Create a model response
Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model’s response.
Body ParametersJSONExpand Collapse
Whether to run the model response in the background. Learn more.
context_management: optional array of object { type, compact_threshold } Context management configuration for this request.
Context management configuration for this request.
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.
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.
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).
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 thestoreparameter is set tofalse, or when an organization is enrolled in the zero data retention program).
input: optional string or array of BetaEasyInputMessage { content, role, phase, type } or object { content, role, agent, 2 more } or BetaResponseOutputMessage { id, content, role, 4 more } or 32 moreText, image, or file inputs to the model, used to generate a response.
Learn more:
Text, image, or file inputs to the model, used to generate a response.
Learn more:
InputItemList = array of BetaEasyInputMessage { content, role, phase, type } or object { content, role, agent, 2 more } or BetaResponseOutputMessage { id, content, role, 4 more } or 32 moreA list of one or many input items to the model, containing
different content types.
A list of one or many input items to the model, containing different content types.
BetaEasyInputMessage 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.
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.
Text, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
A list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
role: "user" or "assistant" or "system" or "developer"The role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
phase: optional "commentary" or "final_answer"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.
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.
Message object { content, role, agent, 2 more } 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.
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.
A list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
role: "user" or "system" or "developer"The role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
BetaResponseOutputMessage object { id, content, role, 4 more } An output message from the model.
An output message from the model.
content: array of BetaResponseOutputText { annotations, logprobs, text, type } or BetaResponseOutputRefusal { refusal, type } The content of the output message.
The content of the output message.
BetaResponseOutputText object { annotations, logprobs, text, type } A text output from the model.
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.
The annotations of the text output.
URLCitation object { end_index, start_index, title, 2 more } A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
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.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
phase: optional "commentary" or "final_answer"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.
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.
FileSearchCall object { id, queries, status, 3 more } The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
status: "in_progress" or "searching" or "completed" or 2 moreThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
results: optional array of object { attributes, file_id, filename, 2 more } The results of the file search tool call.
The results of the file search tool call.
attributes: optional map[string or number or boolean]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.
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.
ComputerCall object { id, call_id, pending_safety_checks, 5 more } A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
pending_safety_checks: array of object { id, code, message } The pending safety checks for the computer call.
The pending safety checks for the computer call.
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.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
A click action.
A click action.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
ComputerCallOutput object { call_id, output, type, 4 more } The output of a computer tool call.
The output of a computer tool call.
WebSearchCall object { id, action, status, 2 more } The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
action: 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).
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).
FunctionCall object { arguments, call_id, name, 6 more } A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
FunctionCallOutput object { call_id, output, type, 4 more } The output of a function tool call.
The output of a function tool call.
output: string or array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or BetaResponseInputFileContent { type, detail, file_data, 4 more } Text, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or BetaResponseInputFileContent { type, detail, file_data, 4 more } An array of content outputs (text, image, file) for the function tool call.
An array of content outputs (text, image, file) for the function tool call.
BetaResponseInputTextContent object { text, type, prompt_cache_breakpoint } A text input to the model.
A text input to the model.
BetaResponseInputImageContent object { type, detail, file_id, 2 more } An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
detail: optional "low" or "high" or "auto" or "original"The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
BetaResponseInputFileContent object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
The unique ID of the function tool call output. Populated when this item is returned via API.
AgentMessage object { author, content, recipient, 3 more } A message routed between agents.
A message routed between agents.
content: array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or object { encrypted_content, type } Plaintext, image, or encrypted content sent between agents.
Plaintext, image, or encrypted content sent between agents.
BetaResponseInputTextContent object { text, type, prompt_cache_breakpoint } A text input to the model.
A text input to the model.
BetaResponseInputImageContent object { type, detail, file_id, 2 more } An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
detail: optional "low" or "high" or "auto" or "original"The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
MultiAgentCall object { action, arguments, call_id, 3 more }
MultiAgentCallOutput object { action, call_id, output, 3 more }
action: "spawn_agent" or "interrupt_agent" or "list_agents" or 3 moreThe multi-agent action that produced this result.
