WebSocket events

Send client events and receive server events over a persistent Responses API WebSocket connection. Learn more about WebSocket mode.

Client events

Events sent by the client over a Responses API WebSocket connection.

response.create

Client event for creating a response over a persistent WebSocket connection. This payload uses the same top-level fields as POST /v1/responses, plus WebSocket-only envelope metadata.

Notes:

stream is implicit over WebSocket and should not be sent.
background is not supported over WebSocket.
stream_id is WebSocket-only and is not part of POST /v1/responses.

type: "response.create"

The type of the client event. Always response.create.

access_programs: optional object { cyber }

Domain-specific access programs to use for this request.

cyber: optional "standard" or "daybreak_blue" or "daybreak_red"

The Cyber access program to use for this request. Supported values are standard, daybreak_blue, and daybreak_red. If omitted, the API resolves the program from the model's Cyber tier and your organization and project access, subject to model-specific eligibility restrictions. By default, models without a Cyber tier use Standard. Blue-tier models use Daybreak Blue when authorized; otherwise they fall back to Standard unless the model requires Daybreak access. Red-tier models use Daybreak Red and require authorization. Requests that require unavailable Daybreak access return 403. An implicit Standard fallback is represented by null in the response's access_programs field, rather than an explicit Standard selection.

One of the following:

"standard"

"daybreak_blue"

"daybreak_red"

background: optional boolean or null

Whether to run the model response in the background. Learn more.

context_management: optional array of object { type, compact_threshold } or null

Context management configuration for this request.

type: string

The context management entry type. Currently only 'compaction' is supported.

compact_threshold: optional number or null

Token threshold at which compaction should be triggered for this entry.

minimum1000

conversation: optional string or ResponseConversationParam { id } or null

The conversation that this response belongs to. Items from this conversation are prepended to input_items for this response request. Input items and output items from this response are automatically added to this conversation after this response completes.

One of the following:

ConversationID = string

The unique ID of the conversation.

ResponseConversationParam object { id }

The conversation that this response belongs to.

id: string

The unique ID of the conversation.

include: optional array of ResponseIncludable or null

Specify additional output data to include in the model response. Currently supported values are:

web_search_call.action.sources: Include the sources of the web search tool call.
code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
computer_call_output.output.image_url: Include image urls from the computer call output.
file_search_call.results: Include the search results of the file search tool call.
message.input_image.image_url: Include image urls from the input message.
message.output_text.logprobs: Include logprobs with assistant messages.
reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).

One of the following:

"file_search_call.results"

"web_search_call.results"

"web_search_call.action.sources"

"message.input_image.image_url"

"computer_call_output.output.image_url"

"code_interpreter_call.outputs"

"reasoning.encrypted_content"

"message.output_text.logprobs"

input: optional string or array of EasyInputMessage { content, role, phase, type } or object { content, role, status, type } or ResponseOutputMessage { id, content, role, 3 more } or 30 more

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

Learn more:

One of the following:

TextInput = string

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

InputItemList = array of EasyInputMessage { content, role, phase, type } or object { content, role, status, type } or ResponseOutputMessage { id, content, role, 3 more } or 30 more

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

One of the following:

EasyInputMessage object { content, role, phase, type }

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. Messages with the assistant role are presumed to have been generated by the model in previous interactions.

content: string or ResponseInputMessageContentList { , , }

Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.

One of the following:

TextInput = string

A text input to the model.

ResponseInputMessageContentList = array of ResponseInputContent

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

One of the following:

ResponseInputText object { text, type, prompt_cache_breakpoint }

A text input to the model.

text: string

The text input to the model.

type: "input_text"

The type of the input item. Always input_text.

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputImage object { detail, type, file_id, 2 more }

An image input to the model. Learn about image inputs.

detail: ImageDetail

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

type: "input_image"

The type of the input item. Always input_image.

file_id: optional string or null

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

image_url: optional string or null

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

formaturi

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputFile object { type, detail, file_data, 4 more }

A file input to the model.

type: "input_file"

The type of the input item. Always input_file.

detail: optional "auto" or "low" or "high"

The detail level of the file to be sent to the model. Use auto to let the system select the detail level; for GPT-5.6 and later models, auto uses high-quality rendering, which may increase input token usage. Use low for lower-cost rendering, or high to render the file at higher quality. Defaults to auto.

One of the following:

"auto"

"low"

"high"

file_data: optional string

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

file_id: optional string or null

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

file_url: optional string

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

formaturi

filename: optional string

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

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

role: "user" or "assistant" or "system" or "developer"

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

One of the following:

"user"

"assistant"

"system"

"developer"

phase: optional "commentary" or "final_answer" or null

Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.

One of the following:

"commentary"

"final_answer"

type: optional "message"

The type of the message input. Always message.

Message object { content, role, status, type }

content: ResponseInputMessageContentList { , , }

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

role: "user" or "system" or "developer"

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

One of the following:

"user"

"system"

"developer"

status: optional "in_progress" or "completed" or "incomplete"

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

One of the following:

"in_progress"

"completed"

"incomplete"

type: optional "message"

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

ResponseOutputMessage object { id, content, role, 3 more }

An output message from the model.

id: string

The unique ID of the output message.

content: array of ResponseOutputText { annotations, logprobs, text, type } or ResponseOutputRefusal { refusal, type }

The content of the output message.

One of the following:

ResponseOutputText object { annotations, logprobs, text, type }

A text output from the model.

annotations: array of object { file_id, filename, index, type } or object { end_index, start_index, title, 2 more } or object { container_id, end_index, file_id, 3 more } or object { file_id, index, type }

The annotations of the text output.

One of the following:

FileCitation object { file_id, filename, index, type }

A citation to a file.

file_id: string

The ID of the file.

filename: string

The filename of the file cited.

index: number

The index in the output text at which to insert the file citation.

type: "file_citation"

The type of the file citation. Always file_citation.

URLCitation object { end_index, start_index, title, 2 more }

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

end_index: number

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

start_index: number

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

title: string

The title of the web resource.

type: "url_citation"

The type of the URL citation. Always url_citation.

url: string

The URL of the web resource.

formaturi

ContainerFileCitation object { container_id, end_index, file_id, 3 more }

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

container_id: string

The ID of the container file.

end_index: number

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

file_id: string

The ID of the file.

filename: string

The filename of the container file cited.

start_index: number

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

type: "container_file_citation"

The type of the container file citation. Always container_file_citation.

FilePath object { file_id, index, type }

A path to a file.

file_id: string

The ID of the file.

index: number

The index of the file in the list of files.

type: "file_path"

The type of the file path. Always file_path.

logprobs: array of object { token, bytes, logprob, top_logprobs }

token: string

bytes: array of number

logprob: number

top_logprobs: array of object { token, bytes, logprob }

token: string

bytes: array of number

logprob: number

text: string

The text output from the model.

type: "output_text"

The type of the output text. Always output_text.

ResponseOutputRefusal object { refusal, type }

A refusal from the model.

refusal: string

The refusal explanation from the model.

type: "refusal"

The type of the refusal. Always refusal.

role: "assistant"

The role of the output message. Always assistant.

status: "in_progress" or "completed" or "incomplete"

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

One of the following:

"in_progress"

"completed"

"incomplete"

type: "message"

The type of the output message. Always message.

phase: optional "commentary" or "final_answer" or null

One of the following:

"commentary"

"final_answer"

FileSearchCall object { id, queries, status, 2 more }

The results of a file search tool call. See the file search guide for more information.

id: string

The unique ID of the file search tool call.

queries: array of string

The queries used to search for files.

status: "in_progress" or "searching" or "completed" or 2 more

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

One of the following:

"in_progress"

"searching"

"completed"

"incomplete"

"failed"

type: "file_search_call"

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

results: optional array of object { attributes, file_id, filename, 2 more } or null

The results of the file search tool call.

attributes: optional map[string or number or boolean] or null

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers.

One of the following:

string

number

boolean

file_id: optional string

The unique ID of the file.

filename: optional string

The name of the file.

score: optional number

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

formatfloat

text: optional string

The text that was retrieved from the file.

ComputerCall object { id, call_id, pending_safety_checks, 4 more }

A tool call to a computer use tool. See the computer use guide for more information.

id: string

The unique ID of the computer call.

call_id: string

An identifier used when responding to the tool call with output.

pending_safety_checks: array of object { id, code, message }

The pending safety checks for the computer call.

id: string

The ID of the pending safety check.

code: optional string or null

The type of the pending safety check.

message: optional string or null

Details about the pending safety check.

status: "in_progress" or "completed" or "incomplete"

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

One of the following:

"in_progress"

"completed"

"incomplete"

type: "computer_call"

The type of the computer call. Always computer_call.

action: optional ComputerAction

A click action.

actions: optional ComputerActionList { Click, DoubleClick, Drag, 6 more }

Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields.

ComputerCallOutput object { call_id, output, type, 3 more }

The output of a computer tool call.

call_id: string

The ID of the computer tool call that produced the output.

minLength1

maxLength64

output: ResponseComputerToolCallOutputScreenshot { type, file_id, image_url }

A computer screenshot image used with the computer use tool.

type: "computer_call_output"

The type of the computer tool call output. Always computer_call_output.

id: optional string or null

The ID of the computer tool call output.

acknowledged_safety_checks: optional array of object { id, code, message } or null

The safety checks reported by the API that have been acknowledged by the developer.

id: string

The ID of the pending safety check.

code: optional string or null

The type of the pending safety check.

message: optional string or null

Details about the pending safety check.

status: optional "in_progress" or "completed" or "incomplete" or null

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

One of the following:

"in_progress"

"completed"

"incomplete"

WebSearchCall object { id, status, type, action }

The results of a web search tool call. See the web search guide for more information.

id: string

The unique ID of the web search tool call.

status: "in_progress" or "searching" or "completed" or 2 more

The status of the web search tool call.

One of the following:

"in_progress"

"searching"

"completed"

"failed"

"incomplete"

type: "web_search_call"

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

action: optional object { type, queries, query, sources } or object { type, url } or object { pattern, type, url }

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).

One of the following:

Search object { type, queries, query, sources }

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

type: "search"

The action type.

queries: optional array of string

The search queries.

query: optional string

Deprecated.

The search query.

sources: optional array of object { type, url }

The sources used in the search.

type: "url"

The type of source. Always url.

url: string

The URL of the source.

formaturi

OpenPage object { type, url }

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

type: "open_page"

The action type.

url: optional string or null

The URL opened by the model.

formaturi

FindInPage object { pattern, type, url }

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

pattern: string

The pattern or text to search for within the page.

type: "find_in_page"

The action type.

url: string

The URL of the page searched for the pattern.

formaturi

FunctionCall object { arguments, call_id, name, 6 more }

A tool call to run a function. See the function calling guide for more information.

arguments: string

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

call_id: string

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

The name of the function to run.

type: "function_call"

The type of the function tool call. Always function_call.

id: optional string

The unique ID of the function tool call.

async: optional boolean

Whether the function tool call runs asynchronously.

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

type: "program"

namespace: optional string

The namespace of the function to run.

status: optional "in_progress" or "completed" or "incomplete"

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

One of the following:

"in_progress"

"completed"

"incomplete"

FunctionCallOutput object { output, type, id, 5 more }

The output of a function tool call.

output: string or array of ResponseInputTextContent { text, type, prompt_cache_breakpoint } or ResponseInputImageContent { type, detail, file_id, 2 more } or ResponseInputFileContent { type, detail, file_data, 4 more }

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

One of the following:

string

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

array of ResponseInputTextContent { text, type, prompt_cache_breakpoint } or ResponseInputImageContent { type, detail, file_id, 2 more } or ResponseInputFileContent { type, detail, file_data, 4 more }

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

One of the following:

ResponseInputTextContent object { text, type, prompt_cache_breakpoint }

A text input to the model.

text: string

The text input to the model.

maxLength10485760

type: "input_text"

The type of the input item. Always input_text.

prompt_cache_breakpoint: optional object { mode } or null

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputImageContent object { type, detail, file_id, 2 more }

An image input to the model. Learn about image inputs

type: "input_image"

The type of the input item. Always input_image.

detail: optional ImageDetail or null

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

file_id: optional string or null

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

image_url: optional string or null

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

maxLength20971520

formaturi

prompt_cache_breakpoint: optional object { mode } or null

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputFileContent object { type, detail, file_data, 4 more }

A file input to the model.

type: "input_file"

The type of the input item. Always input_file.

detail: optional "auto" or "low" or "high"

One of the following:

"auto"

"low"

"high"

file_data: optional string or null

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

maxLength73400320

file_id: optional string or null

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

file_url: optional string or null

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

formaturi

filename: optional string or null

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

prompt_cache_breakpoint: optional object { mode } or null

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

type: "function_call_output"

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

id: optional string or null

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

call_id: optional string or null

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

minLength1

maxLength64

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

The name of the tool that produced the output.

minLength1

maxLength128

namespace: optional string or null

The namespace of the tool that produced the output.

minLength1

maxLength64

status: optional "in_progress" or "completed" or "incomplete" or null

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

One of the following:

"in_progress"

"completed"

"incomplete"

ToolSearchCall object { arguments, type, id, 3 more }

arguments: unknown

The arguments supplied to the tool search call.

type: "tool_search_call"

The item type. Always tool_search_call.

id: optional string or null

The unique ID of this tool search call.

call_id: optional string or null

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

minLength1

maxLength64

execution: optional "server" or "client"

Whether tool search was executed by the server or by the client.

One of the following:

"server"

"client"

status: optional "in_progress" or "completed" or "incomplete" or null

The status of the tool search call.

One of the following:

"in_progress"

"completed"

"incomplete"

ToolSearchOutput object { tools, type, id, 3 more }

tools: array of object { name, parameters, strict, 6 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 more

The loaded tool definitions returned by the tool search output.

One of the following:

Function object { name, parameters, strict, 6 more }

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

The name of the function to call.

parameters: map[unknown] or null

A JSON schema object describing the parameters of the function.

strict: boolean or null

Whether strict parameter validation is enforced for this function tool.

type: "function"

The type of the function tool. Always function.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

defer_loading: optional boolean

Whether this function is deferred and loaded via tool search.

description: optional string or null

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

output_schema: optional map[unknown] or null

A JSON schema object describing the JSON value encoded in string outputs for this function.

FileSearch object { type, vector_store_ids, filters, 2 more }

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

type: "file_search"

The type of the file search tool. Always file_search.

vector_store_ids: array of string

The IDs of the vector stores to search.

filters: optional ComparisonFilter { key, type, value } or CompoundFilter { filters, type } or null

A filter to apply.

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter object { filters, type }

Combine multiple filters using and or or.

filters: array of ComparisonFilter { key, type, value } or CompoundFilter { filters, type }

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

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter { filters, type }

This type repeats the enclosing schema.

type: "and" or "or"

Type of operation: and or or.

One of the following:

"and"

"or"

max_num_results: optional number

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

ranking_options: optional object { hybrid_search, ranker, score_threshold }

Ranking options for search.

hybrid_search: optional object { embedding_weight, text_weight }

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

embedding_weight: number

The weight of the embedding in the reciprocal ranking fusion.

text_weight: number

The weight of the text in the reciprocal ranking fusion.

ranker: optional "auto" or "default-2024-11-15"

The ranker to use for the file search.

One of the following:

"auto"

"default-2024-11-15"

score_threshold: optional 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.

Computer object { type }

A tool that controls a virtual computer. Learn more about the computer tool.

type: "computer"

The type of the computer tool. Always computer.

ComputerUsePreview object { display_height, display_width, environment, type }

A tool that controls a virtual computer. Learn more about the computer tool.

display_height: number

The height of the computer display.

display_width: number

The width of the computer display.

environment: "windows" or "mac" or "linux" or 2 more

The type of computer environment to control.

One of the following:

"windows"

"mac"

"linux"

"ubuntu"

"browser"

type: "computer_use_preview"

The type of the computer use tool. Always computer_use_preview.

WebSearch object { type, external_web_access, filters, 2 more }

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

type: "web_search" or "web_search_2025_08_26"

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

One of the following:

"web_search"

"web_search_2025_08_26"

external_web_access: optional boolean

Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content.

filters: optional object { allowed_domains } or null

Filters for the search.

allowed_domains: optional array of string or null

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

Example: ["pubmed.ncbi.nlm.nih.gov"]

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { city, country, region, 2 more } or null

The approximate location of the user. If omitted or null, defaults to the United States. To avoid this fallback, pass {"type": "approximate"} without location fields. To localize results, provide the relevant location fields.

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

type: optional "approximate"

The type of location approximation. Always approximate.

Mcp object { server_label, type, allowed_callers, 9 more }

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

server_label: string

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

type: "mcp"

The type of the MCP tool. Always mcp.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

allowed_tools: optional array of string or object { read_only, tool_names } or null

List of allowed tool names or a filter object.

One of the following:

McpAllowedTools = array of string

A string array of allowed tool names

McpToolFilter object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

authorization: optional 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.

connector_id: optional "connector_dropbox" or "connector_gmail" or "connector_googlecalendar" or 5 more

Deprecated.

Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.

This field is deprecated for models released after September 1, 2026. Use server_url to connect to a remote MCP server, or tunnel_id to connect through a Secure MCP Tunnel.

Currently supported connector_id values are:

Dropbox: connector_dropbox
Gmail: connector_gmail
Google Calendar: connector_googlecalendar
Google Drive: connector_googledrive
Microsoft Teams: connector_microsoftteams
Outlook Calendar: connector_outlookcalendar
Outlook Email: connector_outlookemail
SharePoint: connector_sharepoint

One of the following:

"connector_dropbox"

"connector_gmail"

"connector_googlecalendar"

"connector_googledrive"

"connector_microsoftteams"

"connector_outlookcalendar"

"connector_outlookemail"

"connector_sharepoint"

defer_loading: optional boolean

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

headers: optional map[string] or null

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

require_approval: optional object { always, never } or "always" or "never" or null

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

One of the following:

McpToolApprovalFilter object { always, never }

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

always: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

never: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

McpToolApprovalSetting = "always" or "never"

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.

One of the following:

"always"

"never"

server_description: optional string

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

server_url: optional string

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

formaturi

tunnel_id: optional string

The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.

CodeInterpreter object { container, type, allowed_callers }

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

container: string or object { type, file_ids, memory_limit, network_policy }

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.

One of the following:

string

The container ID.

CodeInterpreterToolAuto object { type, file_ids, memory_limit, network_policy }

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

type: "auto"

Always auto.

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the code interpreter container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

type: "code_interpreter"

The type of the code interpreter tool. Always code_interpreter.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

The type of the tool. Always programmatic_tool_calling.

ImageGeneration object { type, action, background, 9 more }

A tool that generates images using the GPT image models.

type: "image_generation"

The type of the image generation tool. Always image_generation.

action: optional "generate" or "edit" or "auto"

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

One of the following:

"generate"

"edit"

"auto"

background: optional "transparent" or "opaque" or "auto"

Set the background of the generated image. One of transparent, opaque, or auto. gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, support opaque and transparent backgrounds. Transparent backgrounds are available for supported GPT Image models. For gpt-image-2 and gpt-image-2-2026-04-21, this support is in preview. When using transparent, set the output format to png or webp. Default: auto.

One of the following:

"transparent"

"opaque"

"auto"

input_fidelity: optional "high" or "low" or null

Control how much effort the model will exert to match the style and features, especially facial features, of input images. Supports high and low on gpt-image-1 and gpt-image-1.5; gpt-image-1-mini supports only low. For gpt-image-2, omit this parameter. Defaults to low on supported models.

One of the following:

"high"

"low"

input_image_mask: optional object { file_id, image_url }

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

file_id: optional string

File ID for the mask image.

image_url: optional string

Base64-encoded mask image.

model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

The image generation model to use. One of gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, gpt-image-2.5-flare-2026-09-08, or chatgpt-image-latest. Default: gpt-image-1.

One of the following:

string

"gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

One of the following:

"gpt-image-1"

"gpt-image-1-mini"

"gpt-image-1.5"

"gpt-image-2"

"gpt-image-2-2026-04-21"

"gpt-image-2.5-sunburst"

"gpt-image-2.5-sunburst-2026-09-08"

"gpt-image-2.5-flare"

"gpt-image-2.5-flare-2026-09-08"

moderation: optional "auto" or "low"

Moderation level for the generated image. Default: auto.

One of the following:

"auto"

"low"

output_compression: optional number

Compression level for the output image. Default: 100.

minimum0

maximum100

output_format: optional "png" or "webp" or "jpeg"

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

One of the following:

"png"

"webp"

"jpeg"

partial_images: optional number

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

minimum0

maximum3

quality: optional "low" or "medium" or "high" or 3 more

The quality of the generated image. The GPT image models support low, medium, and high. gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, also support xhigh and max. Default: auto.

One of the following:

"low"

"medium"

"high"

"xhigh"

"max"

"auto"

size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The size of the generated images. For gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, and gpt-image-2.5-flare-2026-09-08, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing.

One of the following:

string

"1024x1024" or "1024x1536" or "1536x1024" or "auto"

One of the following:

"1024x1024"

"1024x1536"

"1536x1024"

"auto"

LocalShell object { type }

A tool that allows the model to execute shell commands in a local environment.

type: "local_shell"

The type of the local shell tool. Always local_shell.

Shell object { type, allowed_callers, environment }

A tool that allows the model to execute shell commands.

type: "shell"

The type of the shell tool. Always shell.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

environment: optional ContainerAuto { type, file_ids, memory_limit, 2 more } or LocalEnvironment { type, skills } or ContainerReference { container_id, type } or null

One of the following:

ContainerAuto object { type, file_ids, memory_limit, 2 more }

type: "container_auto"

Automatically creates a container for this request

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

skills: optional array of SkillReference { skill_id, type, version } or InlineSkill { description, name, source, type }

An optional list of skills referenced by id or inline data.

One of the following:

SkillReference object { skill_id, type, version }

skill_id: string

The ID of the referenced skill.

minLength1

maxLength64

type: "skill_reference"

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

version: optional string

Optional skill version. Use a positive integer or 'latest'. Omit for default.

InlineSkill object { description, name, source, type }

description: string

The description of the skill.

The name of the skill.

source: InlineSkillSource { data, media_type, type }

Inline skill payload

type: "inline"

Defines an inline skill for this request.

LocalEnvironment object { type, skills }

type: "local"

Use a local computer environment.

skills: optional array of LocalSkill { description, name, path }

An optional list of skills.

description: string

The description of the skill.

The name of the skill.

path: string

The path to the directory containing the skill.

ContainerReference object { container_id, type }

container_id: string

The ID of the referenced container.

type: "container_reference"

References a container created with the /v1/containers endpoint

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

Namespace object { description, name, tools, type }

Groups function/custom tools under a shared namespace.

description: string

A description of the namespace shown to the model.

The namespace name used in tool calls (for example, crm).

minLength1

tools: array of object { name, type, allowed_callers, 6 more } or object { name, type, allowed_callers, 4 more }

The function/custom tools available inside this namespace.

One of the following:

Function object { name, type, allowed_callers, 6 more }

minLength1

maxLength128

type: "function"

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this function should be deferred and discovered via tool search.

description: optional string or null

output_schema: optional map[unknown] or null

A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs.

parameters: optional unknown or null

strict: optional boolean or null

Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise.

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

type: "namespace"

The type of the tool. Always namespace.

ToolSearch object { type, description, execution, parameters }

Hosted or BYOT tool search configuration for deferred tools.

type: "tool_search"

The type of the tool. Always tool_search.

description: optional string or null

Description shown to the model for a client-executed tool search tool.

execution: optional "server" or "client"

Whether tool search is executed by the server or by the client.

One of the following:

"server"

"client"

parameters: optional unknown or null

Parameter schema for a client-executed tool search tool.

WebSearchPreview object { type, search_content_types, search_context_size, user_location }

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

type: "web_search_preview" or "web_search_preview_2025_03_11"

The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.

One of the following:

"web_search_preview"

"web_search_preview_2025_03_11"

search_content_types: optional array of "text" or "image"

One of the following:

"text"

"image"

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { type, city, country, 2 more } or null

type: "approximate"

The type of location approximation. Always approximate.

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

ApplyPatch object { type, allowed_callers }

Allows the assistant to create, delete, or update files using unified diffs.

type: "apply_patch"

The type of the tool. Always apply_patch.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

type: "tool_search_output"

The item type. Always tool_search_output.

id: optional string or null

The unique ID of this tool search output.

call_id: optional string or null

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

minLength1

maxLength64

execution: optional "server" or "client"

Whether tool search was executed by the server or by the client.

One of the following:

"server"

"client"

status: optional "in_progress" or "completed" or "incomplete" or null

The status of the tool search output.

One of the following:

"in_progress"

"completed"

"incomplete"

AdditionalTools object { role, tools, type, id }

role: "developer"

The role that provided the additional tools. Only developer is supported.

tools: array of object { name, parameters, strict, 6 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 more

A list of additional tools made available at this item.

One of the following:

Function object { name, parameters, strict, 6 more }

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

The name of the function to call.

parameters: map[unknown] or null

A JSON schema object describing the parameters of the function.

strict: boolean or null

Whether strict parameter validation is enforced for this function tool.

type: "function"

The type of the function tool. Always function.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

defer_loading: optional boolean

Whether this function is deferred and loaded via tool search.

description: optional string or null

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

output_schema: optional map[unknown] or null

A JSON schema object describing the JSON value encoded in string outputs for this function.

FileSearch object { type, vector_store_ids, filters, 2 more }

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

type: "file_search"

The type of the file search tool. Always file_search.

vector_store_ids: array of string

The IDs of the vector stores to search.

filters: optional ComparisonFilter { key, type, value } or CompoundFilter { filters, type } or null

A filter to apply.

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter object { filters, type }

Combine multiple filters using and or or.

filters: array of ComparisonFilter { key, type, value } or CompoundFilter { filters, type }

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

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter { filters, type }

This type repeats the enclosing schema.

type: "and" or "or"

Type of operation: and or or.

One of the following:

"and"

"or"

max_num_results: optional number

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

ranking_options: optional object { hybrid_search, ranker, score_threshold }

Ranking options for search.

hybrid_search: optional object { embedding_weight, text_weight }

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

embedding_weight: number

The weight of the embedding in the reciprocal ranking fusion.

text_weight: number

The weight of the text in the reciprocal ranking fusion.

ranker: optional "auto" or "default-2024-11-15"

The ranker to use for the file search.

One of the following:

"auto"

"default-2024-11-15"

score_threshold: optional 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.

Computer object { type }

A tool that controls a virtual computer. Learn more about the computer tool.

type: "computer"

The type of the computer tool. Always computer.

ComputerUsePreview object { display_height, display_width, environment, type }

A tool that controls a virtual computer. Learn more about the computer tool.

display_height: number

The height of the computer display.

display_width: number

The width of the computer display.

environment: "windows" or "mac" or "linux" or 2 more

The type of computer environment to control.

One of the following:

"windows"

"mac"

"linux"

"ubuntu"

"browser"

type: "computer_use_preview"

The type of the computer use tool. Always computer_use_preview.

WebSearch object { type, external_web_access, filters, 2 more }

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

type: "web_search" or "web_search_2025_08_26"

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

One of the following:

"web_search"

"web_search_2025_08_26"

external_web_access: optional boolean

Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content.

filters: optional object { allowed_domains } or null

Filters for the search.

allowed_domains: optional array of string or null

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

Example: ["pubmed.ncbi.nlm.nih.gov"]

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { city, country, region, 2 more } or null

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

type: optional "approximate"

The type of location approximation. Always approximate.

Mcp object { server_label, type, allowed_callers, 9 more }

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

server_label: string

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

type: "mcp"

The type of the MCP tool. Always mcp.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

allowed_tools: optional array of string or object { read_only, tool_names } or null

List of allowed tool names or a filter object.

One of the following:

McpAllowedTools = array of string

A string array of allowed tool names

McpToolFilter object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

authorization: optional string

connector_id: optional "connector_dropbox" or "connector_gmail" or "connector_googlecalendar" or 5 more

Deprecated.

Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.

This field is deprecated for models released after September 1, 2026. Use server_url to connect to a remote MCP server, or tunnel_id to connect through a Secure MCP Tunnel.

Currently supported connector_id values are:

Dropbox: connector_dropbox
Gmail: connector_gmail
Google Calendar: connector_googlecalendar
Google Drive: connector_googledrive
Microsoft Teams: connector_microsoftteams
Outlook Calendar: connector_outlookcalendar
Outlook Email: connector_outlookemail
SharePoint: connector_sharepoint

One of the following:

"connector_dropbox"

"connector_gmail"

"connector_googlecalendar"

"connector_googledrive"

"connector_microsoftteams"

"connector_outlookcalendar"

"connector_outlookemail"

"connector_sharepoint"

defer_loading: optional boolean

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

headers: optional map[string] or null

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

require_approval: optional object { always, never } or "always" or "never" or null

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

One of the following:

McpToolApprovalFilter object { always, never }

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

always: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

never: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

McpToolApprovalSetting = "always" or "never"

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.

One of the following:

"always"

"never"

server_description: optional string

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

server_url: optional string

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

formaturi

tunnel_id: optional string

The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.

CodeInterpreter object { container, type, allowed_callers }

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

container: string or object { type, file_ids, memory_limit, network_policy }

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.

One of the following:

string

The container ID.

CodeInterpreterToolAuto object { type, file_ids, memory_limit, network_policy }

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

type: "auto"

Always auto.

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the code interpreter container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

type: "code_interpreter"

The type of the code interpreter tool. Always code_interpreter.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

The type of the tool. Always programmatic_tool_calling.

ImageGeneration object { type, action, background, 9 more }

A tool that generates images using the GPT image models.

type: "image_generation"

The type of the image generation tool. Always image_generation.

action: optional "generate" or "edit" or "auto"

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

One of the following:

"generate"

"edit"

"auto"

background: optional "transparent" or "opaque" or "auto"

One of the following:

"transparent"

"opaque"

"auto"

input_fidelity: optional "high" or "low" or null

One of the following:

"high"

"low"

input_image_mask: optional object { file_id, image_url }

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

file_id: optional string

File ID for the mask image.

image_url: optional string

Base64-encoded mask image.

model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

One of the following:

string

"gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

One of the following:

"gpt-image-1"

"gpt-image-1-mini"

"gpt-image-1.5"

"gpt-image-2"

"gpt-image-2-2026-04-21"

"gpt-image-2.5-sunburst"

"gpt-image-2.5-sunburst-2026-09-08"

"gpt-image-2.5-flare"

"gpt-image-2.5-flare-2026-09-08"

moderation: optional "auto" or "low"

Moderation level for the generated image. Default: auto.

One of the following:

"auto"

"low"

output_compression: optional number

Compression level for the output image. Default: 100.

minimum0

maximum100

output_format: optional "png" or "webp" or "jpeg"

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

One of the following:

"png"

"webp"

"jpeg"

partial_images: optional number

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

minimum0

maximum3

quality: optional "low" or "medium" or "high" or 3 more

One of the following:

"low"

"medium"

"high"

"xhigh"

"max"

"auto"

size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

One of the following:

string

"1024x1024" or "1024x1536" or "1536x1024" or "auto"

One of the following:

"1024x1024"

"1024x1536"

"1536x1024"

"auto"

LocalShell object { type }

A tool that allows the model to execute shell commands in a local environment.

type: "local_shell"

The type of the local shell tool. Always local_shell.

Shell object { type, allowed_callers, environment }

A tool that allows the model to execute shell commands.

type: "shell"

The type of the shell tool. Always shell.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

environment: optional ContainerAuto { type, file_ids, memory_limit, 2 more } or LocalEnvironment { type, skills } or ContainerReference { container_id, type } or null

One of the following:

ContainerAuto object { type, file_ids, memory_limit, 2 more }

type: "container_auto"

Automatically creates a container for this request

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

skills: optional array of SkillReference { skill_id, type, version } or InlineSkill { description, name, source, type }

An optional list of skills referenced by id or inline data.

One of the following:

SkillReference object { skill_id, type, version }

skill_id: string

The ID of the referenced skill.

minLength1

maxLength64

type: "skill_reference"

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

version: optional string

Optional skill version. Use a positive integer or 'latest'. Omit for default.

InlineSkill object { description, name, source, type }

description: string

The description of the skill.

The name of the skill.

source: InlineSkillSource { data, media_type, type }

Inline skill payload

type: "inline"

Defines an inline skill for this request.

LocalEnvironment object { type, skills }

type: "local"

Use a local computer environment.

skills: optional array of LocalSkill { description, name, path }

An optional list of skills.

description: string

The description of the skill.

The name of the skill.

path: string

The path to the directory containing the skill.

ContainerReference object { container_id, type }

container_id: string

The ID of the referenced container.

type: "container_reference"

References a container created with the /v1/containers endpoint

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

Namespace object { description, name, tools, type }

Groups function/custom tools under a shared namespace.

description: string

A description of the namespace shown to the model.

The namespace name used in tool calls (for example, crm).

minLength1

tools: array of object { name, type, allowed_callers, 6 more } or object { name, type, allowed_callers, 4 more }

The function/custom tools available inside this namespace.

One of the following:

Function object { name, type, allowed_callers, 6 more }

minLength1

maxLength128

type: "function"

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this function should be deferred and discovered via tool search.

description: optional string or null

output_schema: optional map[unknown] or null

A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs.

parameters: optional unknown or null

strict: optional boolean or null

Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise.

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

type: "namespace"

The type of the tool. Always namespace.

ToolSearch object { type, description, execution, parameters }

Hosted or BYOT tool search configuration for deferred tools.

type: "tool_search"

The type of the tool. Always tool_search.

description: optional string or null

Description shown to the model for a client-executed tool search tool.

execution: optional "server" or "client"

Whether tool search is executed by the server or by the client.

One of the following:

"server"

"client"

parameters: optional unknown or null

Parameter schema for a client-executed tool search tool.

WebSearchPreview object { type, search_content_types, search_context_size, user_location }

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

type: "web_search_preview" or "web_search_preview_2025_03_11"

The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.

One of the following:

"web_search_preview"

"web_search_preview_2025_03_11"

search_content_types: optional array of "text" or "image"

One of the following:

"text"

"image"

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { type, city, country, 2 more } or null

type: "approximate"

The type of location approximation. Always approximate.

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

ApplyPatch object { type, allowed_callers }

Allows the assistant to create, delete, or update files using unified diffs.

type: "apply_patch"

The type of the tool. Always apply_patch.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

type: "additional_tools"

The item type. Always additional_tools.

id: optional string or null

The unique ID of this additional tools item.

ConfigurationUpdate object { type, id, reasoning }

An update to the conversation's response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update.

type: "configuration_update"

The item type. Always configuration_update.

id: optional string or null

The unique ID of the configuration update item.

reasoning: optional object { effort }

Updates to reasoning configuration. Only effort is supported.

effort: optional ReasoningEffort or null

The reasoning effort to use for subsequent responses until another configuration update replaces it.

Reasoning object { id, summary, type, 3 more }

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.

id: string

The unique identifier of the reasoning content.

summary: array of SummaryTextContent { text, type }

Reasoning summary content.

text: string

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

type: "summary_text"

The type of the object. Always summary_text.

type: "reasoning"

The type of the object. Always reasoning.

content: optional array of object { text, type }

Reasoning text content.

text: string

The reasoning text from the model.

type: "reasoning_text"

The type of the reasoning text. Always reasoning_text.

encrypted_content: optional string or null

The encrypted content of the reasoning item. This is populated by default for reasoning items returned by POST /v1/responses and WebSocket response.create requests.

When streaming, use the completed reasoning item and its encrypted_content from the response.output_item.done event in subsequent requests. The encrypted_content in response.output_item.added may be incomplete. This is especially important when store is false or when using Zero Data Retention.

status: optional "in_progress" or "completed" or "incomplete"

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

One of the following:

"in_progress"

"completed"

"incomplete"

Compaction object { encrypted_content, type, id }

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

encrypted_content: string

The encrypted content of the compaction summary.

maxLength104857600

type: "compaction"

The type of the item. Always compaction.

id: optional string or null

The ID of the compaction item.

ImageGenerationCall object { id, result, status, 7 more }

An image generation request made by the model.

id: string

The unique ID of the image generation call.

result: string or null

The generated image encoded in base64.

status: "in_progress" or "completed" or "generating" or "failed"

The status of the image generation call.

One of the following:

"in_progress"

"completed"

"generating"

"failed"

type: "image_generation_call"

The type of the image generation call. Always image_generation_call.

action: optional "generate" or "edit" or "auto" or null

The action used for image generation.

One of the following:

"generate"

"edit"

"auto"

background: optional "transparent" or "opaque" or "auto" or null

The background setting used for generation.

One of the following:

"transparent"

"opaque"

"auto"

output_format: optional "png" or "webp" or "jpeg" or null

The output format used for generation.

One of the following:

"png"

"webp"

"jpeg"

quality: optional "low" or "medium" or "high" or 3 more or null

The quality of the image generated by the image generation tool call. One of low, medium, high, xhigh, max, or auto.

One of the following:

"low"

"medium"

"high"

"xhigh"

"max"

"auto"

revised_prompt: optional string or null

The prompt that was used after any model prompt rewriting.

size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or null

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:

string

"1024x1024" or "1024x1536" or "1536x1024"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:

"1024x1024"

"1024x1536"

"1536x1024"

CodeInterpreterCall object { id, code, container_id, 3 more }

A tool call to run code.

id: string

The unique ID of the code interpreter tool call.

code: string or null

The code to run, or null if not available.

container_id: string

The ID of the container used to run the code.

outputs: array of object { logs, type } or object { type, url } or null

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

One of the following:

Logs object { logs, type }

The logs output from the code interpreter.

logs: string

The logs output from the code interpreter.

type: "logs"

The type of the output. Always logs.

Image object { type, url }

The image output from the code interpreter.

type: "image"

The type of the output. Always image.

url: string

The URL of the image output from the code interpreter.

formaturi

status: "in_progress" or "completed" or "incomplete" or 2 more

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

One of the following:

"in_progress"

"completed"

"incomplete"

"interpreting"

"failed"

type: "code_interpreter_call"

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

LocalShellCall object { id, action, call_id, 2 more }

A tool call to run a command on the local shell.

id: string

The unique ID of the local shell call.

action: object { command, env, type, 3 more }

Execute a shell command on the server.

command: array of string

The command to run.

env: map[string]

Environment variables to set for the command.

type: "exec"

The type of the local shell action. Always exec.

timeout_ms: optional number or null

Optional timeout in milliseconds for the command.

user: optional string or null

Optional user to run the command as.

working_directory: optional string or null

Optional working directory to run the command in.

call_id: string

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

status: "in_progress" or "completed" or "incomplete"

The status of the local shell call.

One of the following:

"in_progress"

"completed"

"incomplete"

type: "local_shell_call"

The type of the local shell call. Always local_shell_call.

LocalShellCallOutput object { id, output, type, status }

The output of a local shell tool call.

id: string

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

output: string

A JSON string of the output of the local shell tool call.

type: "local_shell_call_output"

The type of the local shell tool call output. Always local_shell_call_output.

status: optional "in_progress" or "completed" or "incomplete" or null

The status of the item. One of in_progress, completed, or incomplete.

One of the following:

"in_progress"

"completed"

"incomplete"

ShellCall object { action, call_id, type, 4 more }

A tool representing a request to execute one or more shell commands.

action: object { commands, max_output_length, timeout_ms }

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

commands: array of string

Ordered shell commands for the execution environment to run.

max_output_length: optional number or null

Maximum number of UTF-8 characters to capture from combined stdout and stderr output.

timeout_ms: optional number or null

Maximum wall-clock time in milliseconds to allow the shell commands to run.

call_id: string

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

minLength1

maxLength64

type: "shell_call"

The type of the item. Always shell_call.

id: optional string or null

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

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

environment: optional LocalEnvironment { type, skills } or ContainerReference { container_id, type } or null

The environment to execute the shell commands in.

One of the following:

LocalEnvironment object { type, skills }

type: "local"

Use a local computer environment.

skills: optional array of LocalSkill { description, name, path }

An optional list of skills.

description: string

The description of the skill.

The name of the skill.

path: string

The path to the directory containing the skill.

ContainerReference object { container_id, type }

container_id: string

The ID of the referenced container.

type: "container_reference"

References a container created with the /v1/containers endpoint

status: optional "in_progress" or "completed" or "incomplete" or null

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

One of the following:

"in_progress"

"completed"

"incomplete"

ShellCallOutput object { call_id, output, type, 4 more }

The streamed output items emitted by a shell tool call.

call_id: string

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

minLength1

maxLength64

output: array of ResponseFunctionShellCallOutputContent { outcome, stderr, stdout }

Captured chunks of stdout and stderr output, along with their associated outcomes.

outcome: object { type } or object { exit_code, type }

The exit or timeout outcome associated with this shell call.

One of the following:

Timeout object { type }

Indicates that the shell call exceeded its configured time limit.

type: "timeout"

The outcome type. Always timeout.

Exit object { exit_code, type }

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

exit_code: number

The exit code returned by the shell process.

type: "exit"

The outcome type. Always exit.

stderr: string

Captured stderr output for the shell call.

maxLength10485760

stdout: string

Captured stdout output for the shell call.

maxLength10485760

type: "shell_call_output"

The type of the item. Always shell_call_output.

id: optional string or null

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

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

max_output_length: optional number or null

The maximum number of UTF-8 characters captured for this shell call's combined output.

status: optional "in_progress" or "completed" or "incomplete" or null

The status of the shell call output.

One of the following:

"in_progress"

"completed"

"incomplete"

ApplyPatchCall object { call_id, operation, status, 3 more }

A tool call representing a request to create, delete, or update files using diff patches.

call_id: string

The unique ID of the apply patch tool call generated by the model.

minLength1

maxLength64

operation: object { diff, path, type } or object { path, type } or object { diff, path, type }

The specific create, delete, or update instruction for the apply_patch tool call.

One of the following:

CreateFile object { diff, path, type }

Instruction for creating a new file via the apply_patch tool.

diff: string

Unified diff content to apply when creating the file.

maxLength10485760

path: string

Path of the file to create relative to the workspace root.

minLength1

type: "create_file"

The operation type. Always create_file.

DeleteFile object { path, type }

Instruction for deleting an existing file via the apply_patch tool.

path: string

Path of the file to delete relative to the workspace root.

minLength1

type: "delete_file"

The operation type. Always delete_file.

UpdateFile object { diff, path, type }

Instruction for updating an existing file via the apply_patch tool.

diff: string

Unified diff content to apply to the existing file.

maxLength10485760

path: string

Path of the file to update relative to the workspace root.

minLength1

type: "update_file"

The operation type. Always update_file.

status: "in_progress" or "completed"

The status of the apply patch tool call. One of in_progress or completed.

One of the following:

"in_progress"

"completed"

type: "apply_patch_call"

The type of the item. Always apply_patch_call.

id: optional string or null

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

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

ApplyPatchCallOutput object { call_id, status, type, 3 more }

The streamed output emitted by an apply patch tool call.

call_id: string

The unique ID of the apply patch tool call generated by the model.

minLength1

maxLength64

status: "completed" or "failed"

The status of the apply patch tool call output. One of completed or failed.

One of the following:

"completed"

"failed"

type: "apply_patch_call_output"

The type of the item. Always apply_patch_call_output.

id: optional string or null

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

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

output: optional string or null

Optional human-readable log text from the apply patch tool (e.g., patch results or errors).

maxLength10485760

McpListTools object { id, server_label, tools, 2 more }

A list of tools available on an MCP server.

id: string

The unique ID of the list.

server_label: string

The label of the MCP server.

tools: array of object { input_schema, name, annotations, description }

The tools available on the server.

input_schema: unknown

The JSON schema describing the tool's input.

The name of the tool.

annotations: optional unknown or null

Additional annotations about the tool.

description: optional string or null

The description of the tool.

type: "mcp_list_tools"

The type of the item. Always mcp_list_tools.

error: optional string or null

Error message if the server could not list tools.

McpApprovalRequest object { id, arguments, name, 2 more }

A request for human approval of a tool invocation.

id: string

The unique ID of the approval request.

arguments: string

A JSON string of arguments for the tool.

The name of the tool to run.

server_label: string

The label of the MCP server making the request.

type: "mcp_approval_request"

The type of the item. Always mcp_approval_request.

McpApprovalResponse object { approval_request_id, approve, type, 2 more }

A response to an MCP approval request.

approval_request_id: string

The ID of the approval request being answered.

approve: boolean

Whether the request was approved.

type: "mcp_approval_response"

The type of the item. Always mcp_approval_response.

id: optional string or null

The unique ID of the approval response

reason: optional string or null

Optional reason for the decision.

McpCall object { id, arguments, name, 6 more }

An invocation of a tool on an MCP server.

id: string

The unique ID of the tool call.

arguments: string

A JSON string of the arguments passed to the tool.

The name of the tool that was run.

server_label: string

The label of the MCP server running the tool.

type: "mcp_call"

The type of the item. Always mcp_call.

approval_request_id: optional string or null

Unique identifier for the MCP tool call approval request. Include this value in a subsequent mcp_approval_response input to approve or reject the corresponding tool call.

error: optional McpToolCallError or null

The error from the tool call, if any.

output: optional string or null

The output from the tool call.

status: optional "in_progress" or "completed" or "incomplete" or 2 more

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

One of the following:

"in_progress"

"completed"

"incomplete"

"calling"

"failed"

CustomToolCallOutput object { call_id, output, type, 2 more }

The output of a custom tool call from your code, being sent back to the model.

call_id: string

The call ID, used to map this custom tool call output to a custom tool call.

output: string or array of ResponseInputText { text, type, prompt_cache_breakpoint } or ResponseInputImage { detail, type, file_id, 2 more } or ResponseInputFile { type, detail, file_data, 4 more }

The output from the custom tool call generated by your code. Can be a string or an list of output content.

One of the following:

StringOutput = string

A string of the output of the custom tool call.

OutputContentList = array of ResponseInputText { text, type, prompt_cache_breakpoint } or ResponseInputImage { detail, type, file_id, 2 more } or ResponseInputFile { type, detail, file_data, 4 more }

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

One of the following:

ResponseInputText object { text, type, prompt_cache_breakpoint }

A text input to the model.

text: string

The text input to the model.

type: "input_text"

The type of the input item. Always input_text.

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputImage object { detail, type, file_id, 2 more }

An image input to the model. Learn about image inputs.

detail: ImageDetail

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

type: "input_image"

The type of the input item. Always input_image.

file_id: optional string or null

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

image_url: optional string or null

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

formaturi

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

ResponseInputFile object { type, detail, file_data, 4 more }

A file input to the model.

type: "input_file"

The type of the input item. Always input_file.

detail: optional "auto" or "low" or "high"

One of the following:

"auto"

"low"

"high"

file_data: optional string

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

file_id: optional string or null

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

file_url: optional string

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

formaturi

filename: optional string

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

prompt_cache_breakpoint: optional object { mode }

Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's prompt_cache_options.ttl; the boundary is not rounded to a token block.

mode: "explicit"

The breakpoint mode. Always explicit.

type: "custom_tool_call_output"

The type of the custom tool call output. Always custom_tool_call_output.

id: optional string

The unique ID of the custom tool call output in the OpenAI platform.

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

The caller type. Always direct.

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

minLength1

maxLength64

type: "program"

The caller type. Always program.

CustomToolCall object { call_id, input, name, 5 more }

A call to a custom tool created by the model.

call_id: string

An identifier used to map this custom tool call to a tool call output.

input: string

The input for the custom tool call generated by the model.

The name of the custom tool being called.

type: "custom_tool_call"

The type of the custom tool call. Always custom_tool_call.

id: optional string

The unique ID of the custom tool call in the OpenAI platform.

async: optional boolean

Whether the custom tool call runs asynchronously.

caller: optional object { type } or object { caller_id, type } or null

The execution context that produced this tool call.

One of the following:

Direct object { type }

type: "direct"

Program object { caller_id, type }

caller_id: string

The call ID of the program item that produced this tool call.

type: "program"

namespace: optional string

The namespace of the custom tool being called.

CompactionTrigger object { type, id }

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

type: "compaction_trigger"

The type of the item. Always compaction_trigger.

id: optional string or null

The unique ID of this compaction trigger.

ItemReference object { id, type }

An internal identifier for an item to reference.

id: string

The ID of the item to reference.

type: optional "item_reference" or null

The type of item to reference. Always item_reference.

Program object { id, call_id, code, 2 more }

id: string

The unique ID of this program item.

call_id: string

The stable call ID of the program item.

minLength1

maxLength64

code: string

The JavaScript source executed by programmatic tool calling.

maxLength10485760

fingerprint: string

Opaque program replay fingerprint that must be round-tripped.

maxLength10485760

type: "program"

The item type. Always program.

ProgramOutput object { id, call_id, result, 2 more }

id: string

The unique ID of this program output item.

call_id: string

The call ID of the program item.

minLength1

maxLength64

result: string

The result produced by the program item.

maxLength10485760

status: "completed" or "incomplete"

The terminal status of the program output.

One of the following:

"completed"

"incomplete"

type: "program_output"

The item type. Always program_output.

instructions: optional string or null

A system (or developer) message inserted into the model's context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

max_output_tokens: optional number or null

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

minimum16

max_tool_calls: optional number or null

The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

metadata: optional Metadata or null

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

model: optional ResponsesModel

Model ID used to generate the response, like gpt-6-astra. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

moderation: optional object { model, policy } or null

Configuration for running moderation on the input and output of this response.

model: string

The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'.

policy: optional object { input, output } or null

The policy to apply to moderated response input and output.

input: optional object { mode } or null

The moderation policy for the response input.

mode: "score" or "block"

One of the following:

"score"

"block"

output: optional object { mode } or null

The moderation policy for the response output.

mode: "score" or "block"

One of the following:

"score"

"block"

parallel_tool_calls: optional boolean or null

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

previous_response_id: optional string or null

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

prompt: optional ResponsePrompt { id, variables, version } or null

Reference to a prompt template and its variables. Learn more.

prompt_cache_key: optional string or null

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

prompt_cache_options: optional object { comparison_response_id, mode, prewarm, ttl }

Options for prompt caching. Supported for gpt-5.6 and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with prompt_cache_breakpoint. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set mode to explicit to disable the implicit breakpoint. The ttl defaults to 30m, which is currently the only supported value. See the prompt caching guide for current details.

comparison_response_id: optional string or null

The ID of a response to compare when diagnosing prompt cache reuse. Supplying this field requests prompt cache diagnostics when the feature is enabled.

mode: optional "implicit" or "explicit"

Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to implicit. With implicit, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With explicit, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching.

One of the following:

"implicit"

"explicit"

prewarm: optional boolean

Prepares the prompt cache without generating output. Defaults to false. When set to true, overrides the generate field to false.

ttl: optional "30m"

The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to 30m, which is currently the only supported value. The backend may retain cache entries for longer.

prompt_cache_retention: optional "in_memory" or "24h" or null

Deprecated.

Deprecated. Use prompt_cache_options.ttl instead.

The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more. This field expresses a maximum retention policy, while prompt_cache_options.ttl expresses a minimum cache lifetime. The two fields are independent and do not interact. For gpt-5.5, gpt-5.5-pro, and future models, only 24h is supported.

For older models that support both in_memory and 24h, the default depends on your organization's data retention policy:

Organizations without ZDR enabled default to 24h.
Organizations with ZDR enabled default to in_memory when prompt_cache_retention is not specified.

One of the following:

"in_memory"

"24h"

reasoning: optional Reasoning { context, effort, generate_summary, 2 more } or null

Configuration options for reasoning models.

safety_identifier: optional string or null

A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

maxLength64

service_tier: optional ServiceTier or null

Specifies the processing type used for serving the request.

If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
If set to 'flex', then the request will be processed with the Flex Processing service tier.
To opt-in to Fast mode at the request level, include the service_tier=fast or service_tier=priority parameter for Responses or Chat Completions. The response will show service_tier=priority regardless of if you specify service_tier=fast or priority in your request.
If set to 'ultrafast', then the request will be processed with the access-controlled Ultrafast Processing service tier. This tier is currently available for gpt-5.6-sol; a response served through it will show service_tier=ultrafast.
When not set, the default behavior is 'auto'.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

store: optional boolean or null

Whether to store the generated model response for later retrieval via API. Defaults to true when omitted. If set to true, response data will be stored for at least 30 days, subject to the data retention exceptions.

stream: optional boolean or null

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.

stream_id: optional string

The WebSocket lane for this response. Requests with the same stream_id are processed FIFO, and events for the response echo the same stream_id.

stream_id controls routing; previous_response_id controls conversation lineage, so a new lane can fork from a response created on another lane.

minLength1

maxLength256

stream_options: optional object { include_obfuscation } or null

Options for streaming responses. Only set this when you set stream: true.

include_obfuscation: optional boolean

When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

temperature: optional number or null

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

minimum0

maximum2

text: optional ResponseTextConfig { format, verbosity }

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

tool_choice: optional ToolChoiceOptions or ToolChoiceAllowed { mode, tools, type } or ToolChoiceTypes { type } or 6 more

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 the following:

ToolChoiceOptions = "none" or "auto" or "required"

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.

One of the following:

"none"

"auto"

"required"

ToolChoiceAllowed object { mode, tools, type }

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

mode: "auto" or "required"

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.

One of the following:

"auto"

"required"

tools: array of map[unknown]

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

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

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

type: "allowed_tools"

Allowed tool configuration type. Always allowed_tools.

ToolChoiceTypes object { type }

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

type: "file_search" or "web_search_preview" or "computer" or 5 more

The type of hosted tool the model should to use. Learn more about built-in tools.

Allowed values are:

file_search
web_search_preview
computer
computer_use_preview
computer_use
code_interpreter
image_generation

One of the following:

"file_search"

"web_search_preview"

"computer"

"computer_use_preview"

"computer_use"

"web_search_preview_2025_03_11"

"image_generation"

"code_interpreter"

ToolChoiceFunction object { name, type }

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

The name of the function to call.

type: "function"

For function calling, the type is always function.

ToolChoiceMcp object { server_label, type, name }

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

server_label: string

The label of the MCP server to use.

type: "mcp"

For MCP tools, the type is always mcp.

The name of the tool to call on the server.

ToolChoiceCustom object { name, type }

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

The name of the custom tool to call.

type: "custom"

For custom tool calling, the type is always custom.

SpecificProgrammaticToolCallingParam object { type }

type: "programmatic_tool_calling"

The tool to call. Always programmatic_tool_calling.

ToolChoiceApplyPatch object { type }

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

type: "apply_patch"

The tool to call. Always apply_patch.

ToolChoiceShell object { type }

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

type: "shell"

The tool to call. Always shell.

tools: optional array of object { name, parameters, strict, 6 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 more

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.

We support the following categories of tools:

Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
MCP Tools: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about MCP Tools.
Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about function calling. You can also use custom tools to call your own code.

One of the following:

Function object { name, parameters, strict, 6 more }

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

The name of the function to call.

parameters: map[unknown] or null

A JSON schema object describing the parameters of the function.

strict: boolean or null

Whether strict parameter validation is enforced for this function tool.

type: "function"

The type of the function tool. Always function.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

defer_loading: optional boolean

Whether this function is deferred and loaded via tool search.

description: optional string or null

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

output_schema: optional map[unknown] or null

A JSON schema object describing the JSON value encoded in string outputs for this function.

FileSearch object { type, vector_store_ids, filters, 2 more }

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

type: "file_search"

The type of the file search tool. Always file_search.

vector_store_ids: array of string

The IDs of the vector stores to search.

filters: optional ComparisonFilter { key, type, value } or CompoundFilter { filters, type } or null

A filter to apply.

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter object { filters, type }

Combine multiple filters using and or or.

filters: array of ComparisonFilter { key, type, value } or CompoundFilter { filters, type }

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

One of the following:

ComparisonFilter object { key, type, value }

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

key: string

The key to compare against the value.

type: "eq" or "ne" or "gt" or 5 more

Specifies the comparison operator: eq, ne, gt, gte, lt, lte, in, nin.

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

One of the following:

"eq"

"ne"

"gt"

"gte"

"lt"

"lte"

"in"

"nin"

value: string or number or boolean or array of string or number

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

One of the following:

string

number

boolean

array of string or number

One of the following:

string

number

CompoundFilter { filters, type }

This type repeats the enclosing schema.

type: "and" or "or"

Type of operation: and or or.

One of the following:

"and"

"or"

max_num_results: optional number

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

ranking_options: optional object { hybrid_search, ranker, score_threshold }

Ranking options for search.

hybrid_search: optional object { embedding_weight, text_weight }

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

embedding_weight: number

The weight of the embedding in the reciprocal ranking fusion.

text_weight: number

The weight of the text in the reciprocal ranking fusion.

ranker: optional "auto" or "default-2024-11-15"

The ranker to use for the file search.

One of the following:

"auto"

"default-2024-11-15"

score_threshold: optional 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.

Computer object { type }

A tool that controls a virtual computer. Learn more about the computer tool.

type: "computer"

The type of the computer tool. Always computer.

ComputerUsePreview object { display_height, display_width, environment, type }

A tool that controls a virtual computer. Learn more about the computer tool.

display_height: number

The height of the computer display.

display_width: number

The width of the computer display.

environment: "windows" or "mac" or "linux" or 2 more

The type of computer environment to control.

One of the following:

"windows"

"mac"

"linux"

"ubuntu"

"browser"

type: "computer_use_preview"

The type of the computer use tool. Always computer_use_preview.

WebSearch object { type, external_web_access, filters, 2 more }

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

type: "web_search" or "web_search_2025_08_26"

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

One of the following:

"web_search"

"web_search_2025_08_26"

external_web_access: optional boolean

Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content.

filters: optional object { allowed_domains } or null

Filters for the search.

allowed_domains: optional array of string or null

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

Example: ["pubmed.ncbi.nlm.nih.gov"]

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { city, country, region, 2 more } or null

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

type: optional "approximate"

The type of location approximation. Always approximate.

Mcp object { server_label, type, allowed_callers, 9 more }

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

server_label: string

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

type: "mcp"

The type of the MCP tool. Always mcp.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

allowed_tools: optional array of string or object { read_only, tool_names } or null

List of allowed tool names or a filter object.

One of the following:

McpAllowedTools = array of string

A string array of allowed tool names

McpToolFilter object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

authorization: optional string

connector_id: optional "connector_dropbox" or "connector_gmail" or "connector_googlecalendar" or 5 more

Deprecated.

Identifier for service connectors, like those available in ChatGPT. One of server_url, connector_id, or tunnel_id must be provided. Learn more about service connectors here.

This field is deprecated for models released after September 1, 2026. Use server_url to connect to a remote MCP server, or tunnel_id to connect through a Secure MCP Tunnel.

Currently supported connector_id values are:

Dropbox: connector_dropbox
Gmail: connector_gmail
Google Calendar: connector_googlecalendar
Google Drive: connector_googledrive
Microsoft Teams: connector_microsoftteams
Outlook Calendar: connector_outlookcalendar
Outlook Email: connector_outlookemail
SharePoint: connector_sharepoint

One of the following:

"connector_dropbox"

"connector_gmail"

"connector_googlecalendar"

"connector_googledrive"

"connector_microsoftteams"

"connector_outlookcalendar"

"connector_outlookemail"

"connector_sharepoint"

defer_loading: optional boolean

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

headers: optional map[string] or null

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

require_approval: optional object { always, never } or "always" or "never" or null

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

One of the following:

McpToolApprovalFilter object { always, never }

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

always: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

never: optional object { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only: optional 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: optional array of string

List of allowed tool names.

McpToolApprovalSetting = "always" or "never"

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.

One of the following:

"always"

"never"

server_description: optional string

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

server_url: optional string

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

formaturi

tunnel_id: optional string

The Secure MCP Tunnel ID to use instead of a direct server URL. One of server_url, connector_id, or tunnel_id must be provided.

CodeInterpreter object { container, type, allowed_callers }

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

container: string or object { type, file_ids, memory_limit, network_policy }

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.

One of the following:

string

The container ID.

CodeInterpreterToolAuto object { type, file_ids, memory_limit, network_policy }

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

type: "auto"

Always auto.

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the code interpreter container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

type: "code_interpreter"

The type of the code interpreter tool. Always code_interpreter.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

The type of the tool. Always programmatic_tool_calling.

ImageGeneration object { type, action, background, 9 more }

A tool that generates images using the GPT image models.

type: "image_generation"

The type of the image generation tool. Always image_generation.

action: optional "generate" or "edit" or "auto"

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

One of the following:

"generate"

"edit"

"auto"

background: optional "transparent" or "opaque" or "auto"

One of the following:

"transparent"

"opaque"

"auto"

input_fidelity: optional "high" or "low" or null

One of the following:

"high"

"low"

input_image_mask: optional object { file_id, image_url }

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

file_id: optional string

File ID for the mask image.

image_url: optional string

Base64-encoded mask image.

model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

One of the following:

string

"gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5" or 6 more

One of the following:

"gpt-image-1"

"gpt-image-1-mini"

"gpt-image-1.5"

"gpt-image-2"

"gpt-image-2-2026-04-21"

"gpt-image-2.5-sunburst"

"gpt-image-2.5-sunburst-2026-09-08"

"gpt-image-2.5-flare"

"gpt-image-2.5-flare-2026-09-08"

moderation: optional "auto" or "low"

Moderation level for the generated image. Default: auto.

One of the following:

"auto"

"low"

output_compression: optional number

Compression level for the output image. Default: 100.

minimum0

maximum100

output_format: optional "png" or "webp" or "jpeg"

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

One of the following:

"png"

"webp"

"jpeg"

partial_images: optional number

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

minimum0

maximum3

quality: optional "low" or "medium" or "high" or 3 more

One of the following:

"low"

"medium"

"high"

"xhigh"

"max"

"auto"

size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

One of the following:

string

"1024x1024" or "1024x1536" or "1536x1024" or "auto"

One of the following:

"1024x1024"

"1024x1536"

"1536x1024"

"auto"

LocalShell object { type }

A tool that allows the model to execute shell commands in a local environment.

type: "local_shell"

The type of the local shell tool. Always local_shell.

Shell object { type, allowed_callers, environment }

A tool that allows the model to execute shell commands.

type: "shell"

The type of the shell tool. Always shell.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

environment: optional ContainerAuto { type, file_ids, memory_limit, 2 more } or LocalEnvironment { type, skills } or ContainerReference { container_id, type } or null

One of the following:

ContainerAuto object { type, file_ids, memory_limit, 2 more }

type: "container_auto"

Automatically creates a container for this request

file_ids: optional array of string

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

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional ContainerNetworkPolicyDisabled { type } or ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:

ContainerNetworkPolicyDisabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist object { allowed_domains, type, domain_secrets }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets: optional array of ContainerNetworkPolicyDomainSecret { domain, name, value }

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1

The name of the secret to inject for the domain.

minLength1

value: string

The secret value to inject for the domain.

minLength1

maxLength10485760

skills: optional array of SkillReference { skill_id, type, version } or InlineSkill { description, name, source, type }

An optional list of skills referenced by id or inline data.

One of the following:

SkillReference object { skill_id, type, version }

skill_id: string

The ID of the referenced skill.

minLength1

maxLength64

type: "skill_reference"

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

version: optional string

Optional skill version. Use a positive integer or 'latest'. Omit for default.

InlineSkill object { description, name, source, type }

description: string

The description of the skill.

The name of the skill.

source: InlineSkillSource { data, media_type, type }

Inline skill payload

type: "inline"

Defines an inline skill for this request.

LocalEnvironment object { type, skills }

type: "local"

Use a local computer environment.

skills: optional array of LocalSkill { description, name, path }

An optional list of skills.

description: string

The description of the skill.

The name of the skill.

path: string

The path to the directory containing the skill.

ContainerReference object { container_id, type }

container_id: string

The ID of the referenced container.

type: "container_reference"

References a container created with the /v1/containers endpoint

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

Namespace object { description, name, tools, type }

Groups function/custom tools under a shared namespace.

description: string

A description of the namespace shown to the model.

The namespace name used in tool calls (for example, crm).

minLength1

tools: array of object { name, type, allowed_callers, 6 more } or object { name, type, allowed_callers, 4 more }

The function/custom tools available inside this namespace.

One of the following:

Function object { name, type, allowed_callers, 6 more }

minLength1

maxLength128

type: "function"

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this function should be deferred and discovered via tool search.

description: optional string or null

output_schema: optional map[unknown] or null

A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs.

parameters: optional unknown or null

strict: optional boolean or null

Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise.

Custom object { name, type, allowed_callers, 4 more }

A custom tool that processes input using a specified format. Learn more about custom tools

The name of the custom tool, used to identify it in tool calls.

type: "custom"

The type of the custom tool. Always custom.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

async: optional boolean

Whether the tool response can be returned asynchronously versus immediately returned on next response creation.

defer_loading: optional boolean

Whether this tool should be deferred and discovered via tool search.

description: optional string

Optional description of the custom tool, used to provide more context.

format: optional CustomToolInputFormat

The input format for the custom tool. Default is unconstrained text.

type: "namespace"

The type of the tool. Always namespace.

ToolSearch object { type, description, execution, parameters }

Hosted or BYOT tool search configuration for deferred tools.

type: "tool_search"

The type of the tool. Always tool_search.

description: optional string or null

Description shown to the model for a client-executed tool search tool.

execution: optional "server" or "client"

Whether tool search is executed by the server or by the client.

One of the following:

"server"

"client"

parameters: optional unknown or null

Parameter schema for a client-executed tool search tool.

WebSearchPreview object { type, search_content_types, search_context_size, user_location }

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

type: "web_search_preview" or "web_search_preview_2025_03_11"

The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.

One of the following:

"web_search_preview"

"web_search_preview_2025_03_11"

search_content_types: optional array of "text" or "image"

One of the following:

"text"

"image"

search_context_size: optional "low" or "medium" or "high"

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.

One of the following:

"low"

"medium"

"high"

user_location: optional object { type, city, country, 2 more } or null

type: "approximate"

The type of location approximation. Always approximate.

city: optional string or null

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

country: optional string or null

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

region: optional string or null

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

timezone: optional string or null

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

ApplyPatch object { type, allowed_callers }

Allows the assistant to create, delete, or update files using unified diffs.

type: "apply_patch"

The type of the tool. Always apply_patch.

allowed_callers: optional array of "direct" or "programmatic" or null

The tool invocation context(s).

One of the following:

"direct"

"programmatic"

top_logprobs: optional number or null

An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.

minimum0

maximum20

top_p: optional number or null

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

minimum0

maximum1

truncation: optional "auto" or "disabled" or null

Deprecated.

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.

One of the following:

"auto"

"disabled"

user: optional string or null

Deprecated.

This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

response.steer

Queues user input to steer a response on this WebSocket connection. Input can contain text, images, and files. Steering is supported only for single-agent responses on models and execution modes that support steering. Responses bound to a conversation or using automatic compaction do not support steering.

A response.steer.accepted event acknowledges that the server owns the queued input, not that it has been applied. The successor's response.created event is the commit point. Input that cannot be committed is returned in response.steer.failed.

Steering may cause the active response to finish at a safe output boundary with response.incomplete and incomplete_details.reason set to steered, followed automatically by a successor response.created. Normal completion can also be followed by an automatic successor. Automatic successors inherit the previous response's settings and continue from it with the queued input.

If the response stops for client-owned tool output or approval, accepted steering input remains queued and response.steer.pending is emitted after response.completed. Fill the required_input stubs from that event with saved tool results or approval decisions, and send one explicit response.create per parent with the same previous_response_id and WebSocket lane. Do not rerun tools or resend accepted steering input. The queued input is prepended in submission order to that request's input, and the explicit request retains its own settings.

This event accepts only type, previous_response_id, and input. Do not send stream_id; the target response determines the WebSocket lane.

input: ResponseSteerInput

Input to queue for a continuation of the response. Uses the same string or input-item shape as response.create.input, with a non-empty array when supplying input items.

Steering accepts only messages with the user role. Each message may contain only type, role, and content, with content as a string or an array of input_text, input_image, and input_file parts. The optional type must be message. Other roles, tool outputs, and item types are not supported for steering.

previous_response_id: string

The ID of the response to steer on this WebSocket connection.

type: "response.steer"

The event discriminator. Always response.steer.

OBJECT

response.steer

{
  "type": "response.steer",
  "previous_response_id": "resp_123",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Prioritize the database rollout."
        }
      ]
    }
  ]
}

Server events (WebSocket only)

Events emitted only over a Responses API WebSocket connection.

response.steer.accepted

Emitted when steering input has been validated and queued. Acceptance means the server owns the input, not that it has been applied. The successor's response.created event is the commit point. If accepted input cannot be committed, response.steer.failed returns it with the same steering ID.

When the response stops for client-owned tool output or approval, the input remains queued and response.steer.pending is emitted after response.completed. Fill the pending event's required_input stubs with saved results and send one matching explicit response.create per parent. Do not resend accepted input while it is still queued.

sequence_number: number

The sequence number for this event.

steer: object { id, previous_response_id }

The accepted steering submission.

id: string

The ID assigned to the steering submission.

previous_response_id: string

The ID of the response being steered.

type: "response.steer.accepted"

The event discriminator. Always response.steer.accepted.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the target response's response.create event supplied a stream_id.

response.steer.pending

Emitted when accepted steering input remains queued after the target response completes. The server still owns the input. Do not resend it. The successor's response.created event is the commit point.

When reason is waiting_for_required_input, this event follows response.completed while the response waits for the tool results or approval decisions identified by required_input. Copy those stubs, fill their result fields using the ordinary response.create input schemas, and submit one continuation per parent with the same previous_response_id and WebSocket lane. Use saved results without rerunning tools. The queued steering input is prepended in submission order to the continuation's input. That explicit request retains its own settings.

This notification is emitted at most once per steering submission. Multiple submissions for the same parent can report the same required inputs; they do not each require a separate continuation.

reason: ResponseSteerPendingReason

An extensible enum describing why accepted steering input is still queued. Clients should handle unknown values because additional reasons may be introduced. Known values include:

waiting_for_required_input: The response is waiting for the tool results or approval decisions identified by required_input.

required_input: array of ResponseSteerRequiredInput

Input stubs identifying outstanding client-owned tool results or approval decisions. Each stub contains identifying fields only; the client supplies the result before including it in response.create.

One of the following:

FunctionCallOutput object { call_id, name, type }

Supply output using the function tool call output input schema.

call_id: string

type: "function_call_output"

CustomToolCallOutput object { call_id, type }

Supply output using the custom tool call output input schema. The original custom tool call supplies the tool's name.

call_id: string

type: "custom_tool_call_output"

ComputerCallOutput object { call_id, type }

Supply output using the computer tool call output input schema, including any required acknowledged_safety_checks.

call_id: string

type: "computer_call_output"

ShellCallOutput object { call_id, type }

Supply output using the shell tool call output input schema. Each output entry includes stdout, stderr, and outcome.

call_id: string

type: "shell_call_output"

ApplyPatchCallOutput object { call_id, type }

Supply status and optional output using the apply patch tool call output input schema.

call_id: string

type: "apply_patch_call_output"

ToolSearchOutput object { call_id, execution, type }

Supply tools using the tool search output input schema, retaining execution: "client".

call_id: string

execution: "client"

type: "tool_search_output"

McpApprovalResponse object { approval_request_id, type }

Supply approve using the MCP approval response input schema. An optional reason can be supplied when denying the request. The original approval request identifies the tool and server.

approval_request_id: string

type: "mcp_approval_response"

sequence_number: number

The sequence number for this event.

steer: object { id, previous_response_id }

The steering submission that remains queued.

id: string

The ID assigned to the steering submission.

previous_response_id: string

The ID of the response being steered.

type: "response.steer.pending"

The event discriminator. Always response.steer.pending.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the target response's response.create event supplied a stream_id.

OBJECT

response.steer.pending

{
  "type": "response.steer.pending",
  "sequence_number": 10,
  "steer": {
    "id": "steer_456",
    "previous_response_id": "resp_123"
  },
  "reason": "waiting_for_required_input",
  "required_input": [
    {
      "type": "function_call_output",
      "call_id": "call_789",
      "name": "lookup"
    }
  ]
}

response.steer.failed

Emitted when steering input is rejected or cannot be committed to a successor response. Returns the original, uncommitted input so the client can carry it into response.create when appropriate. Invalid input must be corrected before retrying.

Failures after acceptance include the same steering ID. Failures before an ID is allocated omit steer.id. A lost connection or missing acknowledgement leaves the outcome unknown; it is not proof that the input was rejected.

error: object { code, message, type }

Information about why the input could not be committed.

code: ResponseSteerErrorCode

A machine-readable steering error code. Clients should handle unknown values because additional codes may be introduced. Known values include:

response_not_found: The target response is not available on this connection.
invalid_input: The event or input failed validation.
steering_not_supported: The model or response execution mode does not support steering.
too_many_pending_steers: Too much steering input is pending for the response.
response_already_completed: The response completed and is no longer accepting steering input.
response_not_active: The response is no longer accepting steering input.
successor_creation_failed: The successor response could not be created.

message: string

A human-readable description of the error.

type: "invalid_request_error"

The error type. Always invalid_request_error.

sequence_number: number

The sequence number for this event.

steer: object { input, previous_response_id, id }

The steering submission that could not be committed.

input: ResponseSteerInput

Input to queue for a continuation of the response. Uses the same string or input-item shape as response.create.input, with a non-empty array when supplying input items.

previous_response_id: string

The ID of the response that was targeted for steering.

id: optional string

The ID assigned to the steering submission, if one was allocated.

type: "response.steer.failed"

The event discriminator. Always response.steer.failed.

stream_id: optional string

The WebSocket lane that emitted this event, when the target response is available and its response.create event supplied a stream_id.

OBJECT

response.steer.failed

{
  "type": "response.steer.failed",
  "sequence_number": 5,
  "steer": {
    "id": "steer_456",
    "previous_response_id": "resp_123",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "Prioritize the database rollout."
          }
        ]
      }
    ]
  },
  "error": {
    "type": "invalid_request_error",
    "code": "successor_creation_failed",
    "message": "We couldn't start the next response. Send this steering input again with response.create."
  }
}

error

Emitted when an error occurs while processing a Responses WebSocket request.

error: object { code, message, param, 3 more }

Details about the error.

code: string or null

The error code that was emitted, if any.

message: string

The human-readable error message that was emitted.

param: string or null

The parameter name that was associated with the error, if any.

type: string

The error type that was emitted.

headers: optional map[string]

The response headers that were emitted with the error, if any.

misalignment: optional object { detailed_explanation, error_type, steer }

detailed_explanation: optional string

The public explanation for this block.

error_type: optional string or "potentially_unintended_data_transfer" or "potentially_unintended_data_access" or "potentially_unintended_destructive_activity" or "other"

An optional classification; clients must accept additional values.

One of the following:

string

SafetyAlertErrorType = "potentially_unintended_data_transfer" or "potentially_unintended_data_access" or "potentially_unintended_destructive_activity" or "other"

An optional classification; clients must accept additional values.

One of the following:

"potentially_unintended_data_transfer"

"potentially_unintended_data_access"

"potentially_unintended_destructive_activity"

"other"

steer: optional object { message }

An optional public continuation instruction.

message: string

The public continuation instruction.

type: "error"

The type of the event. Always error.

sequence_number: optional number

The sequence number of an error emitted by the response stream.

status: optional number

The HTTP status code associated with a WebSocket protocol error.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

error

{
  "type": "error",
  "status": 400,
  "stream_id": "agent_1",
  "error": {
    "type": "invalid_request_error",
    "code": "websocket_stream_limit_reached",
    "message": "This WebSocket connection has reached its stream limit.",
    "param": "stream_id"
  }
}

OBJECT

response.incomplete

{
  "type": "response.incomplete",
  "response": {
    "id": "resp_123",
    "object": "response",
    "access_programs": null,
    "created_at": 1740855869,
    "status": "incomplete",
    "completed_at": null,
    "error": null,
    "incomplete_details": {
      "reason": "max_output_tokens"
    },
    "instructions": null,
    "max_output_tokens": null,
    "model": "gpt-6-astra",
    "output": [],
    "previous_response_id": null,
    "reasoning_effort": null,
    "store": false,
    "temperature": 1,
    "text": {
      "format": {
        "type": "text"
      }
    },
    "tool_choice": "auto",
    "tools": [],
    "top_p": 1,
    "truncation": "disabled",
    "usage": null,
    "user": null,
    "metadata": {},
    "parallel_tool_calls": true
  },
  "sequence_number": 1
}

response.output_item.added

Emitted when a new output item is added.

item: ResponseOutputItem

The output item that was added. For reasoning items, encrypted_content may be incomplete while the item is in progress. Use the reasoning item from the corresponding response.output_item.done event when passing it as input to a subsequent request.

output_index: number

The index of the output item that was added.

sequence_number: number

The sequence number of this event.

type: "response.output_item.added"

The type of the event. Always response.output_item.added.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.output_item.added

{
  "type": "response.output_item.added",
  "output_index": 0,
  "item": {
    "id": "msg_123",
    "status": "in_progress",
    "type": "message",
    "role": "assistant",
    "content": []
  },
  "sequence_number": 1
}

response.output_item.done

Emitted when an output item is marked done.

item: ResponseOutputItem

The output item that was marked done.

output_index: number

The index of the output item that was marked done.

sequence_number: number

The sequence number of this event.

type: "response.output_item.done"

The type of the event. Always response.output_item.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.output_item.done

{
  "type": "response.output_item.done",
  "output_index": 0,
  "item": {
    "id": "msg_123",
    "status": "completed",
    "type": "message",
    "role": "assistant",
    "content": [
      {
        "type": "output_text",
        "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.",
        "annotations": [],
        "logprobs": []
      }
    ]
  },
  "sequence_number": 1
}

response.content_part.added

Emitted when a new content part is added.

content_index: number

The index of the content part that was added.

item_id: string

The ID of the output item that the content part was added to.

output_index: number

The index of the output item that the content part was added to.

part: ResponseOutputText { annotations, logprobs, text, type } or ResponseOutputRefusal { refusal, type } or object { text, type }

The content part that was added.

One of the following:

ResponseOutputText object { annotations, logprobs, text, type }

A text output from the model.

The annotations of the text output.

One of the following:

FileCitation object { file_id, filename, index, type }

A citation to a file.

file_id: string

The ID of the file.

filename: string

The filename of the file cited.

index: number

The index in the output text at which to insert the file citation.

type: "file_citation"

The type of the file citation. Always file_citation.

URLCitation object { end_index, start_index, title, 2 more }

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

end_index: number

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

start_index: number

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

title: string

The title of the web resource.

type: "url_citation"

The type of the URL citation. Always url_citation.

url: string

The URL of the web resource.

formaturi

ContainerFileCitation object { container_id, end_index, file_id, 3 more }

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

container_id: string

The ID of the container file.

end_index: number

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

file_id: string

The ID of the file.

filename: string

The filename of the container file cited.

start_index: number

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

type: "container_file_citation"

The type of the container file citation. Always container_file_citation.

FilePath object { file_id, index, type }

A path to a file.

file_id: string

The ID of the file.

index: number

The index of the file in the list of files.

type: "file_path"

The type of the file path. Always file_path.

logprobs: array of object { token, bytes, logprob, top_logprobs }

token: string

bytes: array of number

logprob: number

top_logprobs: array of object { token, bytes, logprob }

token: string

bytes: array of number

logprob: number

text: string

The text output from the model.

type: "output_text"

The type of the output text. Always output_text.

ResponseOutputRefusal object { refusal, type }

A refusal from the model.

refusal: string

The refusal explanation from the model.

type: "refusal"

The type of the refusal. Always refusal.

ReasoningText object { text, type }

Reasoning text from the model.

text: string

The reasoning text from the model.

type: "reasoning_text"

The type of the reasoning text. Always reasoning_text.

sequence_number: number

The sequence number of this event.

type: "response.content_part.added"

The type of the event. Always response.content_part.added.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.content_part.added

{
  "type": "response.content_part.added",
  "item_id": "msg_123",
  "output_index": 0,
  "content_index": 0,
  "part": {
    "type": "output_text",
    "text": "",
    "annotations": [],
    "logprobs": []
  },
  "sequence_number": 1
}

response.content_part.done

Emitted when a content part is done.

content_index: number

The index of the content part that is done.

item_id: string

The ID of the output item that the content part was added to.

output_index: number

The index of the output item that the content part was added to.

part: ResponseOutputText { annotations, logprobs, text, type } or ResponseOutputRefusal { refusal, type } or object { text, type }

The content part that is done.

