Get input token counts

CURRENTLY NOT SUPPORTED

Returns input token counts of the request. Returns an object with object set to response.input_tokens and an input_tokens count.

Request

POST

https://ai.api.cloud.yandex.net/v1/responses/input_tokens

Body

application/json
{
  "model": "example",
  "input": "example",
  "previous_response_id": "example",
  "tools": [
    {
      "type": "function",
      "name": "example",
      "description": "example",
      "parameters": {},
      "strict": true,
      "defer_loading": true
    }
  ],
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "reasoning": {
    "effort": "medium"
  },
  "truncation": "auto",
  "instructions": "example",
  "conversation": null,
  "tool_choice": "none",
  "parallel_tool_calls": true
}

Name

Description

conversation

Type: ConversationParam

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.

Default: null

Example: example

input
One of 2 types

  • Type: string

    A text input to the model, equivalent to a text input with the user role.

    Max length: 10485760

    Example: example

  • Type: InputItem[]

    A list of one or many input items to the model, containing different content types.

    Example
    [
  {
    "type": "message",
    "role": "user",
    "status": "in_progress",
    "content": [
      null
    ]
  }
]

Text, image, or file inputs to the model, used to generate a response

Example: example

instructions

Type: string

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.

Example: example

model

Type: string

Model ID used to generate the response. AI Studio offers a wide range of models with different capabilities, performance characteristics, and price points.

Example: example

parallel_tool_calls

Type: boolean

Whether to allow the model to run tool calls in parallel.

previous_response_id

Type: string

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Cannot be used in conjunction with conversation.

Example: example

reasoning

Type: Reasoning

Configuration options for reasoning models.

Example
{
  "effort": "medium"
}

text

Type: ResponseTextParam

Configuration options for a text response from the model. Can be plain text or structured JSON data.

Example
{
  "format": {
    "type": "text"
  },
  "verbosity": "medium"
}

tool_choice

Type: ToolChoiceParam

Controls which tool the model should use, if any.

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Example: none

tools

Type: Tool[]

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.

Example
[
  {
    "type": "function",
    "name": "example",
    "description": "example",
    "parameters": {},
    "strict": true,
    "defer_loading": true
  }
]

truncation

Type: TruncationEnum

The truncation strategy to use for the model response.

  • auto: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation.
  • disabled (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.

Enum: auto, disabled

InputTextContent

A text input to the model.

Name

Description

text

Type: string

The text input to the model.

Example: example

type

Type: string

The type of the input item. Always input_text.

Default: input_text

Const: input_text
Example
{
  "type": "input_text",
  "text": "example"
}

ImageDetail

Type: string

Enum: low, high, auto, original

InputImageContent

An image input to the model.

Name

Description

detail

Type: ImageDetail

The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.

Enum: low, high, auto, original

type

Type: string

The type of the input item. Always input_image.

Default: input_image

Const: input_image

file_id

Type: string

The ID of the file to be sent to the model.

Example: example

image_url

Type: string

The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

Example: example
Example
{
  "type": "input_image",
  "image_url": "example",
  "file_id": "example",
  "detail": "low"
}

FileInputDetail

Type: string

Enum: low, high

InputFileContent

A file input to the model.

Name

Description

type

Type: string

The type of the input item. Always input_file.

Default: input_file

Const: input_file

detail

Type: FileInputDetail

The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.

Enum: low, high

file_data

Type: string

The content of the file to be sent to the model.

Example: example

file_id

Type: string

The ID of the file to be sent to the model.

Example: example

file_url

Type: string

The URL of the file to be sent to the model.

Example: example

filename

Type: string

The name of the file to be sent to the model.

Example: example
Example
{
  "type": "input_file",
  "file_id": "example",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}

InputContent

One of 3 types

  • Input text

    Type: InputTextContent

    A text input to the model.

    Example
    {
  "type": "input_text",
  "text": "example"
}

  • Input image

    Type: InputImageContent

    An image input to the model.

    Example
    {
  "type": "input_image",
  "image_url": "example",
  "file_id": "example",
  "detail": "low"
}

  • Input file

    Type: InputFileContent

    A file input to the model.

    Example
    {
  "type": "input_file",
  "file_id": "example",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}
Example
{
  "type": "input_text",
  "text": "example"
}

InputMessageContentList

A list of one or many input items to the model, containing different content types.

Type: InputContent[]

Example
[
  {
    "type": "input_text",
    "text": "example"
  }
]

InputMessage

A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.

Name

Description

content

Type: InputMessageContentList

A list of one or many input items to the model, containing different content types.

Example
[
  {
    "type": "input_text",
    "text": "example"
  }
]

role

Type: string

The role of the message input. One of user, system, or developer.

Enum: user, system, developer

status

Type: string

The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the message input. Always set to message.

Const: message

Example: example
Example
{
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

FileCitationBody

A citation to a file.

Name

Description

file_id

Type: string

The ID of the file.

Example: example

filename

Type: string

The filename of the file cited.

Example: example

index

Type: integer

The index of the file in the list of files.

type

Type: string

The type of the file citation. Always file_citation.

Default: file_citation

Const: file_citation
Example
{
  "type": "file_citation",
  "file_id": "example",
  "index": 0,
  "filename": "example"
}

UrlCitationBody

A citation for a web resource used to generate a model response.

Name

Description

end_index

Type: integer

The index of the last character of the URL citation in the message.

start_index

Type: integer

The index of the first character of the URL citation in the message.

title

Type: string

The title of the web resource.

Example: example

type

Type: string

The type of the URL citation. Always url_citation.

Default: url_citation

Const: url_citation

url

Type: string

The URL of the web resource.

Example: example
Example
{
  "type": "url_citation",
  "url": "example",
  "start_index": 0,
  "end_index": 0,
  "title": "example"
}

ContainerFileCitationBody

A citation for a container file used to generate a model response.

Name

Description

container_id

Type: string

The ID of the container file.

Example: example

end_index

Type: integer

The index of the last character of the container file citation in the message.

file_id

Type: string

The ID of the file.

Example: example

filename

Type: string

The filename of the container file cited.

Example: example

start_index

Type: integer

The index of the first character of the container file citation in the message.

type

Type: string

The type of the container file citation. Always container_file_citation.

Default: container_file_citation

Const: container_file_citation
Example
{
  "type": "container_file_citation",
  "container_id": "example",
  "file_id": "example",
  "start_index": 0,
  "end_index": 0,
  "filename": "example"
}

FilePath

A path to a file.

Name

Description

file_id

Type: string

The ID of the file.

Example: example

index

Type: integer

The index of the file in the list of files.

type

Type: string

The type of the file path. Always file_path.

Const: file_path

Example: example
Example
{
  "type": "file_path",
  "file_id": "example",
  "index": 0
}

Annotation

An annotation that applies to a span of output text.

One of 4 types

  • File citation

    Type: FileCitationBody

    A citation to a file.

    Example
    {
  "type": "file_citation",
  "file_id": "example",
  "index": 0,
  "filename": "example"
}

  • URL citation

    Type: UrlCitationBody

    A citation for a web resource used to generate a model response.

    Example
    {
  "type": "url_citation",
  "url": "example",
  "start_index": 0,
  "end_index": 0,
  "title": "example"
}

  • Container file citation

    Type: ContainerFileCitationBody

    A citation for a container file used to generate a model response.

    Example
    {
  "type": "container_file_citation",
  "container_id": "example",
  "file_id": "example",
  "start_index": 0,
  "end_index": 0,
  "filename": "example"
}

  • File path

    Type: FilePath

    A path to a file.

    Example
    {
  "type": "file_path",
  "file_id": "example",
  "index": 0
}
Example
{
  "type": "file_citation",
  "file_id": "example",
  "index": 0,
  "filename": "example"
}

TopLogProb

The top log probability of a token.

Name

Description

bytes

Type: integer[]

Example
[
  0
]

logprob

Type: number

token

Type: string

Example: example
Example
{
  "token": "example",
  "logprob": 0.5,
  "bytes": [
    0
  ]
}

LogProb

The log probability of a token.

Name

Description

bytes

Type: integer[]

Example
[
  0
]

logprob

Type: number

token

Type: string

Example: example

top_logprobs

Type: TopLogProb[]

Example
[
  {
    "token": "example",
    "logprob": 0.5,
    "bytes": [
      0
    ]
  }
]
Example
{
  "token": "example",
  "logprob": 0.5,
  "bytes": [
    0
  ],
  "top_logprobs": [
    {
      "token": "example",
      "logprob": 0.5,
      "bytes": [
        0
      ]
    }
  ]
}

OutputTextContent

A text output from the model.

Name

Description

annotations

Type: Annotation[]

The annotations of the text output.

Example
[
  {
    "type": "file_citation",
    "file_id": "example",
    "index": 0,
    "filename": "example"
  }
]

logprobs

Type: LogProb[]

Example
[
  {
    "token": "example",
    "logprob": 0.5,
    "bytes": [
      0
    ],
    "top_logprobs": [
      {
        "token": "example",
        "logprob": 0.5,
        "bytes": [
          0
        ]
      }
    ]
  }
]

text

Type: string

The text output from the model.

Example: example

type

Type: string

The type of the output text. Always output_text.

Default: output_text

Const: output_text
Example
{
  "type": "output_text",
  "text": "example",
  "annotations": [
    {
      "type": "file_citation",
      "file_id": "example",
      "index": 0,
      "filename": "example"
    }
  ],
  "logprobs": [
    {
      "token": "example",
      "logprob": 0.5,
      "bytes": [
        0
      ],
      "top_logprobs": [
        {
          "token": "example",
          "logprob": 0.5,
          "bytes": [
            null
          ]
        }
      ]
    }
  ]
}

RefusalContent

A refusal from the model.

Name

Description

refusal

Type: string

The refusal explanation from the model.

Example: example

type

Type: string

The type of the refusal. Always refusal.

Default: refusal

Const: refusal
Example
{
  "type": "refusal",
  "refusal": "example"
}

OutputMessageContent

One of 2 types

  • Output text

    Type: OutputTextContent

    A text output from the model.

    Example
    {
  "type": "output_text",
  "text": "example",
  "annotations": [
    {
      "type": "file_citation",
      "file_id": "example",
      "index": 0,
      "filename": "example"
    }
  ],
  "logprobs": [
    {
      "token": "example",
      "logprob": 0.5,
      "bytes": [
        0
      ],
      "top_logprobs": [
        {
          "token": "example",
          "logprob": 0.5,
          "bytes": [
            null
          ]
        }
      ]
    }
  ]
}

  • Refusal

    Type: RefusalContent

    A refusal from the model.

    Example
    {
  "type": "refusal",
  "refusal": "example"
}
Example
{
  "type": "output_text",
  "text": "example",
  "annotations": [
    {
      "type": "file_citation",
      "file_id": "example",
      "index": 0,
      "filename": "example"
    }
  ],
  "logprobs": [
    {
      "token": "example",
      "logprob": 0.5,
      "bytes": [
        0
      ],
      "top_logprobs": [
        {}
      ]
    }
  ]
}

MessagePhase

Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). Not used for user messages.

Type: string

Enum: commentary, final_answer

OutputMessage

An output message from the model.

Name

Description

content

Type: OutputMessageContent[]

The content of the output message.

Example
[
  {
    "type": "output_text",
    "text": "example",
    "annotations": [
      {}
    ],
    "logprobs": [
      {
        "token": "example",
        "logprob": 0.5,
        "bytes": [
          null
        ],
        "top_logprobs": [
          null
        ]
      }
    ]
  }
]

id

Type: string

The unique ID of the output message.

Example: example

role

Type: string

The role of the output message. Always assistant.

Const: assistant

Example: example

status

Type: string

The status of the message input. One of in_progress, completed, or incomplete. Populated when input items are returned via API.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the output message. Always message.

Const: message

Example: example

phase

Type: MessagePhase

Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). Not used for user messages.

Enum: commentary, final_answer
Example
{
  "id": "example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "output_text",
      "text": "example",
      "annotations": [
        null
      ],
      "logprobs": [
        {}
      ]
    }
  ],
  "phase": "commentary",
  "status": "in_progress"
}

VectorStoreFileAttributes

Any of 2 types
  • Type: object

    [additional]
    One of 3 types

    • Type: string

      Max length: 512

      Example: example

    • Type: number

    • Type: boolean

    Example: example

    Set of key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

    Max properties: 16

    Example
    {}

  • Type: unknown

    Example: null

Default: null

FileSearchToolCall

The results of a File Search tool call.

Name

Description

id

Type: string

The unique ID of the file search tool call.

Example: example

queries

Type: string[]

The queries used to search for files.

Example
[
  "example"
]

status

Type: string

The status of the file search tool call. One of in_progress, searching, incomplete or failed,

Enum: in_progress, searching, completed, incomplete, failed

type

Type: string

The type of the file search tool call. Always file_search_call.

Const: file_search_call

Example: example

results
Type: object[]

attributes

Type: VectorStoreFileAttributes

Default: null

Example
{}

file_id

Type: string

The unique ID of the file.

Example: example

filename

Type: string

The name of the file.

Example: example

score

Type: number

The relevance score of the file - a value between 0 and 1.

text

Type: string

The text that was retrieved from the file.

Example: example

The results of the file search tool call.

Example
[
  {
    "file_id": "example",
    "text": "example",
    "filename": "example",
    "attributes": null,
    "score": 0.5
  }
]
Example
{
  "id": "example",
  "type": "file_search_call",
  "status": "in_progress",
  "queries": [
    "example"
  ],
  "results": [
    {
      "file_id": "example",
      "text": "example",
      "filename": "example",
      "attributes": null,
      "score": 0.5
    }
  ]
}

WebSearchActionSearch

Action type "search" - Performs a web search query.

Name

Description

query

Type: string

[DEPRECATED] The search query.

Example: example

type

Type: string

The action type.

Const: search

Example: example

queries

Type: string[]

The search queries.

Example
[
  "example"
]

sources
Type: Web search source

type

Type: string

The type of source. Always url.

Const: url

Example: example

url

Type: string

The URL of the source.

Example: example

The sources used in the search.

Example
[
  {
    "type": "url",
    "url": "example"
  }
]
Example
{
  "type": "search",
  "query": "example",
  "queries": [
    "example"
  ],
  "sources": [
    {
      "type": "url",
      "url": "example"
    }
  ]
}

WebSearchActionOpenPage

Action type "open_page" - Opens a specific URL from search results.

Name

Description

type

Type: string

The action type.

Const: open_page

Example: example

url

Type: string<uri>

The URL opened by the model.

Example: https://example.com
Example
{
  "type": "open_page",
  "url": "https://example.com"
}

WebSearchActionFind

Action type "find_in_page": Searches for a pattern within a loaded page.

Name

Description

pattern

Type: string

The pattern or text to search for within the page.

Example: example

type

Type: string

The action type.

Const: find_in_page

Example: example

url

Type: string<uri>

The URL of the page searched for the pattern.

Example: https://example.com
Example
{
  "type": "find_in_page",
  "url": "https://example.com",
  "pattern": "example"
}

WebSearchToolCall

The results of a web search tool call.

Name

Description

action

Type: object

One of 3 types

  • Search action

    Type: WebSearchActionSearch

    Action type "search" - Performs a web search query.

    Example
    {
  "type": "search",
  "query": "example",
  "queries": [
    "example"
  ],
  "sources": [
    {
      "type": "url",
      "url": "example"
    }
  ]
}

  • Open page action

    Type: WebSearchActionOpenPage

    Action type "open_page" - Opens a specific URL from search results.

    Example
    {
  "type": "open_page",
  "url": "https://example.com"
}

  • Find action

    Type: WebSearchActionFind

    Action type "find_in_page": Searches for a pattern within a loaded page.

    Example
    {
  "type": "find_in_page",
  "url": "https://example.com",
  "pattern": "example"
}

An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).

Example
{
  "type": "search",
  "query": "example",
  "queries": [
    "example"
  ],
  "sources": [
    {
      "type": "url",
      "url": "example"
    }
  ]
}

id

Type: string

The unique ID of the web search tool call.

Example: example

status

Type: string

The status of the web search tool call.

Enum: in_progress, searching, completed, failed

type

Type: string

The type of the web search tool call. Always web_search_call.

Const: web_search_call

Example: example
Example
{
  "id": "example",
  "type": "web_search_call",
  "status": "in_progress",
  "action": {
    "type": "search",
    "query": "example",
    "queries": [
      "example"
    ],
    "sources": [
      {
        "type": "url",
        "url": "example"
      }
    ]
  }
}

FunctionToolCall

A tool call to run a function.

Name

Description

arguments

Type: string

A JSON string of the arguments to pass to the function.

Example: example

call_id

Type: string

The unique ID of the function tool call generated by the model.

Example: example

name

Type: string

The name of the function to run.

Example: example

type

Type: string

The type of the function tool call. Always function_call.

Const: function_call

Example: example

id

Type: string

The unique ID of the function tool call.

Example: example

namespace

Type: string

The namespace of the function to run.

Example: example

status

Type: string

The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

Enum: in_progress, completed, incomplete
Example
{
  "id": "example",
  "type": "function_call",
  "call_id": "example",
  "namespace": "example",
  "name": "example",
  "arguments": "example",
  "status": "in_progress"
}

InputTextContentParam

A text input to the model.

Name

Description

text

Type: string

The text input to the model.

Max length: 10485760

Example: example

type

Type: string

The type of the input item. Always input_text.

Default: input_text

Const: input_text
Example
{
  "type": "input_text",
  "text": "example"
}

InputImageContentParamAutoParam

An image input to the model.

Name

Description

type

Type: string

The type of the input item. Always input_image.

Default: input_image

Const: input_image

detail

Type: DetailEnum

The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.

Enum: low, high, auto, original

file_id

Type: string

The ID of the file to be sent to the model.

Example: fvtdeb81rt1d978c5hvb

image_url

Type: string

The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

Max length: 20971520

Example: example
Example
{
  "type": "input_image",
  "image_url": "example",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "detail": "low"
}

InputFileContentParam

A file input to the model.

Name

Description

type

Type: string

The type of the input item. Always input_file.

Default: input_file

Const: input_file

detail

Type: FileDetailEnum

The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.

Enum: low, high

file_data

Type: string

The base64-encoded data of the file to be sent to the model.

Max length: 73400320

Example: example

file_id

Type: string

The ID of the file to be sent to the model.

Example: fvtdeb81rt1d978c5hvb

file_url

Type: string

The URL of the file to be sent to the model.

Example: example

filename

Type: string

The name of the file to be sent to the model.

Example: example
Example
{
  "type": "input_file",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}

FunctionCallItemStatus

Type: string

Enum: in_progress, completed, incomplete

FunctionCallOutputItemParam

The output of a function tool call.

Name

Description

call_id

Type: string

The unique ID of the function tool call generated by the model.

Min length: 1

Max length: 64

Example: example

output
One of 2 types

  • Type: string

    A JSON string of the output of the function tool call.

    Max length: 10485760

    Example: example

  • Type: array
    One of 3 types

    • Input text

      Type: InputTextContentParam

      A text input to the model.

      Example
      {
  "type": "input_text",
  "text": "example"
}

    • Input image

      Type: InputImageContentParamAutoParam

      An image input to the model.