The multi-agent action that produced this result.
output: array of object { text, type, annotations } Text output returned by the multi-agent action.
Text output returned by the multi-agent action.
annotations: optional array of object { file_id, filename, index, type } or array of object { end_index, start_index, title, 2 more } or array of object { container_id, end_index, file_id, 3 more } Citations associated with the text content.
Citations associated with the text content.
ToolSearchCall object { arguments, type, id, 4 more }
ToolSearchOutput object { tools, type, id, 4 more }
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreThe loaded tool definitions returned by the tool search output.
The loaded tool definitions returned by the tool search output.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
The unique ID of the tool search call generated by the model.
AdditionalTools object { role, tools, type, 2 more }
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreA list of additional tools made available at this item.
A list of additional tools made available at this item.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
Reasoning object { id, summary, type, 4 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.
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.
Compaction object { encrypted_content, type, id, agent } A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
ImageGenerationCall object { id, result, status, 2 more } An image generation request made by the model.
An image generation request made by the model.
CodeInterpreterCall object { id, code, container_id, 4 more } A tool call to run code.
A tool call to run code.
outputs: array of object { logs, type } or object { type, url } The outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
status: "in_progress" or "completed" or "incomplete" or 2 moreThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
LocalShellCall object { id, action, call_id, 3 more } A tool call to run a command on the local shell.
A tool call to run a command on the local shell.
LocalShellCallOutput object { id, output, type, 2 more } The output of a local shell tool call.
The output of a local shell tool call.
ShellCall object { action, call_id, type, 5 more } A tool representing a request to execute one or more shell commands.
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.
The shell commands and limits that describe how to run the tool call.
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 } The execution context that produced this tool call.
The execution context that produced this tool call.
environment: optional BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type } The environment to execute the shell commands in.
The environment to execute the shell commands in.
ShellCallOutput object { call_id, output, type, 5 more } The streamed output items emitted by a shell tool call.
The streamed output items emitted by a shell tool call.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
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 } The execution context that produced this tool call.
The execution context that produced this tool call.
ApplyPatchCall object { call_id, operation, status, 4 more } A tool call representing a request to create, delete, or update files using diff patches.
A tool call representing a request to create, delete, or update files using diff patches.
The unique ID of the apply patch tool call generated by the model.
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.
The specific create, delete, or update instruction for the apply_patch tool call.
CreateFile object { diff, path, type } Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
DeleteFile object { path, type } Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
status: "in_progress" or "completed"The status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput object { call_id, status, type, 4 more } The streamed output emitted by an apply patch tool call.
The streamed output emitted by an apply patch tool call.
The unique ID of the apply patch tool call generated by the model.
status: "completed" or "failed"The status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
McpListTools object { id, server_label, tools, 3 more } A list of tools available on an MCP server.
A list of tools available on an MCP server.
McpApprovalRequest object { id, arguments, name, 3 more } A request for human approval of a tool invocation.
A request for human approval of a tool invocation.
McpApprovalResponse object { approval_request_id, approve, type, 3 more } A response to an MCP approval request.
A response to an MCP approval request.
McpCall object { id, arguments, name, 7 more } An invocation of a tool on an MCP server.
An invocation of a tool on an MCP server.
CustomToolCallOutput object { call_id, output, type, 3 more } The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
output: string or array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { 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.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
OutputContentList = array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } Text, image, or file output of the custom tool call.
Text, image, or file output of the custom tool call.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
The type of the custom tool call output. Always custom_tool_call_output.
CustomToolCall object { call_id, input, name, 5 more } A call to a custom tool created by the model.
A call to a custom tool created by the model.
CompactionTrigger object { type, agent } Compacts the current context. Must be the final input item.
Compacts the current context. Must be the final input item.
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.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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.
model: optional "gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 more or stringModel ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
Model ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
"gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 moreModel ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
Model ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
moderation: optional object { model, policy } Configuration for running moderation on the input and output of this response.
Configuration for running moderation on the input and output of this response.
multi_agent: optional object { enabled, max_concurrent_subagents } Configuration for server-hosted multi-agent execution.
