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. @@ -225661,7 +225661,7 @@ Create a message. - `"assistant"` -- `attachments: optional array of object { file_id, tools }` +- `attachments: optional array of object { file_id, tools } or null` A list of files attached to the message, and the tools they should be added to. @@ -225689,7 +225689,7 @@ Create a message. - `"file_search"` -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -225708,11 +225708,11 @@ Create a message. The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -225740,7 +225740,7 @@ Create a message. - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -225882,11 +225882,11 @@ Create a message. The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -225904,7 +225904,7 @@ Create a message. - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -225927,7 +225927,7 @@ Create a message. - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -226144,11 +226144,11 @@ Returns a list of messages for a given thread. The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -226176,7 +226176,7 @@ Returns a list of messages for a given thread. - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -226318,11 +226318,11 @@ Returns a list of messages for a given thread. The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -226340,7 +226340,7 @@ Returns a list of messages for a given thread. - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -226363,7 +226363,7 @@ Returns a list of messages for a given thread. - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -226531,11 +226531,11 @@ Retrieve a message. The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -226563,7 +226563,7 @@ Retrieve a message. - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -226705,11 +226705,11 @@ Retrieve a message. The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -226727,7 +226727,7 @@ Retrieve a message. - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -226750,7 +226750,7 @@ Retrieve a message. - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -226866,7 +226866,7 @@ Modifies a message. ### Body Parameters -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -226885,11 +226885,11 @@ Modifies a message. The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -226917,7 +226917,7 @@ Modifies a message. - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -227059,11 +227059,11 @@ Modifies a message. The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -227081,7 +227081,7 @@ Modifies a message. - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -227104,7 +227104,7 @@ Modifies a message. - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -227537,11 +227537,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ The identifier, which can be referenced in API endpoints. - - `assistant_id: string` + - `assistant_id: string or null` If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - - `attachments: array of object { file_id, tools }` + - `attachments: array of object { file_id, tools } or null` A list of files attached to the message, and the tools they were added to. @@ -227569,7 +227569,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - `"file_search"` - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the message was completed. @@ -227711,11 +227711,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ The Unix timestamp (in seconds) for when the message was created. - - `incomplete_at: number` + - `incomplete_at: number or null` The Unix timestamp (in seconds) for when the message was marked as incomplete. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` On an incomplete message, details about why the message is incomplete. @@ -227733,7 +227733,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - `"run_failed"` - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -227756,7 +227756,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ - `"assistant"` - - `run_id: string` + - `run_id: string or null` The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. @@ -228508,11 +228508,11 @@ Cancels a run that is `in_progress`. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -228520,15 +228520,15 @@ Cancels a run that is `in_progress`. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -228544,7 +228544,7 @@ Cancels a run that is `in_progress`. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -228562,15 +228562,15 @@ Cancels a run that is `in_progress`. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -228593,7 +228593,7 @@ Cancels a run that is `in_progress`. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -228633,7 +228633,7 @@ Cancels a run that is `in_progress`. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -228696,7 +228696,7 @@ Cancels a run that is `in_progress`. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -228710,7 +228710,7 @@ Cancels a run that is `in_progress`. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -228740,7 +228740,7 @@ Cancels a run that is `in_progress`. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -228844,7 +228844,7 @@ Cancels a run that is `in_progress`. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -228854,7 +228854,7 @@ Cancels a run that is `in_progress`. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -228866,11 +228866,11 @@ Cancels a run that is `in_progress`. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -228886,11 +228886,11 @@ Cancels a run that is `in_progress`. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -229042,11 +229042,11 @@ Create a run. The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. -- `additional_instructions: optional string` +- `additional_instructions: optional string or null` 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. -- `additional_messages: optional array of object { content, role, attachments, metadata }` +- `additional_messages: optional array of object { content, role, attachments, metadata } or null` Adds additional messages to the thread before creating the run. @@ -229139,7 +229139,7 @@ Create a run. - `"assistant"` - - `attachments: optional array of object { file_id, tools }` + - `attachments: optional array of object { file_id, tools } or null` A list of files attached to the message, and the tools they should be added to. @@ -229167,7 +229167,7 @@ Create a run. - `"file_search"` - - `metadata: optional Metadata` + - `metadata: optional Metadata or null` 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 @@ -229176,19 +229176,19 @@ Create a run. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `instructions: optional string` +- `instructions: optional string or null` Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. -- `max_completion_tokens: optional number` +- `max_completion_tokens: optional number or null` 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. -- `max_prompt_tokens: optional number` +- `max_prompt_tokens: optional number or null` 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. -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -229197,7 +229197,7 @@ Create a run. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. -- `model: optional string or "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 39 more` +- `model: optional string or "gpt-5" or "gpt-5-mini" or "gpt-5-nano" or 39 more or null` The ID of the [Model](/docs/api-reference/models) 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. @@ -229295,7 +229295,7 @@ Create a run. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. -- `reasoning_effort: optional ReasoningEffort` +- `reasoning_effort: optional ReasoningEffort or null` Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. @@ -229319,7 +229319,7 @@ Create a run. - `"max"` -- `response_format: optional AssistantResponseFormatOption` +- `response_format: optional AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -229382,7 +229382,7 @@ Create a run. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -229396,15 +229396,15 @@ Create a run. - `"json_schema"` -- `stream: optional boolean` +- `stream: optional boolean or null` If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. -- `temperature: optional number` +- `temperature: optional number or null` 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. -- `tool_choice: optional AssistantToolChoiceOption` +- `tool_choice: optional AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -229442,7 +229442,7 @@ Create a run. The name of the function to call. -- `tools: optional array of CodeInterpreterTool or FileSearchTool or FunctionTool` +- `tools: optional array of CodeInterpreterTool or FileSearchTool or FunctionTool or null` Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. @@ -229502,7 +229502,7 @@ Create a run. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -229512,13 +229512,13 @@ Create a run. - `"function"` -- `top_p: optional number` +- `top_p: optional number or null` 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. -- `truncation_strategy: optional object { type, last_messages }` +- `truncation_strategy: optional object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -229530,7 +229530,7 @@ Create a run. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. @@ -229548,11 +229548,11 @@ Create a run. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -229560,15 +229560,15 @@ Create a run. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -229584,7 +229584,7 @@ Create a run. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -229602,15 +229602,15 @@ Create a run. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -229633,7 +229633,7 @@ Create a run. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -229673,7 +229673,7 @@ Create a run. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -229736,7 +229736,7 @@ Create a run. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -229750,7 +229750,7 @@ Create a run. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -229780,7 +229780,7 @@ Create a run. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -229884,7 +229884,7 @@ Create a run. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -229894,7 +229894,7 @@ Create a run. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -229906,11 +229906,11 @@ Create a run. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -229926,11 +229926,11 @@ Create a run. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -230255,11 +230255,11 @@ Returns a list of runs belonging to a thread. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -230267,15 +230267,15 @@ Returns a list of runs belonging to a thread. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -230291,7 +230291,7 @@ Returns a list of runs belonging to a thread. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -230309,15 +230309,15 @@ Returns a list of runs belonging to a thread. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -230340,7 +230340,7 @@ Returns a list of runs belonging to a thread. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -230380,7 +230380,7 @@ Returns a list of runs belonging to a thread. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -230443,7 +230443,7 @@ Returns a list of runs belonging to a thread. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -230457,7 +230457,7 @@ Returns a list of runs belonging to a thread. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -230487,7 +230487,7 @@ Returns a list of runs belonging to a thread. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -230591,7 +230591,7 @@ Returns a list of runs belonging to a thread. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -230601,7 +230601,7 @@ Returns a list of runs belonging to a thread. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -230613,11 +230613,11 @@ Returns a list of runs belonging to a thread. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -230633,11 +230633,11 @@ Returns a list of runs belonging to a thread. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -230873,11 +230873,11 @@ Retrieves a run. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -230885,15 +230885,15 @@ Retrieves a run. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -230909,7 +230909,7 @@ Retrieves a run. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -230927,15 +230927,15 @@ Retrieves a run. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -230958,7 +230958,7 @@ Retrieves a run. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -230998,7 +230998,7 @@ Retrieves a run. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -231061,7 +231061,7 @@ Retrieves a run. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -231075,7 +231075,7 @@ Retrieves a run. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -231105,7 +231105,7 @@ Retrieves a run. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -231209,7 +231209,7 @@ Retrieves a run. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -231219,7 +231219,7 @@ Retrieves a run. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -231231,11 +231231,11 @@ Retrieves a run. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -231251,11 +231251,11 @@ Retrieves a run. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -231411,7 +231411,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The ID of the tool call in the `required_action` object within the run object the output is being submitted for. -- `stream: optional boolean` +- `stream: optional boolean or null` If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. @@ -231429,11 +231429,11 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -231441,15 +231441,15 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -231465,7 +231465,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -231483,15 +231483,15 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -231514,7 +231514,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -231554,7 +231554,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -231617,7 +231617,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -231631,7 +231631,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -231661,7 +231661,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -231765,7 +231765,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -231775,7 +231775,7 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -231787,11 +231787,11 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -231807,11 +231807,11 @@ When a run has the `status: "requires_action"` and `required_action.type` is `su Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -232055,7 +232055,7 @@ Modifies a run. ### Body Parameters -- `metadata: optional Metadata` +- `metadata: optional Metadata or null` 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 @@ -232078,11 +232078,11 @@ Modifies a run. The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -232090,15 +232090,15 @@ Modifies a run. The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -232114,7 +232114,7 @@ Modifies a run. The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -232132,15 +232132,15 @@ Modifies a run. A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -232163,7 +232163,7 @@ Modifies a run. Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -232203,7 +232203,7 @@ Modifies a run. - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -232266,7 +232266,7 @@ Modifies a run. The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -232280,7 +232280,7 @@ Modifies a run. - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -232310,7 +232310,7 @@ Modifies a run. The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -232414,7 +232414,7 @@ Modifies a run. Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -232424,7 +232424,7 @@ Modifies a run. - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -232436,11 +232436,11 @@ Modifies a run. - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -232456,11 +232456,11 @@ Modifies a run. Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -232652,11 +232652,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run was completed. @@ -232664,15 +232664,15 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ The Unix timestamp (in seconds) for when the run was created. - - `expires_at: number` + - `expires_at: number or null` The Unix timestamp (in seconds) for when the run will expire. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run failed. - - `incomplete_details: object { reason }` + - `incomplete_details: object { reason } or null` Details on why the run is incomplete. Will be `null` if the run is not incomplete. @@ -232688,7 +232688,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ The instructions that the [assistant](/docs/api-reference/assistants) used for this run. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run. Will be `null` if there are no errors. @@ -232706,15 +232706,15 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ A human-readable description of the error. - - `max_completion_tokens: number` + - `max_completion_tokens: number or null` The maximum number of completion tokens specified to have been used over the course of the run. - - `max_prompt_tokens: number` + - `max_prompt_tokens: number or null` The maximum number of prompt tokens specified to have been used over the course of the run. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -232737,7 +232737,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. - - `required_action: object { submit_tool_outputs, type }` + - `required_action: object { submit_tool_outputs, type } or null` Details on the action required to continue the run. Will be `null` if no action is required. @@ -232777,7 +232777,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - `"submit_tool_outputs"` - - `response_format: AssistantResponseFormatOption` + - `response_format: AssistantResponseFormatOption or null` Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. @@ -232840,7 +232840,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - - `strict: optional boolean` + - `strict: optional boolean or null` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined @@ -232854,7 +232854,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - `"json_schema"` - - `started_at: number` + - `started_at: number or null` The Unix timestamp (in seconds) for when the run was started. @@ -232884,7 +232884,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - - `tool_choice: AssistantToolChoiceOption` + - `tool_choice: AssistantToolChoiceOption or null` Controls which (if any) tool is called by the model. `none` means the model will not call any tools and instead generates a message. @@ -232988,7 +232988,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ Omitting `parameters` defines a function with an empty parameter list. - - `strict: optional boolean` + - `strict: optional boolean or null` 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](/docs/guides/function-calling). @@ -232998,7 +232998,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - `"function"` - - `truncation_strategy: object { type, last_messages }` + - `truncation_strategy: object { type, last_messages } or null` Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run. @@ -233010,11 +233010,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - `"last_messages"` - - `last_messages: optional number` + - `last_messages: optional number or null` The number of most recent messages from the thread when constructing the context for the run. - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` 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.). @@ -233030,11 +233030,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ Total number of tokens used (prompt + completion). - - `temperature: optional number` + - `temperature: optional number or null` The sampling temperature used for this run. If not set, defaults to 1. - - `top_p: optional number` + - `top_p: optional number or null` The nucleus sampling value used for this run. If not set, defaults to 1. @@ -233094,11 +233094,11 @@ Returns a list of run steps belonging to a run. The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run step was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run step completed. @@ -233106,15 +233106,15 @@ Returns a list of run steps belonging to a run. The Unix timestamp (in seconds) for when the run step was created. - - `expired_at: number` + - `expired_at: number or null` The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run step failed. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run step. Will be `null` if there are no errors. @@ -233130,7 +233130,7 @@ Returns a list of run steps belonging to a run. A human-readable description of the error. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -233325,7 +233325,7 @@ Returns a list of run steps belonging to a run. The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -233353,7 +233353,7 @@ Returns a list of run steps belonging to a run. - `"tool_calls"` - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. @@ -233516,11 +233516,11 @@ Retrieves a run step. The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run step was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run step completed. @@ -233528,15 +233528,15 @@ Retrieves a run step. The Unix timestamp (in seconds) for when the run step was created. - - `expired_at: number` + - `expired_at: number or null` The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run step failed. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run step. Will be `null` if there are no errors. @@ -233552,7 +233552,7 @@ Retrieves a run step. A human-readable description of the error. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -233747,7 +233747,7 @@ Retrieves a run step. The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -233775,7 +233775,7 @@ Retrieves a run step. - `"tool_calls"` - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. @@ -234148,7 +234148,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -234188,7 +234188,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: optional string` + - `output: optional string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -234224,11 +234224,11 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - - `cancelled_at: number` + - `cancelled_at: number or null` The Unix timestamp (in seconds) for when the run step was cancelled. - - `completed_at: number` + - `completed_at: number or null` The Unix timestamp (in seconds) for when the run step completed. @@ -234236,15 +234236,15 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The Unix timestamp (in seconds) for when the run step was created. - - `expired_at: number` + - `expired_at: number or null` The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - - `failed_at: number` + - `failed_at: number or null` The Unix timestamp (in seconds) for when the run step failed. - - `last_error: object { code, message }` + - `last_error: object { code, message } or null` The last error associated with this run step. Will be `null` if there are no errors. @@ -234260,7 +234260,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ A human-readable description of the error. - - `metadata: Metadata` + - `metadata: Metadata or null` 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 @@ -234455,7 +234455,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -234483,7 +234483,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ - `"tool_calls"` - - `usage: object { completion_tokens, prompt_tokens, total_tokens }` + - `usage: object { completion_tokens, prompt_tokens, total_tokens } or null` Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. @@ -234661,7 +234661,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: optional string` + - `output: optional string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -234825,7 +234825,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: optional string` + - `output: optional string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. @@ -234973,7 +234973,7 @@ curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_ The name of the function. - - `output: string` + - `output: string or null` The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet.