data: Array<ResponseItem>

A list of items used to generate this response.

One of the following:
ResponseInputMessageItem { id, content, role, 2 more }
id: string

The unique ID of the message input.

content: ResponseInputMessageContentList { , , }

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

role: "user" | "system" | "developer"

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

One of the following:
"user"
"system"
"developer"
type: "message"

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

status?: "in_progress" | "completed" | "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"
ResponseOutputMessage { id, content, role, 3 more }

An output message from the model.

id: string

The unique ID of the output message.

content: Array<ResponseOutputText { annotations, text, type, logprobs } | ResponseOutputRefusal { refusal, type } >

The content of the output message.

One of the following:
ResponseOutputText { annotations, text, type, logprobs }

A text output from the model.

annotations: Array<FileCitation { file_id, filename, index, type } | URLCitation { end_index, start_index, title, 2 more } | ContainerFileCitation { container_id, end_index, file_id, 3 more } | FilePath { file_id, index, type } >

The annotations of the text output.

One of the following:
FileCitation { 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 { 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 { 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 { 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.

text: string

The text output from the model.

type: "output_text"

The type of the output text. Always output_text.

logprobs?: Array<Logprob>
token: string
bytes: Array<number>
logprob: number
top_logprobs: Array<TopLogprob>
token: string
bytes: Array<number>
logprob: number
ResponseOutputRefusal { 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" | "completed" | "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?: "commentary" | "final_answer" | 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"
ResponseFileSearchToolCall { 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<string>

The queries used to search for files.

status: "in_progress" | "searching" | "completed" | 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?: Array<Result> | null

The results of the file search tool call.

attributes?: Record<string, string | number | boolean> | 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?: string

The unique ID of the file.

filename?: string

The name of the file.

score?: number

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

formatfloat
text?: string

The text that was retrieved from the file.

ResponseComputerToolCall { 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<PendingSafetyCheck>

The pending safety checks for the computer call.

id: string

The ID of the pending safety check.

code?: string | null

The type of the pending safety check.

message?: string | null

Details about the pending safety check.

status: "in_progress" | "completed" | "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?: Click { button, type, x, 2 more } | DoubleClick { keys, type, x, y } | Drag { path, type, keys } | 6 more

A click action.

One of the following:
Click { button, type, x, 2 more }

A click action.

button: "left" | "right" | "wheel" | 2 more

Indicates which mouse button was pressed during the click. One of left, right, wheel, back, or forward.

One of the following:
"left"
"right"
"wheel"
"back"
"forward"
type: "click"

Specifies the event type. For a click action, this property is always click.

x: number

The x-coordinate where the click occurred.

y: number

The y-coordinate where the click occurred.

keys?: Array<string> | null

The keys being held while clicking.

DoubleClick { keys, type, x, y }

A double click action.

keys: Array<string> | null

The keys being held while double-clicking.

type: "double_click"

Specifies the event type. For a double click action, this property is always set to double_click.

x: number

The x-coordinate where the double click occurred.

y: number

The y-coordinate where the double click occurred.

Drag { path, type, keys }

A drag action.

path: Array<Path>

An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg

[
  { x: 100, y: 200 },
  { x: 200, y: 300 }
]
x: number

The x-coordinate.

y: number

The y-coordinate.

type: "drag"

Specifies the event type. For a drag action, this property is always set to drag.

keys?: Array<string> | null

The keys being held while dragging the mouse.

Keypress { keys, type }

A collection of keypresses the model would like to perform.

keys: Array<string>

The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key.

type: "keypress"

Specifies the event type. For a keypress action, this property is always set to keypress.

Move { type, x, y, keys }

A mouse move action.

type: "move"

Specifies the event type. For a move action, this property is always set to move.

x: number

The x-coordinate to move to.

y: number

The y-coordinate to move to.

keys?: Array<string> | null

The keys being held while moving the mouse.

Screenshot { type }

A screenshot action.

type: "screenshot"

Specifies the event type. For a screenshot action, this property is always set to screenshot.

Scroll { scroll_x, scroll_y, type, 3 more }

A scroll action.

scroll_x: number

The horizontal scroll distance.

scroll_y: number

The vertical scroll distance.

type: "scroll"

Specifies the event type. For a scroll action, this property is always set to scroll.

x: number

The x-coordinate where the scroll occurred.

y: number

The y-coordinate where the scroll occurred.

keys?: Array<string> | null

The keys being held while scrolling.

Type { text, type }

An action to type in text.

text: string

The text to type.

type: "type"

Specifies the event type. For a type action, this property is always set to type.

Wait { type }

A wait action.

type: "wait"

Specifies the event type. For a wait action, this property is always set to wait.

actions?: ComputerActionList { , , , 6 more }

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

ResponseComputerToolCallOutputItem { id, call_id, output, 4 more }
id: string

The ID of the computer tool call output.

call_id: string

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

output: ResponseComputerToolCallOutputScreenshot { type, file_id, image_url }

A computer screenshot image used with the computer use tool.

status: "completed" | "incomplete" | "failed" | "in_progress"

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:
"completed"
"incomplete"
"failed"
"in_progress"
type: "computer_call_output"

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

acknowledged_safety_checks?: Array<AcknowledgedSafetyCheck>

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

id: string

The ID of the pending safety check.

code?: string | null

The type of the pending safety check.

message?: string | null

Details about the pending safety check.

created_by?: string

The identifier of the actor that created the item.

One of the following:
One of the following:
ResponseFunctionToolCallItem extends ResponseFunctionToolCall { arguments, call_id, name, 6 more } { id, status, created_by }

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

id: string

The unique ID of the function tool call.

status: "in_progress" | "completed" | "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"
created_by?: string

The identifier of the actor that created the item.

ResponseFunctionToolCallOutputItem { id, output, status, 6 more }
id: string

The unique ID of the function call tool output.

output: string | Array<ResponseInputText { text, type, prompt_cache_breakpoint } | ResponseInputImage { detail, type, file_id, 2 more } | ResponseInputFile { type, detail, file_data, 4 more } >

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

One of the following:
string
Array<ResponseInputText { text, type, prompt_cache_breakpoint } | ResponseInputImage { detail, type, file_id, 2 more } | ResponseInputFile { type, detail, file_data, 4 more } >
ResponseInputText { 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?: PromptCacheBreakpoint { 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 { 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?: string | null

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

image_url?: string | 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?: PromptCacheBreakpoint { 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 { 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?: "auto" | "low" | "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?: string

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

file_id?: string | null

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

file_url?: string

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

formaturi
filename?: string

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

prompt_cache_breakpoint?: PromptCacheBreakpoint { 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.

status: "in_progress" | "completed" | "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: "function_call_output"

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

call_id?: string

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

caller?: Direct { type } | Program { caller_id, type } | null

The execution context that produced this tool call.

One of the following:
Direct { type }
type: "direct"

The caller type. Always direct.

Program { 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.

created_by?: string

The identifier of the actor that created the item.

name?: string

The name of the tool that produced the output.

namespace?: string

The namespace of the tool that produced the output.

ResponseToolSearchCall { id, arguments, call_id, 4 more }
id: string

The unique ID of the tool search call item.

arguments: unknown

Arguments used for the tool search call.

call_id: string | null

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

execution: "server" | "client"

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

One of the following:
"server"
"client"
status: "in_progress" | "completed" | "incomplete"

The status of the tool search call item that was recorded.

One of the following:
"in_progress"
"completed"
"incomplete"
type: "tool_search_call"

The type of the item. Always tool_search_call.

created_by?: string

The identifier of the actor that created the item.

ResponseToolSearchOutputItem { id, call_id, execution, 4 more }
id: string

The unique ID of the tool search output item.

call_id: string | null

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

execution: "server" | "client"

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

One of the following:
"server"
"client"
status: "in_progress" | "completed" | "incomplete"

The status of the tool search output item that was recorded.

One of the following:
"in_progress"
"completed"
"incomplete"
tools: Array<Tool>

The loaded tool definitions returned by tool search.

One of the following:
FunctionTool { name, parameters, strict, 6 more }

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

name: string

The name of the function to call.

parameters: Record<string, unknown> | null

A JSON schema object describing the parameters of the function.

strict: boolean | null

Whether strict parameter validation is enforced for this function tool.

type: "function"

The type of the function tool. Always function.

allowed_callers?: Array<"direct" | "programmatic"> | null

The tool invocation context(s).

One of the following:
"direct"
"programmatic"
async?: boolean
defer_loading?: boolean

Whether this function is deferred and loaded via tool search.

description?: string | null

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

output_schema?: Record<string, unknown> | null

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

FileSearchTool { 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<string>

The IDs of the vector stores to search.

filters?: ComparisonFilter { key, type, value } | CompoundFilter { filters, type } | null

A filter to apply.

One of the following:
ComparisonFilter { 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" | "ne" | "gt" | 5 more

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

  • eq: equals
  • ne: not equal
  • gt: greater than
  • gte: greater than or equal
  • lt: less than
  • lte: less than or equal
  • in: in
  • nin: not in
One of the following:
"eq"
"ne"
"gt"
"gte"
"lt"
"lte"
"in"
"nin"
value: string | number | boolean | Array<string | number>

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

One of the following:
string
number
boolean
Array<string | number>
string
number
CompoundFilter { filters, type }

Combine multiple filters using and or or.

filters: Array<ComparisonFilter { key, type, value } | unknown>

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

One of the following:
ComparisonFilter { 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" | "ne" | "gt" | 5 more

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

  • eq: equals
  • ne: not equal
  • gt: greater than
  • gte: greater than or equal
  • lt: less than
  • lte: less than or equal
  • in: in
  • nin: not in
One of the following:
"eq"
"ne"
"gt"
"gte"
"lt"
"lte"
"in"
"nin"
value: string | number | boolean | Array<string | number>

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

One of the following:
string
number
boolean
Array<string | number>
string
number
unknown
type: "and" | "or"

Type of operation: and or or.

One of the following:
"and"
"or"
max_num_results?: number

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

ranking_options?: RankingOptions { hybrid_search, ranker, score_threshold }

Ranking options for search.

text_weight: number

The weight of the text in the reciprocal ranking fusion.

ranker?: "auto" | "default-2024-11-15"

The ranker to use for the file search.

One of the following:
"auto"
"default-2024-11-15"
score_threshold?: 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.

ComputerTool { type }

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

type: "computer"

The type of the computer tool. Always computer.

ComputerUsePreviewTool { 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" | "mac" | "linux" | 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.

WebSearchTool { 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" | "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?: 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?: Filters | null

Filters for the search.

allowed_domains?: Array<string> | 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?: "low" | "medium" | "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?: UserLocation | 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?: string | null

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

country?: string | null

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

region?: string | null

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

timezone?: string | null

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

type?: "approximate"

The type of location approximation. Always approximate.

Mcp { 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?: Array<"direct" | "programmatic"> | null

The tool invocation context(s).

One of the following:
"direct"
"programmatic"
allowed_tools?: Array<string> | McpToolFilter { read_only, tool_names } | null

List of allowed tool names or a filter object.

One of the following:
Array<string>
McpToolFilter { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only?: 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?: Array<string>

List of allowed tool names.

authorization?: 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?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 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?: boolean

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

headers?: Record<string, string> | null

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

require_approval?: McpToolApprovalFilter { always, never } | "always" | "never" | null

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

One of the following:
McpToolApprovalFilter { 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?: Always { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only?: 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?: Array<string>

List of allowed tool names.

never?: Never { read_only, tool_names }

A filter object to specify which tools are allowed.

read_only?: 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?: Array<string>

List of allowed tool names.

"always" | "never"
"always"
"never"
server_description?: string

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

server_url?: string

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

formaturi
tunnel_id?: 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 { container, type, allowed_callers }

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

container: string | CodeInterpreterToolAuto { 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
CodeInterpreterToolAuto { 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?: Array<string>

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

memory_limit?: "1g" | "4g" | "16g" | "64g" | null

The memory limit for the code interpreter container.

One of the following:
"1g"
"4g"
"16g"
"64g"
network_policy?: ContainerNetworkPolicyDisabled { type } | ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }

Network access policy for the container.

One of the following:
ContainerNetworkPolicyDisabled { type }
type: "disabled"

Disable outbound network access. Always disabled.

ContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets }
allowed_domains: Array<string>

A list of allowed domains when type is allowlist.

type: "allowlist"

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

domain_secrets?: Array<ContainerNetworkPolicyDomainSecret { domain, name, value } >

Optional domain-scoped secrets for allowlisted domains.

domain: string

The domain associated with the secret.

minLength1
name: string

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?: Array<"direct" | "programmatic"> | null

The tool invocation context(s).

One of the following:
"direct"
"programmatic"
ProgrammaticToolCalling { type }
type: "programmatic_tool_calling"

The type of the tool. Always programmatic_tool_calling.

ImageGeneration { 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?: "generate" | "edit" | "auto"

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

One of the following:
"generate"
"edit"
"auto"
background?: "transparent" | "opaque" | "auto"

Allows to set transparency for the background of the generated image(s). Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.

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.

One of the following:
"transparent"
"opaque"
"auto"
input_fidelity?: "high" | "low" | 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?: InputImageMask { file_id, image_url }

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

file_id?: string

File ID for the mask image.

image_url?: string

Base64-encoded mask image.

model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 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 & {})
This type repeats the enclosing schema.
"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more
"gpt-image-1"
"gpt-image-1-mini"
"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"
"gpt-image-1.5"
"chatgpt-image-latest"
moderation?: "auto" | "low"

Moderation level for the generated image. Default: auto.

One of the following:
"auto"
"low"
output_compression?: number

Compression level for the output image. Default: 100.

minimum0
maximum100
output_format?: "png" | "webp" | "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?: number

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

minimum0
maximum3
quality?: "low" | "medium" | "high" | 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?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | "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 & {})
This type repeats the enclosing schema.
"1024x1024" | "1024x1536" | "1536x1024" | "auto"
LocalShell { type }

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

FunctionShellTool { type, allowed_callers, environment }

A tool that allows the model to execute shell commands.

CustomTool { name, type, allowed_callers, 4 more }

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

NamespaceTool { description, name, tools, type }

Groups function/custom tools under a shared namespace.

ToolSearchTool { type, description, execution, parameters }

Hosted or BYOT tool search configuration for deferred tools.

WebSearchPreviewTool { 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.

ApplyPatchTool { type, allowed_callers }

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

type: "tool_search_output"

The type of the item. Always tool_search_output.

created_by?: string

The identifier of the actor that created the item.

AdditionalTools { id, role, tools, type }
ResponseConfigurationUpdateItem { id, type, reasoning }

A configuration update that applies to subsequent responses until it is replaced by another configuration update.

ResponseReasoningItem { 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.

Program { id, call_id, code, 2 more }
ProgramOutput { id, call_id, result, 2 more }
ResponseCompactionItem { id, encrypted_content, type, created_by }

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

ImageGenerationCall { id, result, status, 7 more }

An image generation request made by the model.

ResponseCodeInterpreterToolCall { id, code, container_id, 3 more }

A tool call to run code.

LocalShellCall { id, action, call_id, 2 more }

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

LocalShellCallOutput { id, output, type, status }

The output of a local shell tool call.

ResponseFunctionShellToolCall { id, action, call_id, 5 more }

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

ResponseFunctionShellToolCallOutput { id, call_id, max_output_length, 5 more }

The output of a shell tool call that was emitted.

ResponseApplyPatchToolCall { id, call_id, operation, 4 more }

A tool call that applies file diffs by creating, deleting, or updating files.

ResponseApplyPatchToolCallOutput { id, call_id, status, 4 more }

The output emitted by an apply patch tool call.

McpListTools { id, server_label, tools, 2 more }

A list of tools available on an MCP server.

McpApprovalRequest { id, arguments, name, 2 more }

A request for human approval of a tool invocation.

McpApprovalResponse { id, approval_request_id, approve, 2 more }

A response to an MCP approval request.

McpCall { id, arguments, name, 6 more }

An invocation of a tool on an MCP server.

ResponseCustomToolCallItem extends ResponseCustomToolCall { call_id, input, name, 5 more } { id, status, created_by }

A call to a custom tool created by the model.

ResponseCustomToolCallOutputItem extends ResponseCustomToolCallOutput { call_id, output, type, 2 more } { id, status, created_by }

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

first_id: string

The ID of the first item in the list.

has_more: boolean

Whether there are more items available.

last_id: string

The ID of the last item in the list.

object: "list"

The type of object returned, must be list.