      Example
      {
  "type": "input_image",
  "image_url": "example",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "detail": "low"
}

    • Input file

      Type: InputFileContentParam

      A file input to the model.

      Example
      {
  "type": "input_file",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}

    An array of content outputs (text, image, file) for the function tool call.

    Example
    [
  {
    "type": "input_text",
    "text": "example"
  }
]

Text, image, or file output of the function tool call.

Example: example

type

Type: string

The type of the function tool call output. Always function_call_output.

Default: function_call_output

Const: function_call_output

id

Type: string

The unique ID of the function tool call output. Populated when this item is returned via API.

Example: example

status

Type: FunctionCallItemStatus

The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

Enum: in_progress, completed, incomplete
Example
{
  "id": "example",
  "call_id": "example",
  "type": "function_call_output",
  "output": "example",
  "status": "in_progress"
}

SummaryTextContent

A summary text from the model.

Name

Description

text

Type: string

A summary of the reasoning output from the model so far.

Example: example

type

Type: string

The type of the object. Always summary_text.

Default: summary_text

Const: summary_text
Example
{
  "type": "summary_text",
  "text": "example"
}

ReasoningTextContent

Reasoning text from the model.

Name

Description

text

Type: string

The reasoning text from the model.

Example: example

type

Type: string

The type of the reasoning text. Always reasoning_text.

Default: reasoning_text

Const: reasoning_text
Example
{
  "type": "reasoning_text",
  "text": "example"
}

ReasoningItem

A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

Name

Description

id

Type: string

The unique identifier of the reasoning content.

Example: example

summary

Type: SummaryTextContent[]

Reasoning summary content.

Example
[
  {
    "type": "summary_text",
    "text": "example"
  }
]

type

Type: string

The type of the object. Always reasoning.

Const: reasoning

Example: example

content

Type: ReasoningTextContent[]

Reasoning text content.

Example
[
  {
    "type": "reasoning_text",
    "text": "example"
  }
]

encrypted_content

Type: string

The encrypted content of the reasoning item - populated when a response is
generated with reasoning.encrypted_content in the include parameter.

Example: example

status

Type: string

The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.

Enum: in_progress, completed, incomplete
Example
{
  "type": "reasoning",
  "id": "example",
  "encrypted_content": "example",
  "summary": [
    {
      "type": "summary_text",
      "text": "example"
    }
  ],
  "content": [
    {
      "type": "reasoning_text",
      "text": "example"
    }
  ],
  "status": "in_progress"
}

CompactionSummaryItemParam

A compaction item generated by the v1/responses/compact API.

Name

Description

encrypted_content

Type: string

The encrypted content of the compaction summary.

Max length: 10485760

Example: example

type

Type: string

The type of the item. Always compaction.

Default: compaction

Const: compaction

id

Type: string

The ID of the compaction item.

Example: example
Example
{
  "id": "example",
  "type": "compaction",
  "encrypted_content": "example"
}

CompactionTrigger

Compacts the current context. Must be the final input item.

Name

Description

type

Type: string

The type of the item. Always compaction_trigger.

Default: compaction_trigger

Const: compaction_trigger

id

Type: string

The unique ID of the compaction trigger item.

Example: example
Example
{
  "id": "example",
  "type": "compaction_trigger"
}

ImageGenToolCall

An image generation request made by the model.

Name

Description

id

Type: string

The unique ID of the image generation call.

Example: example

result

Type: string

The generated image encoded in base64.

Example: example

status

Type: string

The status of the image generation call.

Enum: in_progress, completed, generating, failed

type

Type: string

The type of the image generation call. Always image_generation_call.

Const: image_generation_call

Example: example
Example
{
  "type": "image_generation_call",
  "id": "example",
  "status": "in_progress",
  "result": "example"
}

CodeInterpreterOutputLogs

The logs output from the code interpreter.

Name

Description

logs

Type: string

The logs output from the code interpreter.

Example: example

type

Type: string

The type of the output. Always logs.

Default: logs

Const: logs
Example
{
  "type": "logs",
  "logs": "example"
}

CodeInterpreterOutputImage

The image output from the code interpreter.

Name

Description

type

Type: string

The type of the output. Always image.

Default: image

Const: image

url

Type: string

The URL of the image output from the code interpreter.

Example: example
Example
{
  "type": "image",
  "url": "example"
}

CodeInterpreterToolCall

A tool call to run code.

Name

Description

code

Type: string

The code to run, or null if not available.

Example: example

container_id

Type: string

The ID of the container used to run the code.

Example: example

id

Type: string

The unique ID of the code interpreter tool call.

Example: example

outputs
Type: array
One of 2 types

  • Code interpreter output logs

    Type: CodeInterpreterOutputLogs

    The logs output from the code interpreter.

    Example
    {
  "type": "logs",
  "logs": "example"
}

  • Code interpreter output image

    Type: CodeInterpreterOutputImage

    The image output from the code interpreter.

    Example
    {
  "type": "image",
  "url": "example"
}

The outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.

Example
[
  {
    "type": "logs",
    "logs": "example"
  }
]

status

Type: string

The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.

Enum: in_progress, completed, incomplete, interpreting, failed

type

Type: string

The type of the code interpreter tool call. Always code_interpreter_call.

Default: code_interpreter_call

Const: code_interpreter_call
Example
{
  "type": "code_interpreter_call",
  "id": "example",
  "status": "in_progress",
  "container_id": "example",
  "code": "example",
  "outputs": [
    {
      "type": "logs",
      "logs": "example"
    }
  ]
}

FunctionShellAction

Execute a shell command.

Name

Description

commands

Type: string[]

Example
[
  "example"
]

max_output_length
Any of 2 types

  • Type: integer

    Optional maximum number of characters to return from each command.

  • Type: null

    Example: null

Example: 0

timeout_ms
Any of 2 types

  • Type: integer

    Optional timeout in milliseconds for the commands.

  • Type: null

    Example: null

Example: 0
Example
{
  "commands": [
    "example"
  ],
  "timeout_ms": 0,
  "max_output_length": 0
}

ContainerReferenceResource

Represents a container created with /v1/containers.

Name

Description

container_id

Type: string

Example: example

type

Type: string

The environment type. Always container_reference.

Default: container_reference

Const: container_reference
Example
{
  "type": "container_reference",
  "container_id": "example"
}

FunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Name

Description

action

Type: FunctionShellAction

The shell commands and limits that describe how to run the tool call.

Execute a shell command.

Example
{
  "commands": [
    "example"
  ],
  "timeout_ms": 0,
  "max_output_length": 0
}

call_id

Type: string

The unique ID of the shell tool call generated by the model.

Example: example

environment
Any of 2 types

  • Container Reference

    Type: ContainerReferenceResource

    Represents a container created with /v1/containers.

    Example
    {
  "type": "container_reference",
  "container_id": "example"
}

  • Type: null

    Example: null

Example
{
  "type": "container_reference",
  "container_id": "example"
}

id

Type: string

The unique ID of the shell tool call. Populated when this item is returned via API.

Example: example

status

Type: LocalShellCallStatus

The status of the shell call. One of in_progress, completed, or incomplete.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the item. Always shell_call.

Default: shell_call

Const: shell_call

created_by

Type: string

The ID of the entity that created this tool call.

Example: example
Example
{
  "type": "shell_call",
  "id": "example",
  "call_id": "example",
  "action": {
    "commands": [
      "example"
    ],
    "timeout_ms": 0,
    "max_output_length": 0
  },
  "status": "in_progress",
  "environment": {
    "type": "container_reference",
    "container_id": "example"
  },
  "created_by": "example"
}

FunctionShellCallOutputTimeoutOutcome

Indicates that the shell call exceeded its configured time limit.

Name

Description

type

Type: string

The outcome type. Always timeout.

Default: timeout

Const: timeout
Example
{
  "type": "timeout"
}

FunctionShellCallOutputExitOutcome

Indicates that the shell commands finished and returned an exit code.

Name

Description

exit_code

Type: integer

Exit code from the shell process.

type

Type: string

The outcome type. Always exit.

Default: exit

Const: exit
Example
{
  "type": "exit",
  "exit_code": 0
}

FunctionShellCallOutputContent

The content of a shell tool call output that was emitted.

Name

Description

outcome
One of 2 types

Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.

Example
{
  "type": "timeout"
}

stderr

Type: string

The standard error output that was captured.

Example: example

stdout

Type: string

The standard output that was captured.

Example: example

created_by

Type: string

The identifier of the actor that created the item.

Example: example
Example
{
  "stdout": "example",
  "stderr": "example",
  "outcome": {
    "type": "timeout"
  },
  "created_by": "example"
}

FunctionShellCallOutput

The output of a shell tool call that was emitted.

Name

Description

call_id

Type: string

The unique ID of the shell tool call generated by the model.

Example: example

id

Type: string

The unique ID of the shell call output. Populated when this item is returned via API.

Example: example

max_output_length
Any of 2 types

  • Type: integer

    The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.

  • Type: null

    Example: null

Example: 0

output

Type: FunctionShellCallOutputContent[]

An array of shell call output contents

Example
[
  {
    "stdout": "example",
    "stderr": "example",
    "outcome": {
      "type": "timeout"
    },
    "created_by": "example"
  }
]

status

Type: LocalShellCallOutputStatusEnum

The status of the shell call output. One of in_progress, completed, or incomplete.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the shell call output. Always shell_call_output.

Default: shell_call_output

Const: shell_call_output

created_by

Type: string

The identifier of the actor that created the item.

Example: example
Example
{
  "type": "shell_call_output",
  "id": "example",
  "call_id": "example",
  "status": "in_progress",
  "output": [
    {
      "stdout": "example",
      "stderr": "example",
      "outcome": {
        "type": "timeout"
      },
      "created_by": "example"
    }
  ],
  "max_output_length": 0,
  "created_by": "example"
}

MCPListToolsTool

A tool available on an MCP server.

Name

Description

input_schema

Type: object

The JSON schema describing the tool's input.

Example
{}

name

Type: string

The name of the tool.

Example: example

annotations

Type: object

Additional annotations about the tool.

Example
{}

description

Type: string

The description of the tool.

Example: example
Example
{
  "name": "example",
  "description": "example",
  "input_schema": {},
  "annotations": {}
}

MCPListTools

A list of tools available on an MCP server.

Name

Description

id

Type: string

The unique ID of the list.

Example: example

server_label

Type: string

The label of the MCP server.

Example: example

tools

Type: MCPListToolsTool[]

The tools available on the server.

Example
[
  {
    "name": "example",
    "description": "example",
    "input_schema": {},
    "annotations": {}
  }
]

type

Type: string

The type of the item. Always mcp_list_tools.

Const: mcp_list_tools

Example: example

error

Type: string

Error message if the server could not list tools.

Example: example
Example
{
  "type": "mcp_list_tools",
  "id": "example",
  "server_label": "example",
  "tools": [
    {
      "name": "example",
      "description": "example",
      "input_schema": {},
      "annotations": {}
    }
  ],
  "error": "example"
}

MCPApprovalRequest

A request for human approval of a tool invocation.

Name

Description

arguments

Type: string

A JSON string of arguments for the tool.

Example: example

id

Type: string

The unique ID of the approval request.

Example: example

name

Type: string

The name of the tool to run.

Example: example

server_label

Type: string

The label of the MCP server making the request.

Example: example

type

Type: string

The type of the item. Always mcp_approval_request.

Const: mcp_approval_request

Example: example
Example
{
  "type": "mcp_approval_request",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example"
}

MCPApprovalResponse

A response to an MCP approval request.

Name

Description

approval_request_id

Type: string

The ID of the approval request being answered.

Example: example

approve

Type: boolean

Whether the request was approved.

type

Type: string

The type of the item. Always mcp_approval_response.

Const: mcp_approval_response

Example: example

id

Type: string

The unique ID of the approval response

Example: example

reason

Type: string

Optional reason for the decision.

Example: example
Example
{
  "type": "mcp_approval_response",
  "id": "example",
  "approval_request_id": "example",
  "approve": true,
  "reason": "example"
}

MCPToolCallStatus

Type: string

Enum: in_progress, completed, incomplete, calling, failed

MCPToolCall

An invocation of a tool on an MCP server.

Name

Description

arguments

Type: string

A JSON string of the arguments passed to the tool.

Example: example

id

Type: string

The unique ID of the tool call.

Example: example

name

Type: string

The name of the tool that was run.

Example: example

server_label

Type: string

The label of the MCP server running the tool.

Example: example

type

Type: string

The type of the item. Always mcp_call.

Const: mcp_call

Example: example

approval_request_id

Type: string

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.

Example: example

error

Type: string

The error from the tool call, if any.

Example: example

output

Type: string

The output from the tool call.

Example: example

status

Type: MCPToolCallStatus

The status of the tool call. One of in_progress, completed, incomplete, calling, or failed.

Enum: in_progress, completed, incomplete, calling, failed
Example
{
  "type": "mcp_call",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example",
  "output": "example",
  "error": "example",
  "status": "in_progress",
  "approval_request_id": "example"
}

Item

Content item used to generate a response.

Type: object

One of 17 types

  • Input message

    Type: InputMessage

    A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.

    Example
    {
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

  • Output message

    Type: OutputMessage

    An output message from the model.

    Example
    {
  "id": "example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "output_text",
      "text": "example",
      "annotations": [
        null
      ],
      "logprobs": [
        {}
      ]
    }
  ],
  "phase": "commentary",
  "status": "in_progress"
}

  • File search tool call

    Type: FileSearchToolCall

    The results of a File Search tool call.

    Example
    {
  "id": "example",
  "type": "file_search_call",
  "status": "in_progress",
  "queries": [
    "example"
  ],
  "results": [
    {
      "file_id": "example",
      "text": "example",
      "filename": "example",
      "attributes": null,
      "score": 0.5
    }
  ]
}

  • Web search tool call

    Type: WebSearchToolCall

    The results of a web search tool call.

    Example
    {
  "id": "example",
  "type": "web_search_call",
  "status": "in_progress",
  "action": {
    "type": "search",
    "query": "example",
    "queries": [
      "example"
    ],
    "sources": [
      {
        "type": "url",
        "url": "example"
      }
    ]
  }
}

  • Function tool call

    Type: FunctionToolCall

    A tool call to run a function.

    Example
    {
  "id": "example",
  "type": "function_call",
  "call_id": "example",
  "namespace": "example",
  "name": "example",
  "arguments": "example",
  "status": "in_progress"
}

  • Function tool call output

    Type: FunctionCallOutputItemParam

    The output of a function tool call.

    Example
    {
  "id": "example",
  "call_id": "example",
  "type": "function_call_output",
  "output": "example",
  "status": "in_progress"
}

  • Reasoning

    Type: ReasoningItem

    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

    Example
    {
  "type": "reasoning",
  "id": "example",
  "encrypted_content": "example",
  "summary": [
    {
      "type": "summary_text",
      "text": "example"
    }
  ],
  "content": [
    {
      "type": "reasoning_text",
      "text": "example"
    }
  ],
  "status": "in_progress"
}

  • Compaction item

    Type: CompactionSummaryItemParam

    A compaction item generated by the v1/responses/compact API.

    Example
    {
  "id": "example",
  "type": "compaction",
  "encrypted_content": "example"
}

  • Compaction trigger

    Type: CompactionTrigger

    Compacts the current context. Must be the final input item.

    Example
    {
  "id": "example",
  "type": "compaction_trigger"
}

  • Image generation call

    Type: ImageGenToolCall

    An image generation request made by the model.

    Example
    {
  "type": "image_generation_call",
  "id": "example",
  "status": "in_progress",
  "result": "example"
}

  • Code interpreter tool call

    Type: CodeInterpreterToolCall

    A tool call to run code.

    Example
    {
  "type": "code_interpreter_call",
  "id": "example",
  "status": "in_progress",
  "container_id": "example",
  "code": "example",
  "outputs": [
    {
      "type": "logs",
      "logs": "example"
    }
  ]
}

  • Shell tool call

    Type: FunctionShellCall

    A tool call that executes one or more shell commands in a managed environment.

    Example
    {
  "type": "shell_call",
  "id": "example",
  "call_id": "example",
  "action": {
    "commands": [
      "example"
    ],
    "timeout_ms": 0,
    "max_output_length": 0
  },
  "status": "in_progress",
  "environment": {
    "type": "container_reference",
    "container_id": "example"
  },
  "created_by": "example"
}

  • Shell call output

    Type: FunctionShellCallOutput

    The output of a shell tool call that was emitted.

    Example
    {
  "type": "shell_call_output",
  "id": "example",
  "call_id": "example",
  "status": "in_progress",
  "output": [
    {
      "stdout": "example",
      "stderr": "example",
      "outcome": {
        "type": "timeout"
      },
      "created_by": "example"
    }
  ],
  "max_output_length": 0,
  "created_by": "example"
}

  • MCP list tools

    Type: MCPListTools

    A list of tools available on an MCP server.

    Example
    {
  "type": "mcp_list_tools",
  "id": "example",
  "server_label": "example",
  "tools": [
    {
      "name": "example",
      "description": "example",
      "input_schema": {},
      "annotations": {}
    }
  ],
  "error": "example"
}

  • MCP approval request

    Type: MCPApprovalRequest

    A request for human approval of a tool invocation.

    Example
    {
  "type": "mcp_approval_request",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example"
}

  • MCP approval response

    Type: MCPApprovalResponse

    A response to an MCP approval request.

    Example
    {
  "type": "mcp_approval_response",
  "id": "example",
  "approval_request_id": "example",
  "approve": true,
  "reason": "example"
}

  • MCP tool call

    Type: MCPToolCall

    An invocation of a tool on an MCP server.

    Example
    {
  "type": "mcp_call",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example",
  "output": "example",
  "error": "example",
  "status": "in_progress",
  "approval_request_id": "example"
}
Example
{
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

ItemReferenceParam

An internal identifier for an item to reference.

Name

Description

id

Type: string

The ID of the item to reference.

Example: example

type

Type: string

The type of item to reference. Always item_reference.

Default: item_reference

Const: item_reference
Example
{
  "type": "item_reference",
  "id": "example"
}

InputItem

One of 2 types

  • Item

    Type: Item

    An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

    Content item used to generate a response.

    Example
    {
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

  • Item reference

    Type: ItemReferenceParam

    An internal identifier for an item to reference.

    Example
    {
  "type": "item_reference",
  "id": "example"
}
Example
{
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {}
  ]
}

FunctionTool

Defines a function in your own code the model can choose to call. Learn more about function calling.

Name

Description

name

Type: string

The name of the function to call.

Example: example

parameters
Type: object

[additional]

Type: unknown

Example: null

A JSON schema object describing the parameters of the function.

Example
{}

strict

Type: boolean

Whether to enforce strict parameter validation. Default true.

type

Type: string

The type of the function tool. Always function.

Default: function

Const: function

defer_loading

Type: boolean

Whether this function is deferred and loaded via tool search.

description

Type: string

A description of the function. Used by the model to determine whether or not to call the function.

Example: example
Example
{
  "type": "function",
  "name": "example",
  "description": "example",
  "parameters": {},
  "strict": true,
  "defer_loading": true
}

RankerVersionType

Type: string

Enum: auto, default-2024-11-15

HybridSearchOptions

Name

Description

embedding_weight

Type: number

The weight of the embedding in the reciprocal ranking fusion.

text_weight

Type: number

The weight of the text in the reciprocal ranking fusion.
Example
{
  "embedding_weight": 0.5,
  "text_weight": 0.5
}

RankingOptions

Name

Description

hybrid_search

Type: HybridSearchOptions

Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.

Example
{
  "embedding_weight": 0.5,
  "text_weight": 0.5
}

ranker

Type: RankerVersionType

The ranker to use for the file search.

Enum: auto, default-2024-11-15

score_threshold

Type: number

The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.
Example
{
  "ranker": "auto",
  "score_threshold": 0.5,
  "hybrid_search": {
    "embedding_weight": 0.5,
    "text_weight": 0.5
  }
}

ComparisonFilter

A filter used to compare a specified attribute key to a given value using a defined comparison operation.

Name

Description

key

Type: string

The key to compare against the value.

Example: example

type

Type: string

Specifies the comparison operator:

  • eq: equals - ne: not equal - gt: greater than - gte: greater than or equal - lt: less than - lte: less than or equal - in: in - nin: not in

Default: eq

Enum: eq, ne, gt, gte, lt, lte, in, nin

value
One of 4 types

  • Type: string

    Example: example

  • Type: number

  • Type: boolean

  • Type: array
    One of 2 types

    • Type: string

      Example: example

    • Type: number

    Example
    [
  "example"
]

The value to compare against the attribute key; supports string, number, or boolean types.

Example: example
Example
{
  "type": "eq",
  "key": "example",
  "value": "example"
}

CompoundFilter

Combine multiple filters using and or or.

Name

Description

filters
Type: array
One of 2 types

  • Comparison Filter

    Type: ComparisonFilter

    A filter used to compare a specified attribute key to a given value using a defined comparison operation.

    Example
    {
  "type": "eq",
  "key": "example",
  "value": "example"
}

  • Type: unknown

    Example: null

Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.

Example
[
  {
    "type": "eq",
    "key": "example",
    "value": "example"
  }
]

type

Type: string

Type of operation: and or or.

Enum: and, or
Example
{
  "type": "and",
  "filters": [
    {
      "type": "eq",
      "key": "example",
      "value": "example"
    }
  ]
}

Filters

Any of 2 types

  • Comparison Filter

    Type: ComparisonFilter

    A filter used to compare a specified attribute key to a given value using a defined comparison operation.

    Example
    {
  "type": "eq",
  "key": "example",
  "value": "example"
}

  • Compound Filter

    Type: CompoundFilter

    Combine multiple filters using and or or.

    Example
    {
  "type": "and",
  "filters": [
    {
      "type": "eq",
      "key": "example",
      "value": "example"
    }
  ]
}
Example
{
  "type": "eq",
  "key": "example",
  "value": "example"
}

FileSearchTool

A tool that searches for relevant content from uploaded files. Learn more about the File Search tool.

Name

Description

type

Type: string

The type of the file search tool. Always file_search.

Default: file_search

Const: file_search

vector_store_ids

Type: string[]

The IDs of the vector stores to search.

Example
[
  "example"
]

filters

Type: Filters

A filter to apply.

Example
{
  "type": "eq",
  "key": "example",
  "value": "example"
}

max_num_results

Type: integer

The maximum number of results to return. This number should be between 1 and 50 inclusive.

ranking_options

Type: RankingOptions

Ranking options for search.

Example
{
  "ranker": "auto",
  "score_threshold": 0.5,
  "hybrid_search": {
    "embedding_weight": 0.5,
    "text_weight": 0.5
  }
}
Example
{
  "type": "file_search",
  "vector_store_ids": [
    "example"
  ],
  "max_num_results": 0,
  "ranking_options": {
    "ranker": "auto",
    "score_threshold": 0.5,
    "hybrid_search": {
      "embedding_weight": 0.5,
      "text_weight": 0.5
    }
  },
  "filters": {
    "type": "eq",
    "key": "example",
    "value": "example"
  }
}

WebSearchApproximateLocation

The approximate location of the user.

Name

Description

city

Type: string

Free text input for the city of the user, e.g. San Francisco.

Example: example

country

Type: string

The two-letter ISO country code of the user, e.g. US.

Example: example

region

Type: string

Free text input for the region of the user, e.g. California.

Example: example

timezone

Type: string

The IANA timezone of the user, e.g. America/Los_Angeles.

Example: example

type

Type: string

The type of location approximation. Always approximate.

Default: approximate

Const: approximate
Example
{
  "type": "approximate",
  "country": "example",
  "region": "example",
  "city": "example",
  "timezone": "example"
}

WebSearchTool

Search the Internet for sources related to the prompt. Learn more about the web search tool.

Name

Description

type

Type: string

The type of the web search tool. One of web_search or web_search_2025_08_26.

Default: web_search

Enum: web_search, web_search_2025_08_26

filters
Type: object

allowed_domains

Type: string[]

Allowed domains for the search. If not provided, all domains are allowed.
Subdomains of the provided domains are allowed as well.

Default: []

Example
[
  "example"
]

Filters for the search.

Example
{
  "allowed_domains": []
}

search_context_size

Type: string

High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.

Default: medium

Enum: low, medium, high

user_location

Type: WebSearchApproximateLocation

The approximate location of the user.

Example
{
  "type": "approximate",
  "country": "example",
  "region": "example",
  "city": "example",
  "timezone": "example"
}
Example
{
  "type": "web_search",
  "filters": {
    "allowed_domains": []
  },
  "user_location": {
    "type": "approximate",
    "country": "example",
    "region": "example",
    "city": "example",
    "timezone": "example"
  },
  "search_context_size": "medium"
}

MCPToolFilter

A filter object to specify which tools are allowed.

Name

Description

read_only

Type: boolean

Indicates whether or not a tool modifies data or is read-only. If an

MCP server is annotated with readOnlyHint,
it will match this filter.

tool_names

Type: string[]

List of allowed tool names.

Example
[
  "example"
]
Example
{
  "tool_names": [
    "example"
  ],
  "read_only": true
}

MCPTool

Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

Name

Description

server_label

Type: string

A label for this MCP server, used to identify it in tool calls.

Example: example

type

Type: string

The type of the MCP tool. Always mcp.

Const: mcp

Example: example

allowed_tools
One of 2 types

  • MCP allowed tools

    Type: string[]

    A string array of allowed tool names

    Example
    [
  "example"
]

  • MCP tool filter

    Type: MCPToolFilter

    A filter object to specify which tools are allowed.

    Example
    {
  "tool_names": [
    "example"
  ],
  "read_only": true
}

List of allowed tool names or a filter object.

Example
[
  "example"
]

authorization

Type: string

An OAuth access token that can be used with a remote MCP server,
either with a custom MCP server URL or a service connector. Your
application must handle the OAuth authorization flow and provide the token here.

Example: example

connector_id

Type: string

Identifier for service connectors. One of server_url or connector_id must be provided.

Enum: connector_dropbox, connector_gmail, connector_googlecalendar, connector_googledrive, connector_microsoftteams, connector_outlookcalendar, connector_outlookemail, connector_sharepoint

defer_loading

Type: boolean

Whether this MCP tool is deferred and discovered via tool search.

headers
Type: object

[additional]

Type: string

Example: example

Optional HTTP headers to send to the MCP server. Use for
authentication or other purposes.

Example
{}

require_approval
One of: MCP tool approval filter or MCP tool approval setting

  • Type: MCP tool approval filter

    always

    MCP tool filter

    Type: MCPToolFilter

    A filter object to specify which tools are allowed.

    Example
    {
  "tool_names": [
    "example"
  ],
  "read_only": true
}

    never

    MCP tool filter

    Type: MCPToolFilter

    A filter object to specify which tools are allowed.

    Example
    {
  "tool_names": [
    "example"
  ],
  "read_only": true
}

    Specify which of the MCP server's tools require approval.
    Can be always, never, or a filter object associated with tools
    that require approval.

    Example
    {
  "always": {
    "tool_names": [
      "example"
    ],
    "read_only": true
  },
  "never": null
}

  • MCP tool approval setting

    Type: string

    Specify a single approval policy for all tools. One of always or
    never. When set to always, all tools will require approval. When set to never, all tools will not require approval.

    Enum: always, never

Specify which of the MCP server's tools require approval.

Default: always

server_description

Type: string

Optional description of the MCP server, used to provide more context.

Example: example

server_url

Type: string

The URL for the MCP server. One of server_url or connector_id
must be provided.

Example: example
Example
{
  "type": "mcp",
  "server_label": "example",
  "server_url": "example",
  "connector_id": "connector_dropbox",
  "authorization": "example",
  "server_description": "example",
  "headers": {},
  "allowed_tools": [
    "example"
  ],
  "require_approval": "always",
  "defer_loading": true
}

ContainerMemoryLimit

Type: string

Enum: 1g, 4g, 16g, 64g

ContainerNetworkPolicyDisabledParam

Name

Description

type

Type: string

Disable outbound network access. Always disabled.

Default: disabled

Const: disabled
Example
{
  "type": "disabled"
}

ContainerNetworkPolicyDomainSecretParam

Name

Description

domain

Type: string

The domain associated with the secret.

Min length: 1

Example: example

name

Type: string

The name of the secret to inject for the domain.

Min length: 1

Example: example

value

Type: string

The secret value to inject for the domain.

Min length: 1

Max length: 10485760

Example: example
Example
{
  "domain": "example",
  "name": "example",
  "value": "example"
}

ContainerNetworkPolicyAllowlistParam

Name

Description

allowed_domains

Type: string[]

A list of allowed domains when type is allowlist.

Min items: 1

Example
[
  "example"
]

type

Type: string

Allow outbound network access only to specified domains. Always allowlist.

Default: allowlist

Const: allowlist

domain_secrets

Type: ContainerNetworkPolicyDomainSecretParam[]

Optional domain-scoped secrets for allowlisted domains.

Min items: 1

Example
[
  {
    "domain": "example",
    "name": "example",
    "value": "example"
  }
]
Example
{
  "type": "allowlist",
  "allowed_domains": [
    "example"
  ],
  "domain_secrets": [
    {
      "domain": "example",
      "name": "example",
      "value": "example"
    }
  ]
}

AutoCodeInterpreterToolParam

Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

Name

Description

type

Type: string

Always auto.

Default: auto

Const: auto

file_ids

Type: string[]

An optional list of uploaded files to make available to your code.

Max items: 50

Example
[
  "example"
]

memory_limit

Type: ContainerMemoryLimit

The memory limit for the code interpreter container.

Enum: 1g, 4g, 16g, 64g

network_policy
One of 2 types

Network access policy for the container.

Example
{
  "type": "disabled"
}
Example
{
  "type": "auto",
  "file_ids": [
    "example"
  ],
  "memory_limit": "1g",
  "network_policy": {
    "type": "disabled"
  }
}

CodeInterpreterTool

A tool that runs Python code to help generate a response to a prompt.

Name

Description

container
One of 2 types

  • Type: string

    The container ID.

    Example: example

  • CodeInterpreterToolAuto

    Type: AutoCodeInterpreterToolParam

    Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

    Example
    {
  "type": "auto",
  "file_ids": [
    "example"
  ],
  "memory_limit": "1g",
  "network_policy": {
    "type": "disabled"
  }
}

The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional memory_limit setting.

Example: example

type

Type: string

The type of the code interpreter tool. Always code_interpreter.

Const: code_interpreter

Example: example
Example
{
  "type": "code_interpreter",
  "container": "example"
}

SkillReference

References a skill created with the /v1/skills endpoint.

Name

Description

skill_id

Type: string

The ID of the referenced skill.

Example: example

type

Type: string

The skill attachment type. Always skill_reference.

Default: skill_reference

Const: skill_reference

version

Type: string

Optional skill version. Use a positive integer or latest. Omit to use the default version.

Pattern: ^(?:latest&#124;[1-9][0-9]*)$

Example: example
Example
{
  "type": "skill_reference",
  "skill_id": "example",
  "version": "example"
}

ShellContainerAuto

Automatically creates a container for this request.

Name

Description

type

Type: string

The environment type. Always container_auto.

Default: container_auto

Const: container_auto

file_ids

Type: string[]

Uploaded files to make available in the container.

Example
[
  "example"
]

skills

Type: SkillReference[]

Skills to make available in the container.

Example
[
  {
    "type": "skill_reference",
    "skill_id": "example",
    "version": "example"
  }
]
Example
{
  "type": "container_auto",
  "file_ids": [
    "example"
  ],
  "skills": [
    {
      "type": "skill_reference",
      "skill_id": "example",
      "version": "example"
    }
  ]
}

ShellEnvironment

One of 2 types

  • Automatic shell container

    Type: ShellContainerAuto

    Automatically creates a container for this request.

    Example
    {
  "type": "container_auto",
  "file_ids": [
    "example"
  ],
  "skills": [
    {
      "type": "skill_reference",
      "skill_id": "example",
      "version": "example"
    }
  ]
}

  • Container Reference

    Type: ContainerReferenceResource

    Represents a container created with /v1/containers.

    Example
    {
  "type": "container_reference",
  "container_id": "example"
}
Example
{
  "type": "container_auto",
  "file_ids": [
    "example"
  ],
  "skills": [
    {
      "type": "skill_reference",
      "skill_id": "example",
      "version": "example"
    }
  ]
}

FunctionShellTool

A tool that allows the model to execute shell commands in a managed container.

Name

Description

environment

Type: ShellEnvironment

Example
{
  "type": "container_auto",
  "file_ids": [
    "example"
  ],
  "skills": [
    {
      "type": "skill_reference",
      "skill_id": "example",
      "version": "example"
    }
  ]
}

type

Type: string

The type of the shell tool. Always shell.

Default: shell

Const: shell
Example
{
  "type": "shell",
  "environment": {
    "type": "container_auto",
    "file_ids": [
      "example"
    ],
    "skills": [
      {
        "type": "skill_reference",
        "skill_id": "example",
        "version": "example"
      }
    ]
  }
}

InputFidelity

Control how much effort the model will exert to match the style and features, especially facial features, of input images.
Supports high and low. Defaults to low.

Type: string

Enum: high, low

ImageGenActionEnum

Type: string

Enum: generate, edit, auto

ImageGenTool

A tool that generates images using the image generation models.

Name

Description

type

Type: string

The type of the image generation tool. Always image_generation.

Const: image_generation

Example: example

action

Type: ImageGenActionEnum

Whether to generate a new image or edit an existing image. Default: auto.

Enum: generate, edit, auto

background

Type: string

CURRENTLY NOT SUPPORTED

Background type for the generated image. One of transparent, opaque, or auto. Default: auto.

Default: auto

Enum: transparent, opaque, auto

input_fidelity

Type: InputFidelity

Control how much effort the model will exert to match the style and features, especially facial features, of input images.
Supports high and low. Defaults to low.

Enum: high, low

input_image_mask
Type: object

file_id

Type: string

File ID for the mask image.

Example: example

image_url

Type: string

Base64-encoded mask image.

Example: example

CURRENTLY NOT SUPPORTED

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

Example
{
  "image_url": "example",
  "file_id": "example"
}

model
Any of 2 types

  • Type: string

    Example: example

  • Type: string

    The image generation model to use.

    Default: aliceai-image-art-3.0

    Const: aliceai-image-art-3.0

Example: example

moderation

Type: string

CURRENTLY NOT SUPPORTED

Moderation level for the generated image.

Default: auto

Enum: auto, low

output_compression

Type: integer

Compression level for the output image.

Default: 100

Min value: 0

Max value: 100

output_format

Type: string

The output format of the generated image. One of png, webp, or jpeg.

Default: png

Enum: png, webp, jpeg

partial_images

Type: integer

Number of partial images to generate in streaming mode, from 0 (default value) to 3.

Default: 0

Min value: 0

Max value: 3

quality

Type: string

The quality of the generated image. One of low, medium, high, or auto.

Default: auto

Enum: low, medium, high, auto

size

Type: string

The size of the generated image. One of 1024x1024, 1024x1536, 1536x1024, or auto.

Default: auto

Enum: 1024x1024, 1024x1536, 1536x1024, auto
Example
{
  "type": "image_generation",
  "model": "example",
  "quality": "auto",
  "size": "auto",
  "output_format": "png",
  "output_compression": 100,
  "moderation": "auto",
  "background": "auto",
  "input_fidelity": "high",
  "input_image_mask": {
    "image_url": "example",
    "file_id": "example"
  },
  "partial_images": 0,
  "action": "generate"
}

Tool

A tool that can be used to generate a response.

One of 7 types

  • Function

    Type: FunctionTool

    Defines a function in your own code the model can choose to call. Learn more about function calling.

    Example
    {
  "type": "function",
  "name": "example",
  "description": "example",
  "parameters": {},
  "strict": true,
  "defer_loading": true
}

  • File search

    Type: FileSearchTool

    A tool that searches for relevant content from uploaded files. Learn more about the File Search tool.

    Example
    {
  "type": "file_search",
  "vector_store_ids": [
    "example"
  ],
  "max_num_results": 0,
  "ranking_options": {
    "ranker": "auto",
    "score_threshold": 0.5,
    "hybrid_search": {
      "embedding_weight": 0.5,
      "text_weight": 0.5
    }
  },
  "filters": {
    "type": "eq",
    "key": "example",
    "value": "example"
  }
}

  • Web search

    Type: WebSearchTool

    Search the Internet for sources related to the prompt. Learn more about the web search tool.

    Example
    {
  "type": "web_search",
  "filters": {
    "allowed_domains": []
  },
  "user_location": {
    "type": "approximate",
    "country": "example",
    "region": "example",
    "city": "example",
    "timezone": "example"
  },
  "search_context_size": "medium"
}

  • MCP tool

    Type: MCPTool

    Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.

    Example
    {
  "type": "mcp",
  "server_label": "example",
  "server_url": "example",
  "connector_id": "connector_dropbox",
  "authorization": "example",
  "server_description": "example",
  "headers": {},
  "allowed_tools": [
    "example"
  ],
  "require_approval": "always",
  "defer_loading": true
}

  • Code interpreter

    Type: CodeInterpreterTool

    A tool that runs Python code to help generate a response to a prompt.

    Example
    {
  "type": "code_interpreter",
  "container": "example"
}

  • Shell

    Type: FunctionShellTool

    A tool that allows the model to execute shell commands in a managed container.

    Example
    {
  "type": "shell",
  "environment": {
    "type": "container_auto",
    "file_ids": [
      "example"
    ],
    "skills": [
      {
        "type": "skill_reference",
        "skill_id": "example",
        "version": "example"
      }
    ]
  }
}

  • Image generation tool

    Type: ImageGenTool

    A tool that generates images using the image generation models.

    Example
    {
  "type": "image_generation",
  "model": "example",
  "quality": "auto",
  "size": "auto",
  "output_format": "png",
  "output_compression": 100,
  "moderation": "auto",
  "background": "auto",
  "input_fidelity": "high",
  "input_image_mask": {
    "image_url": "example",
    "file_id": "example"
  },
  "partial_images": 0,
  "action": "generate"
}
Example
{
  "type": "function",
  "name": "example",
  "description": "example",
  "parameters": {},
  "strict": true,
  "defer_loading": true
}

ResponseFormatText

Default response format. Used to generate text responses.

Name

Description

type

Type: string

The type of response format being defined. Always text.

Const: text

Example: example
Example
{
  "type": "text"
}

ResponseFormatJsonSchemaSchema

The schema for the response format, described as a JSON Schema object.

Learn how to build JSON schemas here.

Name

Description
Example
{}

TextResponseFormatJsonSchema

JSON Schema response format. Used to generate structured JSON responses.

Learn more about Structured Outputs.

Name

Description

name

Type: string

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

Example: example

schema

Type: ResponseFormatJsonSchemaSchema

The schema for the response format, described as a JSON Schema object.

Learn how to build JSON schemas here.

Example
{}

type

Type: string

The type of response format being defined. Always json_schema.

Const: json_schema

Example: example

description

Type: string

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

Example: example

strict

Type: boolean

Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs.

Default: false
Example
{
  "type": "json_schema",
  "description": "example",
  "name": "example",
  "schema": {},
  "strict": false
}

ResponseFormatJsonObject

JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

Name

Description

type

Type: string

The type of response format being defined. Always json_object.

Const: json_object

Example: example
Example
{
  "type": "json_object"
}

TextResponseFormatConfiguration

An object specifying the format that the model must output.

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

The default format is { "type": "text" } with no additional options.

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

One of 3 types

  • Text

    Type: ResponseFormatText

    Default response format. Used to generate text responses.

    Example
    {
  "type": "text"
}

  • JSON schema

    Type: TextResponseFormatJsonSchema

    JSON Schema response format. Used to generate structured JSON responses.

    Learn more about Structured Outputs.

    Example
    {
  "type": "json_schema",
  "description": "example",
  "name": "example",
  "schema": {},
  "strict": false
}

  • JSON object

    Type: ResponseFormatJsonObject

    JSON object response format. An older method of generating JSON responses.
    Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

    Example
    {
  "type": "json_object"
}
Example
{
  "type": "text"
}

Verbosity

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.

Type: string

Default: medium

Enum: low, medium, high

ResponseTextParam

Configuration options for a text response from the model. Can be plain text or structured JSON data.

Name

Description

format

Type: TextResponseFormatConfiguration

An object specifying the format that the model must output.

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

The default format is { "type": "text" } with no additional options.

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Example
{
  "type": "text"
}

verbosity

Type: Verbosity

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses.
Currently supported values are low, medium, and high.

Default: medium

Enum: low, medium, high
Example
{
  "format": {
    "type": "text"
  },
  "verbosity": "medium"
}

ReasoningEffort

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

Type: string

Default: medium

Enum: none, minimal, low, medium, high, xhigh

Reasoning

Configuration options for reasoning models.

Name

Description

effort

Type: ReasoningEffort

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

Default: medium

Enum: none, minimal, low, medium, high, xhigh
Example
{
  "effort": "medium"
}

TruncationEnum

Type: string

Enum: auto, disabled

ConversationParam-2

The conversation that this response belongs to.

Name

Description

id

Type: string

The unique ID of the conversation.

Example: example
Example
{
  "id": "example"
}

ConversationParam

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.

One of 2 types

  • Conversation ID

    Type: string

    The unique ID of the conversation.

    Example: example

  • Conversation object

    Type: ConversationParam-2

    The conversation that this response belongs to.

    Example
    {
  "id": "example"
}

Default: null

ToolChoiceOptions

Controls which (if any) tool is called by the model.

  • none means the model will not call any tool and instead generates a message.
  • auto means the model can pick between generating a message or calling one or more tools.
  • required means the model must call one or more tools.

Type: string

Enum: none, auto, required

ToolChoiceAllowed

Constrains the tools available to the model to a pre-defined set.

Name

Description

mode

Type: string

Constrains the tools available to the model to a pre-defined set.

  • auto allows the model to pick from among the allowed tools and
    generate a message.
  • required requires the model to call one or more of the allowed tools.

Enum: auto, required

tools
Type: object[]

A list of tool definitions that the model should be allowed to call.

For the Responses API, the list of tool definitions might look like:

[
  { "type": "function", "name": "get_weather" },
  { "type": "mcp", "server_label": "deepwiki" },
  { "type": "image_generation" }
]
Example
[
  {}
]

type

Type: string

Allowed tool configuration type. Always allowed_tools.

Const: allowed_tools

Example: example
Example
{
  "type": "allowed_tools",
  "mode": "auto",
  "tools": [
    {}
  ]
}

ToolChoiceTypes

Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.

Name

Description

type

Type: string

The type of hosted tool the model should use. Learn more about built-in tools.
Allowed values are: - file_search - web_search - code_interpreter - image_generation

Enum: file_search, web_search, code_interpreter, image_generation
Example
{
  "type": "file_search"
}

ToolChoiceFunction

Use this option to force the model to call a specific function.

Name

Description

name

Type: string

The name of the function to call.

Example: example

type

Type: string

For function calling, the type is always function.

Const: function

Example: example
Example
{
  "type": "function",
  "name": "example"
}

ToolChoiceMCP

Use this option to force the model to call a specific tool on a remote MCP server.

Name

Description

server_label

Type: string

The label of the MCP server to use.

Example: example

type

Type: string

For MCP tools, the type is always mcp.

Const: mcp

Example: example

name

Type: string

The name of the tool to call on the server.

Example: example
Example
{
  "type": "mcp",
  "server_label": "example",
  "name": "example"
}

ToolChoiceCustom

Use this option to force the model to call a specific custom tool.

Name

Description

name

Type: string

The name of the custom tool to call.

Example: example

type

Type: string

For custom tool calling, the type is always custom.

Const: custom

Example: example
Example
{
  "type": "custom",
  "name": "example"
}

SpecificApplyPatchParam

Forces the model to call the apply_patch tool when executing a tool call.

Name

Description

type

Type: string

The tool to call. Always apply_patch.

Default: apply_patch

Const: apply_patch
Example
{
  "type": "apply_patch"
}

SpecificFunctionShellParam

Forces the model to call the shell tool when a tool call is required.

Name

Description

type

Type: string

The tool to call. Always shell.

Default: shell

Const: shell
Example
{
  "type": "shell"
}

ToolChoiceParam

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

One of 8 types

  • Tool choice mode

    Type: ToolChoiceOptions

    Controls which (if any) tool is called by the model.

    • none means the model will not call any tool and instead generates a message.
    • auto means the model can pick between generating a message or calling one or more tools.
    • required means the model must call one or more tools.

    Enum: none, auto, required

  • Allowed tools

    Type: ToolChoiceAllowed

    Constrains the tools available to the model to a pre-defined set.

    Example
    {
  "type": "allowed_tools",
  "mode": "auto",
  "tools": [
    {}
  ]
}

  • Hosted tool

    Type: ToolChoiceTypes

    Indicates that the model should use a built-in tool to generate a response.
    Learn more about built-in tools.

    Example
    {
  "type": "file_search"
}

  • Function tool

    Type: ToolChoiceFunction

    Use this option to force the model to call a specific function.

    Example
    {
  "type": "function",
  "name": "example"
}

  • MCP tool

    Type: ToolChoiceMCP

    Use this option to force the model to call a specific tool on a remote MCP server.

    Example
    {
  "type": "mcp",
  "server_label": "example",
  "name": "example"
}

  • Custom tool

    Type: ToolChoiceCustom

    Use this option to force the model to call a specific custom tool.

    Example
    {
  "type": "custom",
  "name": "example"
}

  • Specific apply patch tool choice

    Type: SpecificApplyPatchParam

    Forces the model to call the apply_patch tool when executing a tool call.

    Example
    {
  "type": "apply_patch"
}

  • Specific shell tool choice

    Type: SpecificFunctionShellParam

    Forces the model to call the shell tool when a tool call is required.

    Example
    {
  "type": "shell"
}

Example: none

Responses

200 OK

Success

Body

application/json
{
  "object": "response.input_tokens",
  "input_tokens": 123
}

Name

Description

input_tokens

Type: integer

object

Type: string

Default: response.input_tokens

Const: response.input_tokens

InputImageContentParamAutoParam

An image input to the model.

Name

Description

type

Type: string

The type of the input item. Always input_image.

Default: input_image

Const: input_image

detail

Type: DetailEnum

The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.

Enum: low, high, auto, original

file_id

Type: string

The ID of the file to be sent to the model.

Example: fvtdeb81rt1d978c5hvb

image_url

Type: string

The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL.

Max length: 20971520

Example: example
Example
{
  "type": "input_image",
  "image_url": "example",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "detail": "low"
}

InputFileContentParam

A file input to the model.

Name

Description

type

Type: string

The type of the input item. Always input_file.

Default: input_file

Const: input_file

detail

Type: FileDetailEnum

The detail level of the file to be sent to the model. Use low for the default rendering behavior, or high to render the file at higher quality. Defaults to low.

Enum: low, high

file_data

Type: string

The base64-encoded data of the file to be sent to the model.

Max length: 73400320

Example: example

file_id

Type: string

The ID of the file to be sent to the model.

Example: fvtdeb81rt1d978c5hvb

file_url

Type: string

The URL of the file to be sent to the model.

Example: example

filename

Type: string

The name of the file to be sent to the model.

Example: example
Example
{
  "type": "input_file",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}

FunctionCallOutputItemParam

The output of a function tool call.

Name

Description

call_id

Type: string

The unique ID of the function tool call generated by the model.

Min length: 1

Max length: 64

Example: example

output
One of 2 types

  • Type: string

    A JSON string of the output of the function tool call.

    Max length: 10485760

    Example: example

  • Type: array
    One of 3 types

    • Input text

      Type: InputTextContentParam

      A text input to the model.