Configuration for server-hosted multi-agent execution.
max_concurrent_subagents sets the maximum number of subagents that can be active simultaneously across the entire agent tree. It includes all descendants—children, grandchildren, and deeper subagents—but excludes the root agent.
The API does not impose a fixed upper bound on this setting. The default is 3, which is recommended for most workloads. Multi-agent runs also have no fixed limit on tree depth or the total number of subagents created during a run.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
variables: optional map[string or BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } ]Optional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
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 { mode, 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.
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.
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.
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.
Deprecatedprompt_cache_retention: optional "in_memory" or "24h"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.
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_memorywhenprompt_cache_retentionis not specified.
reasoning: optional object { context, effort, generate_summary, 2 more } gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
context: optional "auto" or "current_turn" or "all_turns"Controls which reasoning items are rendered back to the model on later turns.
When returned on a response, this is the effective reasoning context mode
used for the response.
Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
effort: optional "none" or "minimal" or "low" or 4 moreConstrains effort on reasoning for reasoning models. Currently supported
values are none, minimal, low, medium, high, xhigh, and max.
Reducing reasoning effort can result in faster responses and fewer tokens
used on reasoning in a response. Not all reasoning models support every
value. See the
reasoning guide
for model-specific support.
Constrains effort on reasoning for reasoning models. Currently supported
values are none, minimal, low, medium, high, xhigh, and max.
Reducing reasoning effort can result in faster responses and fewer tokens
used on reasoning in a response. Not all reasoning models support every
value. See the
reasoning guide
for model-specific support.
Deprecatedgenerate_summary: optional "auto" or "concise" or "detailed"Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
mode: optional string or "standard" or "pro"Controls the reasoning execution mode for the request.
When returned on a response, this is the effective execution mode.
Controls the reasoning execution mode for the request.
When returned on a response, this is the effective execution mode.
summary: optional "auto" or "concise" or "detailed"A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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.
service_tier: optional "auto" or "default" or "flex" or 2 moreSpecifies 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’ or ‘priority’, then the request will be processed with the corresponding service tier.
- 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.
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’ or ‘priority’, then the request will be processed with the corresponding service tier.
- 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.
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_options: optional object { include_obfuscation } Options for streaming responses. Only set this when you set stream: true.
Options for streaming responses. Only set this when you set stream: true.
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.
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.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
An object specifying the format that the model must output.
Configuring { "type": "json_schema" } enables Structured Outputs,
which ensures the model will match your supplied JSON schema. Learn more in the
Structured Outputs guide.
The default format is { "type": "text" } with no additional options.
Not recommended for gpt-4o and newer models:
Setting to { "type": "json_object" } enables the older JSON mode, which
ensures the message the model generates is valid JSON. Using json_schema
is preferred for models that support it.
An object specifying the format that the model must output.
Configuring { "type": "json_schema" } enables Structured Outputs,
which ensures the model will match your supplied JSON schema. Learn more in the
Structured Outputs guide.
The default format is { "type": "text" } with no additional options.
Not recommended for gpt-4o and newer models:
Setting to { "type": "json_object" } enables the older JSON mode, which
ensures the message the model generates is valid JSON. Using json_schema
is preferred for models that support it.
BetaResponseFormatTextJSONSchemaConfig object { name, schema, type, 2 more } JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
tool_choice: optional BetaToolChoiceOptions or BetaToolChoiceAllowed { mode, tools, type } or BetaToolChoiceTypes { type } or 6 moreHow 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.
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.
BetaToolChoiceOptions = "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.
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.
BetaToolChoiceAllowed object { mode, tools, type } Constrains the tools available to the model to a pre-defined set.
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.
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.
BetaToolChoiceTypes object { type } Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
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 moreThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputercomputer_use_previewcomputer_usecode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputercomputer_use_previewcomputer_usecode_interpreterimage_generation
BetaToolChoiceFunction object { name, type } Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
BetaToolChoiceMcp object { server_label, type, name } Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
BetaToolChoiceCustom object { name, type } Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
tools: optional array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreAn 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.
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.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
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.
Deprecatedtruncation: optional "auto" or "disabled"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.
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.
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.
ReturnsExpand Collapse
BetaResponse object { id, created_at, error, 32 more }
An error object returned when the model fails to generate a Response.
An error object returned when the model fails to generate a Response.
instructions: string or array of BetaEasyInputMessage { content, role, phase, type } or object { content, role, agent, 2 more } or BetaResponseOutputMessage { id, content, role, 4 more } or 32 moreA 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.
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.
InputItemList = array of BetaEasyInputMessage { content, role, phase, type } or object { content, role, agent, 2 more } or BetaResponseOutputMessage { id, content, role, 4 more } or 32 moreA list of one or many input items to the model, containing
different content types.
A list of one or many input items to the model, containing different content types.
BetaEasyInputMessage 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.
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.
Text, image, or audio input to the model, used to generate a response.
Can also contain previous assistant responses.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
A list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
role: "user" or "assistant" or "system" or "developer"The role of the message input. One of user, assistant, system, or
developer.
The role of the message input. One of user, assistant, system, or
developer.
phase: optional "commentary" or "final_answer"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.
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.
Message object { content, role, agent, 2 more } 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.
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.
A list of one or many input items to the model, containing different content
types.
A list of one or many input items to the model, containing different content types.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
role: "user" or "system" or "developer"The role of the message input. One of user, system, or developer.
The role of the message input. One of user, system, or developer.
BetaResponseOutputMessage object { id, content, role, 4 more } An output message from the model.
An output message from the model.
content: array of BetaResponseOutputText { annotations, logprobs, text, type } or BetaResponseOutputRefusal { refusal, type } The content of the output message.
The content of the output message.
BetaResponseOutputText object { annotations, logprobs, text, type } A text output from the model.
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.
The annotations of the text output.
URLCitation object { end_index, start_index, title, 2 more } A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
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.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
phase: optional "commentary" or "final_answer"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.
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.
FileSearchCall object { id, queries, status, 3 more } The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
status: "in_progress" or "searching" or "completed" or 2 moreThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
results: optional array of object { attributes, file_id, filename, 2 more } The results of the file search tool call.
The results of the file search tool call.
attributes: optional map[string or number or boolean]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.
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.
ComputerCall object { id, call_id, pending_safety_checks, 5 more } A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
pending_safety_checks: array of object { id, code, message } The pending safety checks for the computer call.
The pending safety checks for the computer call.
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.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
A click action.
A click action.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
ComputerCallOutput object { call_id, output, type, 4 more } The output of a computer tool call.
The output of a computer tool call.
WebSearchCall object { id, action, status, 2 more } The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
action: 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).
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).
FunctionCall object { arguments, call_id, name, 6 more } A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
FunctionCallOutput object { call_id, output, type, 4 more } The output of a function tool call.
The output of a function tool call.
output: string or array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or BetaResponseInputFileContent { type, detail, file_data, 4 more } Text, image, or file output of the function tool call.
Text, image, or file output of the function tool call.
array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or BetaResponseInputFileContent { type, detail, file_data, 4 more } An array of content outputs (text, image, file) for the function tool call.
An array of content outputs (text, image, file) for the function tool call.
BetaResponseInputTextContent object { text, type, prompt_cache_breakpoint } A text input to the model.
A text input to the model.
BetaResponseInputImageContent object { type, detail, file_id, 2 more } An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
detail: optional "low" or "high" or "auto" or "original"The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
BetaResponseInputFileContent object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
The unique ID of the function tool call output. Populated when this item is returned via API.
AgentMessage object { author, content, recipient, 3 more } A message routed between agents.
A message routed between agents.
content: array of BetaResponseInputTextContent { text, type, prompt_cache_breakpoint } or BetaResponseInputImageContent { type, detail, file_id, 2 more } or object { encrypted_content, type } Plaintext, image, or encrypted content sent between agents.
Plaintext, image, or encrypted content sent between agents.
BetaResponseInputTextContent object { text, type, prompt_cache_breakpoint } A text input to the model.
A text input to the model.
BetaResponseInputImageContent object { type, detail, file_id, 2 more } An image input to the model. Learn about image inputs
An image input to the model. Learn about image inputs
detail: optional "low" or "high" or "auto" or "original"The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
The detail level of the image to be sent to the model. One of high, low, auto, or original. Defaults to auto.
MultiAgentCall object { action, arguments, call_id, 3 more }
MultiAgentCallOutput object { action, call_id, output, 3 more }
action: "spawn_agent" or "interrupt_agent" or "list_agents" or 3 moreThe multi-agent action that produced this result.
The multi-agent action that produced this result.
output: array of object { text, type, annotations } Text output returned by the multi-agent action.
Text output returned by the multi-agent action.
annotations: optional array of object { file_id, filename, index, type } or array of object { end_index, start_index, title, 2 more } or array of object { container_id, end_index, file_id, 3 more } Citations associated with the text content.
Citations associated with the text content.
ToolSearchCall object { arguments, type, id, 4 more }
ToolSearchOutput object { tools, type, id, 4 more }
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreThe loaded tool definitions returned by the tool search output.
The loaded tool definitions returned by the tool search output.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
The unique ID of the tool search call generated by the model.
AdditionalTools object { role, tools, type, 2 more }
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreA list of additional tools made available at this item.
A list of additional tools made available at this item.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
Reasoning object { id, summary, type, 4 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.
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.
Compaction object { encrypted_content, type, id, agent } A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
ImageGenerationCall object { id, result, status, 2 more } An image generation request made by the model.
An image generation request made by the model.
CodeInterpreterCall object { id, code, container_id, 4 more } A tool call to run code.
A tool call to run code.
outputs: array of object { logs, type } or object { type, url } The outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
status: "in_progress" or "completed" or "incomplete" or 2 moreThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
LocalShellCall object { id, action, call_id, 3 more } A tool call to run a command on the local shell.
A tool call to run a command on the local shell.
LocalShellCallOutput object { id, output, type, 2 more } The output of a local shell tool call.
The output of a local shell tool call.
ShellCall object { action, call_id, type, 5 more } A tool representing a request to execute one or more shell commands.
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.
The shell commands and limits that describe how to run the tool call.
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 } The execution context that produced this tool call.
The execution context that produced this tool call.
environment: optional BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type } The environment to execute the shell commands in.
The environment to execute the shell commands in.
ShellCallOutput object { call_id, output, type, 5 more } The streamed output items emitted by a shell tool call.
The streamed output items emitted by a shell tool call.
Captured chunks of stdout and stderr output, along with their associated outcomes.
Captured chunks of stdout and stderr output, along with their associated outcomes.
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 } The execution context that produced this tool call.
The execution context that produced this tool call.
ApplyPatchCall object { call_id, operation, status, 4 more } A tool call representing a request to create, delete, or update files using diff patches.
A tool call representing a request to create, delete, or update files using diff patches.
The unique ID of the apply patch tool call generated by the model.
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.
The specific create, delete, or update instruction for the apply_patch tool call.
CreateFile object { diff, path, type } Instruction for creating a new file via the apply_patch tool.
Instruction for creating a new file via the apply_patch tool.
DeleteFile object { path, type } Instruction for deleting an existing file via the apply_patch tool.
Instruction for deleting an existing file via the apply_patch tool.
status: "in_progress" or "completed"The status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
The unique ID of the apply patch tool call. Populated when this item is returned via API.
ApplyPatchCallOutput object { call_id, status, type, 4 more } The streamed output emitted by an apply patch tool call.
The streamed output emitted by an apply patch tool call.
The unique ID of the apply patch tool call generated by the model.
status: "completed" or "failed"The status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
McpListTools object { id, server_label, tools, 3 more } A list of tools available on an MCP server.
A list of tools available on an MCP server.
McpApprovalRequest object { id, arguments, name, 3 more } A request for human approval of a tool invocation.
A request for human approval of a tool invocation.
McpApprovalResponse object { approval_request_id, approve, type, 3 more } A response to an MCP approval request.
A response to an MCP approval request.
McpCall object { id, arguments, name, 7 more } An invocation of a tool on an MCP server.
An invocation of a tool on an MCP server.