One of the following:

ResponseOutputText object { annotations, logprobs, text, type }

A text output from the model.

The annotations of the text output.

One of the following:

FileCitation object { file_id, filename, index, type }

A citation to a file.

file_id: string

The ID of the file.

filename: string

The filename of the file cited.

index: number

The index in the output text at which to insert the file citation.

type: "file_citation"

The type of the file citation. Always file_citation.

URLCitation object { end_index, start_index, title, 2 more }

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

end_index: number

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

start_index: number

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

title: string

The title of the web resource.

type: "url_citation"

The type of the URL citation. Always url_citation.

url: string

The URL of the web resource.

formaturi

ContainerFileCitation object { container_id, end_index, file_id, 3 more }

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

container_id: string

The ID of the container file.

end_index: number

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

file_id: string

The ID of the file.

filename: string

The filename of the container file cited.

start_index: number

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

type: "container_file_citation"

The type of the container file citation. Always container_file_citation.

FilePath object { file_id, index, type }

A path to a file.

file_id: string

The ID of the file.

index: number

The index of the file in the list of files.

type: "file_path"

The type of the file path. Always file_path.

logprobs: array of object { token, bytes, logprob, top_logprobs }

token: string

bytes: array of number

logprob: number

top_logprobs: array of object { token, bytes, logprob }

token: string

bytes: array of number

logprob: number

text: string

The text output from the model.

type: "output_text"

The type of the output text. Always output_text.

ResponseOutputRefusal object { refusal, type }

A refusal from the model.

refusal: string

The refusal explanation from the model.

type: "refusal"

The type of the refusal. Always refusal.

ReasoningText object { text, type }

Reasoning text from the model.

text: string

The reasoning text from the model.

type: "reasoning_text"

The type of the reasoning text. Always reasoning_text.

sequence_number: number

The sequence number of this event.

type: "response.content_part.done"

The type of the event. Always response.content_part.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.content_part.done

{
  "type": "response.content_part.done",
  "item_id": "msg_123",
  "output_index": 0,
  "content_index": 0,
  "sequence_number": 1,
  "part": {
    "type": "output_text",
    "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.",
    "annotations": [],
    "logprobs": []
  }
}

response.output_text.delta

Emitted when there is an additional text delta.

content_index: number

The index of the content part that the text delta was added to.

delta: string

The text delta that was added.

item_id: string

The ID of the output item that the text delta was added to.

logprobs: array of object { token, logprob, top_logprobs }

The log probabilities of the tokens in the delta.

token: string

A possible text token.

logprob: number

The log probability of this token.

top_logprobs: optional array of object { token, logprob }

The log probabilities of up to 20 of the most likely tokens.

token: optional string

A possible text token.

logprob: optional number

The log probability of this token.

output_index: number

The index of the output item that the text delta was added to.

sequence_number: number

The sequence number for this event.

type: "response.output_text.delta"

The type of the event. Always response.output_text.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.output_text.delta

{
  "type": "response.output_text.delta",
  "item_id": "msg_123",
  "output_index": 0,
  "content_index": 0,
  "delta": "In",
  "sequence_number": 1,
  "logprobs": []
}

response.output_text.done

Emitted when text content is finalized.

content_index: number

The index of the content part that the text content is finalized.

item_id: string

The ID of the output item that the text content is finalized.

logprobs: array of object { token, logprob, top_logprobs }

The log probabilities of the tokens in the delta.

token: string

A possible text token.

logprob: number

The log probability of this token.

top_logprobs: optional array of object { token, logprob }

The log probabilities of up to 20 of the most likely tokens.

token: optional string

A possible text token.

logprob: optional number

The log probability of this token.

output_index: number

The index of the output item that the text content is finalized.

sequence_number: number

The sequence number for this event.

text: string

The text content that is finalized.

type: "response.output_text.done"

The type of the event. Always response.output_text.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.output_text.done

{
  "type": "response.output_text.done",
  "item_id": "msg_123",
  "output_index": 0,
  "content_index": 0,
  "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.",
  "sequence_number": 1,
  "logprobs": []
}

response.refusal.delta

Emitted when there is a partial refusal text.

content_index: number

The index of the content part that the refusal text is added to.

delta: string

The refusal text that is added.

item_id: string

The ID of the output item that the refusal text is added to.

output_index: number

The index of the output item that the refusal text is added to.

sequence_number: number

The sequence number of this event.

type: "response.refusal.delta"

The type of the event. Always response.refusal.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.refusal.done

Emitted when refusal text is finalized.

content_index: number

The index of the content part that the refusal text is finalized.

item_id: string

The ID of the output item that the refusal text is finalized.

output_index: number

The index of the output item that the refusal text is finalized.

refusal: string

The refusal text that is finalized.

sequence_number: number

The sequence number of this event.

type: "response.refusal.done"

The type of the event. Always response.refusal.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.function_call_arguments.delta

Emitted when there is a partial function-call arguments delta.

delta: string

The function-call arguments delta that is added.

item_id: string

The ID of the output item that the function-call arguments delta is added to.

output_index: number

The index of the output item that the function-call arguments delta is added to.

sequence_number: number

The sequence number of this event.

type: "response.function_call_arguments.delta"

The type of the event. Always response.function_call_arguments.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.function_call_arguments.done

Emitted when function-call arguments are finalized.

arguments: string

The function-call arguments.

item_id: string

The ID of the item.

output_index: number

The index of the output item.

sequence_number: number

The sequence number of this event.

type: "response.function_call_arguments.done"

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.function_call_arguments.done

{
  "type": "response.function_call_arguments.done",
  "item_id": "item-abc",
  "output_index": 1,
  "arguments": "{ \"arg\": 123 }",
  "sequence_number": 1
}

response.file_search_call.in_progress

Emitted when a file search call is initiated.

item_id: string

The ID of the output item that the file search call is initiated.

output_index: number

The index of the output item that the file search call is initiated.

sequence_number: number

The sequence number of this event.

type: "response.file_search_call.in_progress"

The type of the event. Always response.file_search_call.in_progress.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.file_search_call.searching

Emitted when a file search is currently searching.

item_id: string

The ID of the output item that the file search call is initiated.

output_index: number

The index of the output item that the file search call is searching.

sequence_number: number

The sequence number of this event.

type: "response.file_search_call.searching"

The type of the event. Always response.file_search_call.searching.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.file_search_call.completed

Emitted when a file search call is completed (results found).

item_id: string

The ID of the output item that the file search call is initiated.

output_index: number

The index of the output item that the file search call is initiated.

sequence_number: number

The sequence number of this event.

type: "response.file_search_call.completed"

The type of the event. Always response.file_search_call.completed.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.web_search_call.in_progress

Emitted when a web search call is initiated.

item_id: string

Unique ID for the output item associated with the web search call.

output_index: number

The index of the output item that the web search call is associated with.

sequence_number: number

The sequence number of the web search call being processed.

type: "response.web_search_call.in_progress"

The type of the event. Always response.web_search_call.in_progress.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.web_search_call.searching

Emitted when a web search call is executing.

item_id: string

Unique ID for the output item associated with the web search call.

output_index: number

The index of the output item that the web search call is associated with.

sequence_number: number

The sequence number of the web search call being processed.

type: "response.web_search_call.searching"

The type of the event. Always response.web_search_call.searching.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.web_search_call.completed

Emitted when a web search call is completed.

item_id: string

Unique ID for the output item associated with the web search call.

output_index: number

The index of the output item that the web search call is associated with.

sequence_number: number

The sequence number of the web search call being processed.

type: "response.web_search_call.completed"

The type of the event. Always response.web_search_call.completed.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.reasoning_summary_part.added

Emitted when a new reasoning summary part is added.

item_id: string

The ID of the item this summary part is associated with.

output_index: number

The index of the output item this summary part is associated with.

part: object { text, type }

The summary part that was added.

text: string

The text of the summary part.

type: "summary_text"

The type of the summary part. Always summary_text.

sequence_number: number

The sequence number of this event.

summary_index: number

The index of the summary part within the reasoning summary.

type: "response.reasoning_summary_part.added"

The type of the event. Always response.reasoning_summary_part.added.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.reasoning_summary_part.added

{
  "type": "response.reasoning_summary_part.added",
  "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476",
  "output_index": 0,
  "summary_index": 0,
  "part": {
    "type": "summary_text",
    "text": ""
  },
  "sequence_number": 1
}

response.reasoning_summary_part.done

Emitted when a reasoning summary part is completed.

item_id: string

The ID of the item this summary part is associated with.

output_index: number

The index of the output item this summary part is associated with.

part: object { text, type }

The completed summary part.

text: string

The text of the summary part.

type: "summary_text"

The type of the summary part. Always summary_text.

sequence_number: number

The sequence number of this event.

summary_index: number

The index of the summary part within the reasoning summary.

type: "response.reasoning_summary_part.done"

The type of the event. Always response.reasoning_summary_part.done.

status: optional "incomplete"

The completion status of the summary part. Omitted when the part completed normally and set to incomplete when generation was interrupted.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.reasoning_summary_part.done

{
  "type": "response.reasoning_summary_part.done",
  "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476",
  "output_index": 0,
  "summary_index": 0,
  "part": {
    "type": "summary_text",
    "text": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!"
  },
  "sequence_number": 1
}

response.reasoning_summary_text.delta

Emitted when a delta is added to a reasoning summary text.

delta: string

The text delta that was added to the summary.

item_id: string

The ID of the item this summary text delta is associated with.

output_index: number

The index of the output item this summary text delta is associated with.

sequence_number: number

The sequence number of this event.

summary_index: number

The index of the summary part within the reasoning summary.

type: "response.reasoning_summary_text.delta"

The type of the event. Always response.reasoning_summary_text.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.reasoning_summary_text.delta

{
  "type": "response.reasoning_summary_text.delta",
  "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476",
  "output_index": 0,
  "summary_index": 0,
  "delta": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!",
  "sequence_number": 1
}

response.reasoning_summary_text.done

Emitted when a reasoning summary text is completed.

item_id: string

The ID of the item this summary text is associated with.

output_index: number

The index of the output item this summary text is associated with.

sequence_number: number

The sequence number of this event.

summary_index: number

The index of the summary part within the reasoning summary.

text: string

The full text of the completed reasoning summary.

type: "response.reasoning_summary_text.done"

The type of the event. Always response.reasoning_summary_text.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.reasoning_summary_text.done

{
  "type": "response.reasoning_summary_text.done",
  "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476",
  "output_index": 0,
  "summary_index": 0,
  "text": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!",
  "sequence_number": 1
}

response.reasoning_text.delta

Emitted when a delta is added to a reasoning text.

content_index: number

The index of the reasoning content part this delta is associated with.

delta: string

The text delta that was added to the reasoning content.

item_id: string

The ID of the item this reasoning text delta is associated with.

output_index: number

The index of the output item this reasoning text delta is associated with.

sequence_number: number

The sequence number of this event.

type: "response.reasoning_text.delta"

The type of the event. Always response.reasoning_text.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.reasoning_text.done

Emitted when a reasoning text is completed.

content_index: number

The index of the reasoning content part.

item_id: string

The ID of the item this reasoning text is associated with.

output_index: number

The index of the output item this reasoning text is associated with.

sequence_number: number

The sequence number of this event.

text: string

The full text of the completed reasoning content.

type: "response.reasoning_text.done"

The type of the event. Always response.reasoning_text.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.reasoning_text.done

{
  "type": "response.reasoning_text.done",
  "item_id": "rs_123",
  "output_index": 0,
  "content_index": 0,
  "text": "The user is asking...",
  "sequence_number": 4
}

response.image_generation_call.completed

Emitted when an image generation tool call has completed and the final image is available.

item_id: string

The unique identifier of the image generation item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of this event.

type: "response.image_generation_call.completed"

The type of the event. Always 'response.image_generation_call.completed'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.image_generation_call.generating

Emitted when an image generation tool call is actively generating an image (intermediate state).

item_id: string

The unique identifier of the image generation item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of the image generation item being processed.

type: "response.image_generation_call.generating"

The type of the event. Always 'response.image_generation_call.generating'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.image_generation_call.in_progress

Emitted when an image generation tool call is in progress.

item_id: string

The unique identifier of the image generation item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of the image generation item being processed.

type: "response.image_generation_call.in_progress"

The type of the event. Always 'response.image_generation_call.in_progress'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.image_generation_call.partial_image

Emitted when a partial image is available during image generation streaming.

item_id: string

The unique identifier of the image generation item being processed.

output_index: number

The index of the output item in the response's output array.

partial_image_b64: string

Base64-encoded partial image data, suitable for rendering as an image.

partial_image_index: number

0-based index for the partial image (backend is 1-based, but this is 0-based for the user).

sequence_number: number

The sequence number of the image generation item being processed.

type: "response.image_generation_call.partial_image"

The type of the event. Always 'response.image_generation_call.partial_image'.

background: optional string

The background setting that was used.

output_format: optional string

The output format that was used.

quality: optional string

The image quality that was used.

size: optional string

The image size that was used.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.image_generation_call.partial_image

{
  "type": "response.image_generation_call.partial_image",
  "output_index": 0,
  "item_id": "item-123",
  "sequence_number": 0,
  "partial_image_index": 0,
  "partial_image_b64": "..."
}

response.mcp_call_arguments.delta

Emitted when there is a delta (partial update) to the arguments of an MCP tool call.

delta: string

A JSON string containing the partial update to the arguments for the MCP tool call.

item_id: string

The unique identifier of the MCP tool call item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of this event.