      Example
      {
  "type": "input_text",
  "text": "example"
}

    • Input image

      Type: InputImageContentParamAutoParam

      An image input to the model.

      Example
      {
  "type": "input_image",
  "image_url": "example",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "detail": "low"
}

    • Input file

      Type: InputFileContentParam

      A file input to the model.

      Example
      {
  "type": "input_file",
  "file_id": "fvtdeb81rt1d978c5hvb",
  "filename": "example",
  "file_data": "example",
  "file_url": "example",
  "detail": "low"
}

    An array of content outputs (text, image, file) for the function tool call.

    Example
    [
  {
    "type": "input_text",
    "text": "example"
  }
]

Text, image, or file output of the function tool call.

Example: example

type

Type: string

The type of the function tool call output. Always function_call_output.

Default: function_call_output

Const: function_call_output

id

Type: string

The unique ID of the function tool call output. Populated when this item is returned via API.

Example: example

status

Type: FunctionCallItemStatus

The status of the item. One of in_progress, completed, or incomplete. Populated when items are returned via API.

Enum: in_progress, completed, incomplete
Example
{
  "id": "example",
  "call_id": "example",
  "type": "function_call_output",
  "output": "example",
  "status": "in_progress"
}

FunctionShellCall

A tool call that executes one or more shell commands in a managed environment.

Name

Description

action

Type: FunctionShellAction

The shell commands and limits that describe how to run the tool call.

Execute a shell command.

Example
{
  "commands": [
    "example"
  ],
  "timeout_ms": 0,
  "max_output_length": 0
}

call_id

Type: string

The unique ID of the shell tool call generated by the model.

Example: example

environment
Any of 2 types

  • Container Reference

    Type: ContainerReferenceResource

    Represents a container created with /v1/containers.

    Example
    {
  "type": "container_reference",
  "container_id": "example"
}

  • Type: null

    Example: null

Example
{
  "type": "container_reference",
  "container_id": "example"
}

id

Type: string

The unique ID of the shell tool call. Populated when this item is returned via API.

Example: example

status

Type: LocalShellCallStatus

The status of the shell call. One of in_progress, completed, or incomplete.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the item. Always shell_call.

Default: shell_call

Const: shell_call

created_by

Type: string

The ID of the entity that created this tool call.

Example: example
Example
{
  "type": "shell_call",
  "id": "example",
  "call_id": "example",
  "action": {
    "commands": [
      "example"
    ],
    "timeout_ms": 0,
    "max_output_length": 0
  },
  "status": "in_progress",
  "environment": {
    "type": "container_reference",
    "container_id": "example"
  },
  "created_by": "example"
}

FunctionShellCallOutput

The output of a shell tool call that was emitted.

Name

Description

call_id

Type: string

The unique ID of the shell tool call generated by the model.

Example: example

id

Type: string

The unique ID of the shell call output. Populated when this item is returned via API.

Example: example

max_output_length
Any of 2 types

  • Type: integer

    The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.

  • Type: null

    Example: null

Example: 0

output

Type: FunctionShellCallOutputContent[]

An array of shell call output contents

Example
[
  {
    "stdout": "example",
    "stderr": "example",
    "outcome": {
      "type": "timeout"
    },
    "created_by": "example"
  }
]

status

Type: LocalShellCallOutputStatusEnum

The status of the shell call output. One of in_progress, completed, or incomplete.

Enum: in_progress, completed, incomplete

type

Type: string

The type of the shell call output. Always shell_call_output.

Default: shell_call_output

Const: shell_call_output

created_by

Type: string

The identifier of the actor that created the item.

Example: example
Example
{
  "type": "shell_call_output",
  "id": "example",
  "call_id": "example",
  "status": "in_progress",
  "output": [
    {
      "stdout": "example",
      "stderr": "example",
      "outcome": {
        "type": "timeout"
      },
      "created_by": "example"
    }
  ],
  "max_output_length": 0,
  "created_by": "example"
}

Item

Content item used to generate a response.

Type: object

One of 17 types

  • Input message

    Type: InputMessage

    A message input to the model with a role indicating instruction following hierarchy. Instructions given with the developer or system role take precedence over instructions given with the user role.

    Example
    {
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

  • Output message

    Type: OutputMessage

    An output message from the model.

    Example
    {
  "id": "example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "output_text",
      "text": "example",
      "annotations": [
        null
      ],
      "logprobs": [
        {}
      ]
    }
  ],
  "phase": "commentary",
  "status": "in_progress"
}

  • File search tool call

    Type: FileSearchToolCall

    The results of a File Search tool call.

    Example
    {
  "id": "example",
  "type": "file_search_call",
  "status": "in_progress",
  "queries": [
    "example"
  ],
  "results": [
    {
      "file_id": "example",
      "text": "example",
      "filename": "example",
      "attributes": null,
      "score": 0.5
    }
  ]
}

  • Web search tool call

    Type: WebSearchToolCall

    The results of a web search tool call.

    Example
    {
  "id": "example",
  "type": "web_search_call",
  "status": "in_progress",
  "action": {
    "type": "search",
    "query": "example",
    "queries": [
      "example"
    ],
    "sources": [
      {
        "type": "url",
        "url": "example"
      }
    ]
  }
}

  • Function tool call

    Type: FunctionToolCall

    A tool call to run a function.

    Example
    {
  "id": "example",
  "type": "function_call",
  "call_id": "example",
  "namespace": "example",
  "name": "example",
  "arguments": "example",
  "status": "in_progress"
}

  • Function tool call output

    Type: FunctionCallOutputItemParam

    The output of a function tool call.

    Example
    {
  "id": "example",
  "call_id": "example",
  "type": "function_call_output",
  "output": "example",
  "status": "in_progress"
}

  • Reasoning

    Type: ReasoningItem

    A description of the chain of thought used by a reasoning model while generating a response. Be sure to include these items in your input to the Responses API for subsequent turns of a conversation if you are manually managing context.

    Example
    {
  "type": "reasoning",
  "id": "example",
  "encrypted_content": "example",
  "summary": [
    {
      "type": "summary_text",
      "text": "example"
    }
  ],
  "content": [
    {
      "type": "reasoning_text",
      "text": "example"
    }
  ],
  "status": "in_progress"
}

  • Compaction item

    Type: CompactionSummaryItemParam

    A compaction item generated by the v1/responses/compact API.

    Example
    {
  "id": "example",
  "type": "compaction",
  "encrypted_content": "example"
}

  • Compaction trigger

    Type: CompactionTrigger

    Compacts the current context. Must be the final input item.

    Example
    {
  "id": "example",
  "type": "compaction_trigger"
}

  • Image generation call

    Type: ImageGenToolCall

    An image generation request made by the model.

    Example
    {
  "type": "image_generation_call",
  "id": "example",
  "status": "in_progress",
  "result": "example"
}

  • Code interpreter tool call

    Type: CodeInterpreterToolCall

    A tool call to run code.

    Example
    {
  "type": "code_interpreter_call",
  "id": "example",
  "status": "in_progress",
  "container_id": "example",
  "code": "example",
  "outputs": [
    {
      "type": "logs",
      "logs": "example"
    }
  ]
}

  • Shell tool call

    Type: FunctionShellCall

    A tool call that executes one or more shell commands in a managed environment.

    Example
    {
  "type": "shell_call",
  "id": "example",
  "call_id": "example",
  "action": {
    "commands": [
      "example"
    ],
    "timeout_ms": 0,
    "max_output_length": 0
  },
  "status": "in_progress",
  "environment": {
    "type": "container_reference",
    "container_id": "example"
  },
  "created_by": "example"
}

  • Shell call output

    Type: FunctionShellCallOutput

    The output of a shell tool call that was emitted.

    Example
    {
  "type": "shell_call_output",
  "id": "example",
  "call_id": "example",
  "status": "in_progress",
  "output": [
    {
      "stdout": "example",
      "stderr": "example",
      "outcome": {
        "type": "timeout"
      },
      "created_by": "example"
    }
  ],
  "max_output_length": 0,
  "created_by": "example"
}

  • MCP list tools

    Type: MCPListTools

    A list of tools available on an MCP server.

    Example
    {
  "type": "mcp_list_tools",
  "id": "example",
  "server_label": "example",
  "tools": [
    {
      "name": "example",
      "description": "example",
      "input_schema": {},
      "annotations": {}
    }
  ],
  "error": "example"
}

  • MCP approval request

    Type: MCPApprovalRequest

    A request for human approval of a tool invocation.

    Example
    {
  "type": "mcp_approval_request",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example"
}

  • MCP approval response

    Type: MCPApprovalResponse

    A response to an MCP approval request.

    Example
    {
  "type": "mcp_approval_response",
  "id": "example",
  "approval_request_id": "example",
  "approve": true,
  "reason": "example"
}

  • MCP tool call

    Type: MCPToolCall

    An invocation of a tool on an MCP server.

    Example
    {
  "type": "mcp_call",
  "id": "example",
  "server_label": "example",
  "name": "example",
  "arguments": "example",
  "output": "example",
  "error": "example",
  "status": "in_progress",
  "approval_request_id": "example"
}
Example
{
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

InputItem

One of 2 types

  • Item

    Type: Item

    An item representing part of the context for the response to be generated by the model. Can contain text, images, and audio inputs, as well as previous assistant responses and tool call outputs.

    Content item used to generate a response.

    Example
    {
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {
      "type": "input_text",
      "text": "example"
    }
  ]
}

  • Item reference

    Type: ItemReferenceParam

    An internal identifier for an item to reference.

    Example
    {
  "type": "item_reference",
  "id": "example"
}
Example
{
  "type": "message",
  "role": "user",
  "status": "in_progress",
  "content": [
    {}
  ]
}
Предыдущая
List input items
Следующая
Compact a conversation