type: "response.mcp_call_arguments.delta"

The type of the event. Always 'response.mcp_call_arguments.delta'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.mcp_call_arguments.done

Emitted when the arguments for an MCP tool call are finalized.

arguments: string

A JSON string containing the finalized arguments for the MCP tool call.

item_id: string

The unique identifier of the MCP tool call item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of this event.

type: "response.mcp_call_arguments.done"

The type of the event. Always 'response.mcp_call_arguments.done'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.mcp_call_arguments.done

{
  "type": "response.mcp_call_arguments.done",
  "output_index": 0,
  "item_id": "item-abc",
  "arguments": "{\"arg1\": \"value1\", \"arg2\": \"value2\"}",
  "sequence_number": 1
}

response.mcp_call.completed

Emitted when an MCP tool call has completed successfully.

item_id: string

The ID of the MCP tool call item that completed.

output_index: number

The index of the output item that completed.

sequence_number: number

The sequence number of this event.

type: "response.mcp_call.completed"

The type of the event. Always 'response.mcp_call.completed'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.mcp_call.failed

Emitted when an MCP tool call has failed.

item_id: string

The ID of the MCP tool call item that failed.

output_index: number

The index of the output item that failed.

sequence_number: number

The sequence number of this event.

type: "response.mcp_call.failed"

The type of the event. Always 'response.mcp_call.failed'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.mcp_call.in_progress

Emitted when an MCP tool call is in progress.

item_id: string

The unique identifier of the MCP tool call item being processed.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of this event.

type: "response.mcp_call.in_progress"

The type of the event. Always 'response.mcp_call.in_progress'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.mcp_list_tools.completed

Emitted when the list of available MCP tools has been successfully retrieved.

item_id: string

The ID of the MCP tool call item that produced this output.

output_index: number

The index of the output item that was processed.

sequence_number: number

The sequence number of this event.

type: "response.mcp_list_tools.completed"

The type of the event. Always 'response.mcp_list_tools.completed'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.mcp_list_tools.completed

{
  "type": "response.mcp_list_tools.completed",
  "sequence_number": 1,
  "output_index": 0,
  "item_id": "mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90"
}

response.mcp_list_tools.failed

Emitted when the attempt to list available MCP tools has failed.

item_id: string

The ID of the MCP tool call item that failed.

output_index: number

The index of the output item that failed.

sequence_number: number

The sequence number of this event.

type: "response.mcp_list_tools.failed"

The type of the event. Always 'response.mcp_list_tools.failed'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.mcp_list_tools.in_progress

Emitted when the system is in the process of retrieving the list of available MCP tools.

item_id: string

The ID of the MCP tool call item that is being processed.

output_index: number

The index of the output item that is being processed.

sequence_number: number

The sequence number of this event.

type: "response.mcp_list_tools.in_progress"

The type of the event. Always 'response.mcp_list_tools.in_progress'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.mcp_list_tools.in_progress

{
  "type": "response.mcp_list_tools.in_progress",
  "sequence_number": 1,
  "output_index": 0,
  "item_id": "mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90"
}

response.code_interpreter_call.in_progress

Emitted when a code interpreter call is in progress.

item_id: string

The unique identifier of the code interpreter tool call item.

output_index: number

The index of the output item in the response for which the code interpreter call is in progress.

sequence_number: number

The sequence number of this event, used to order streaming events.

type: "response.code_interpreter_call.in_progress"

The type of the event. Always response.code_interpreter_call.in_progress.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.code_interpreter_call.interpreting

Emitted when the code interpreter is actively interpreting the code snippet.

item_id: string

The unique identifier of the code interpreter tool call item.

output_index: number

The index of the output item in the response for which the code interpreter is interpreting code.

sequence_number: number

The sequence number of this event, used to order streaming events.

type: "response.code_interpreter_call.interpreting"

The type of the event. Always response.code_interpreter_call.interpreting.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.code_interpreter_call.completed

Emitted when the code interpreter call is completed.

item_id: string

The unique identifier of the code interpreter tool call item.

output_index: number

The index of the output item in the response for which the code interpreter call is completed.

sequence_number: number

The sequence number of this event, used to order streaming events.

type: "response.code_interpreter_call.completed"

The type of the event. Always response.code_interpreter_call.completed.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.code_interpreter_call_code.delta

Emitted when a partial code snippet is streamed by the code interpreter.

delta: string

The partial code snippet being streamed by the code interpreter.

item_id: string

The unique identifier of the code interpreter tool call item.

output_index: number

The index of the output item in the response for which the code is being streamed.

sequence_number: number

The sequence number of this event, used to order streaming events.

type: "response.code_interpreter_call_code.delta"

The type of the event. Always response.code_interpreter_call_code.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.code_interpreter_call_code.delta

{
  "type": "response.code_interpreter_call_code.delta",
  "output_index": 0,
  "item_id": "ci_12345",
  "delta": "print('Hello, world')",
  "sequence_number": 1
}

response.code_interpreter_call_code.done

Emitted when the code snippet is finalized by the code interpreter.

code: string

The final code snippet output by the code interpreter.

item_id: string

The unique identifier of the code interpreter tool call item.

output_index: number

The index of the output item in the response for which the code is finalized.

sequence_number: number

The sequence number of this event, used to order streaming events.

type: "response.code_interpreter_call_code.done"

The type of the event. Always response.code_interpreter_call_code.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.output_text.annotation.added

Emitted when an annotation is added to output text content.

annotation: object { file_id, filename, index, type } or object { end_index, start_index, title, 2 more } or object { container_id, end_index, file_id, 3 more } or object { file_id, index, type } or null

The annotation object being added. (See annotation schema for details.)

One of the following:

FileCitation object { file_id, filename, index, type }

A citation to a file.

file_id: string

The ID of the file.

filename: string

The filename of the file cited.

index: number

The index in the output text at which to insert the file citation.

type: "file_citation"

The type of the file citation. Always file_citation.

URLCitation object { end_index, start_index, title, 2 more }

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

end_index: number

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

start_index: number

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

title: string

The title of the web resource.

type: "url_citation"

The type of the URL citation. Always url_citation.

url: string

The URL of the web resource.

formaturi

ContainerFileCitation object { container_id, end_index, file_id, 3 more }

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

container_id: string

The ID of the container file.

end_index: number

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

file_id: string

The ID of the file.

filename: string

The filename of the container file cited.

start_index: number

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

type: "container_file_citation"

The type of the container file citation. Always container_file_citation.

FilePath object { file_id, index, type }

A path to a file.

file_id: string

The ID of the file.

index: number

The index of the file in the list of files.

type: "file_path"

The type of the file path. Always file_path.

annotation_index: number

The index of the annotation within the content part.

content_index: number

The index of the content part within the output item.

item_id: string

The unique identifier of the item to which the annotation is being added.

output_index: number

The index of the output item in the response's output array.

sequence_number: number

The sequence number of this event.

type: "response.output_text.annotation.added"

The type of the event. Always 'response.output_text.annotation.added'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.output_text.annotation.added

{
  "type": "response.output_text.annotation.added",
  "item_id": "item-abc",
  "output_index": 0,
  "content_index": 0,
  "annotation_index": 0,
  "annotation": {
    "type": "file_citation",
    "file_id": "file-abc",
    "index": 0,
    "filename": "example.txt"
  },
  "sequence_number": 1
}

response.queued

Emitted when a response is queued and waiting to be processed.

response: Response { id, access_programs, created_at, 34 more }

The full response object that is queued.

sequence_number: number

The sequence number for this event.

type: "response.queued"

The type of the event. Always 'response.queued'.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.queued

{
  "type": "response.queued",
  "response": {
    "id": "resp_123",
    "object": "response",
    "access_programs": null,
    "created_at": 1609459200,
    "status": "queued",
    "error": null,
    "incomplete_details": null,
    "instructions": null,
    "model": "gpt-6-astra",
    "output": [],
    "parallel_tool_calls": true,
    "temperature": 1,
    "tool_choice": "auto",
    "tools": [],
    "top_p": 1,
    "metadata": {}
  },
  "sequence_number": 1
}

response.custom_tool_call_input.delta

Event representing a delta (partial update) to the input of a custom tool call.

delta: string

The incremental input data (delta) for the custom tool call.

item_id: string

Unique identifier for the API item associated with this event.

output_index: number

The index of the output this delta applies to.

sequence_number: number

The sequence number of this event.

type: "response.custom_tool_call_input.delta"

The event type identifier.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.custom_tool_call_input.delta

{
  "type": "response.custom_tool_call_input.delta",
  "sequence_number": 1,
  "output_index": 0,
  "item_id": "ctc_1234567890abcdef",
  "delta": "partial input text"
}

response.custom_tool_call_input.done

Event indicating that input for a custom tool call is complete.

input: string

The complete input data for the custom tool call.

item_id: string

Unique identifier for the API item associated with this event.

output_index: number

The index of the output this event applies to.

sequence_number: number

The sequence number of this event.

type: "response.custom_tool_call_input.done"

The event type identifier.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.custom_tool_call_input.done

{
  "type": "response.custom_tool_call_input.done",
  "sequence_number": 1,
  "output_index": 0,
  "item_id": "ctc_1234567890abcdef",
  "input": "final complete input text"
}

response.audio.delta

Emitted when there is a partial audio response.

delta: string

A chunk of Base64 encoded response audio bytes.

sequence_number: number

A sequence number for this chunk of the stream response.

type: "response.audio.delta"

The type of the event. Always response.audio.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.audio.done

Emitted when the audio response is complete.

sequence_number: number

The sequence number of the delta.

type: "response.audio.done"

The type of the event. Always response.audio.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.audio.transcript.delta

Emitted when there is a partial transcript of audio.

delta: string

The partial transcript of the audio response.

sequence_number: number

The sequence number of this event.

type: "response.audio.transcript.delta"

The type of the event. Always response.audio.transcript.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.audio.transcript.done

Emitted when the full audio transcript is completed.

sequence_number: number

The sequence number of this event.

type: "response.audio.transcript.done"

The type of the event. Always response.audio.transcript.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.compaction.compacting

Emitted when new summary content is sampled for a compaction trigger. Contains no summary content.

item_id: string

The ID of the compaction output item.

output_index: number

The index of the compaction output item.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.compaction.compacting"

The type of the event, always response.compaction.compacting.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.shell_call_command.added

A streaming event that indicated a shell command was added to a tool call.

command: string

The shell command that was added.

command_index: number

The index of the shell command that was added.

output_index: number

The index of the output item that was updated.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.shell_call_command.added"

The type of the event, always response.shell_call_command.added.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.shell_call_command.delta

A streaming event that indicated a shell command was incrementally updated.

command_index: number

The index of the shell command that was updated.

delta: string

The shell command delta that was appended.

output_index: number

The index of the output item that was updated.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.shell_call_command.delta"

The type of the event, always response.shell_call_command.delta.

obfuscation: optional string

An obfuscation string that was added to pad the event payload.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.shell_call_command.delta

{
  "type": "response.shell_call_command.delta",
  "sequence_number": 0,
  "output_index": 0,
  "command_index": 0,
  "delta": "delta",
  "obfuscation": "obfuscation"
}

response.shell_call_command.done

A streaming event that indicated a shell command was completed.

command: string

The final shell command that was emitted.

command_index: number

The index of the shell command that was completed.

output_index: number

The index of the output item that was updated.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.shell_call_command.done"

The type of the event, always response.shell_call_command.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

response.shell_call_output_content.delta

A streaming event that indicated shell call output was incrementally added.

command_index: number

The index of the shell command that produced output.

delta: object { stderr, stdout }

The stdout/stderr delta that was emitted.

stderr: optional string

The stderr delta that was emitted.

stdout: optional string

The stdout delta that was emitted.

item_id: string

The ID of the output item that was updated.

output_index: number

The index of the output item that was updated.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.shell_call_output_content.delta"

The type of the event, always response.shell_call_output_content.delta.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.shell_call_output_content.delta

{
  "type": "response.shell_call_output_content.delta",
  "sequence_number": 0,
  "item_id": "item_id",
  "output_index": 0,
  "command_index": 0,
  "delta": {
    "stdout": "stdout",
    "stderr": "stderr"
  }
}

response.shell_call_output_content.done

A streaming event that indicated shell call output was completed.

command_index: number

The index of the shell command that produced output.

item_id: string

The ID of the output item that was updated.

output: array of object { outcome, stderr, stdout, created_by }

The output contents emitted for the shell command.

outcome: object { type } or object { exit_code, type }

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

One of the following:

Timeout object { type }

Indicates that the shell call exceeded its configured time limit.

type: "timeout"

The outcome type. Always timeout.

Exit object { exit_code, type }

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

exit_code: number

Exit code from the shell process.

type: "exit"

The outcome type. Always exit.

stderr: string

The standard error output that was captured.

stdout: string

The standard output that was captured.

created_by: optional string

The identifier of the actor that created the item.

output_index: number

The index of the output item that was updated.

sequence_number: number

The sequence number of the event that was emitted.

type: "response.shell_call_output_content.done"

The type of the event, always response.shell_call_output_content.done.

stream_id: optional string

The WebSocket lane that emitted this event. This field is present when the originating response.create event supplied a stream_id.

OBJECT

response.shell_call_output_content.done

{
  "type": "response.shell_call_output_content.done",
  "sequence_number": 0,
  "item_id": "item_id",
  "output_index": 0,
  "command_index": 0,
  "output": [
    {
      "stdout": "stdout",
      "stderr": "stderr",
      "outcome": {
        "type": "timeout"
      },
      "created_by": "created_by"
    }
  ]
}

Suggested