CustomToolCallOutput object { call_id, output, type, 3 more } The output of a custom tool call from your code, being sent back to the model.
The output of a custom tool call from your code, being sent back to the model.
output: string or array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { 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.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
OutputContentList = array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } Text, image, or file output of the custom tool call.
Text, image, or file output of the custom tool call.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
The type of the custom tool call output. Always custom_tool_call_output.
CustomToolCall object { call_id, input, name, 5 more } A call to a custom tool created by the model.
A call to a custom tool created by the model.
CompactionTrigger object { type, agent } Compacts the current context. Must be the final input item.
Compacts the current context. Must be the final input item.
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.
model: "gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 more or stringModel ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
Model ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
"gpt-5.6-sol" or "gpt-5.6-terra" or "gpt-5.6-luna" or 92 moreModel ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
Model ID used to generate the response, like gpt-4o or o3. OpenAI
offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the model guide
to browse and compare available models.
An array of content items generated by the model.
- The length and order of items in the
output array is dependent
on the model’s response.
- Rather than accessing the first item in the
output array and
assuming it’s an assistant message with the content generated by
the model, you might consider using the output_text property where
supported in SDKs.
An array of content items generated by the model.
- The length and order of items in the
outputarray is dependent on the model’s response. - Rather than accessing the first item in the
outputarray and assuming it’s anassistantmessage with the content generated by the model, you might consider using theoutput_textproperty where supported in SDKs.
BetaResponseOutputMessage object { id, content, role, 4 more } An output message from the model.
An output message from the model.
content: array of BetaResponseOutputText { annotations, logprobs, text, type } or BetaResponseOutputRefusal { refusal, type } The content of the output message.
The content of the output message.
BetaResponseOutputText object { annotations, logprobs, text, type } A text output from the model.
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.
The annotations of the text output.
URLCitation object { end_index, start_index, title, 2 more } A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
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.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
phase: optional "commentary" or "final_answer"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.
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.
FileSearchCall object { id, queries, status, 3 more } The results of a file search tool call. See the
file search guide for more information.
The results of a file search tool call. See the file search guide for more information.
status: "in_progress" or "searching" or "completed" or 2 moreThe status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
results: optional array of object { attributes, file_id, filename, 2 more } The results of the file search tool call.
The results of the file search tool call.
attributes: optional map[string or number or boolean]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.
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.
FunctionCall object { arguments, call_id, name, 6 more } A tool call to run a function. See the
function calling guide for more information.
A tool call to run a function. See the function calling guide for more information.
FunctionCallOutput object { id, call_id, output, 5 more }
output: string or array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { 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.
The output from the function call generated by your code. Can be a string or an list of output content.
OutputContentList = array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } Text, image, or file output of the function call.
Text, image, or file output of the function call.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
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.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
AgentMessage object { id, author, content, 3 more }
content: array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseOutputText { annotations, logprobs, text, type } or object { text, type } or 7 moreEncrypted content sent between agents.
Encrypted content sent between agents.
BetaResponseOutputText object { annotations, logprobs, text, type } A text output from the model.
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.
The annotations of the text output.
URLCitation object { end_index, start_index, title, 2 more } A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
ComputerScreenshot object { detail, file_id, image_url, 2 more } A screenshot of a computer.
A screenshot of a computer.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
MultiAgentCall object { id, action, arguments, 3 more }
MultiAgentCallOutput object { id, action, call_id, 3 more }
action: "spawn_agent" or "interrupt_agent" or "list_agents" or 3 moreThe multi-agent action that produced this result.
The multi-agent action that produced this result.
Text output returned by the multi-agent action.
Text output returned by the multi-agent action.
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.
The annotations of the text output.
URLCitation object { end_index, start_index, title, 2 more } A citation for a web resource used to generate a model response.
A citation for a web resource used to generate a model response.
WebSearchCall object { id, action, status, 2 more } The results of a web search tool call. See the
web search guide for more information.
The results of a web search tool call. See the web search guide for more information.
action: 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).
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).
ComputerCall object { id, call_id, pending_safety_checks, 5 more } A tool call to a computer use tool. See the
computer use guide for more information.
A tool call to a computer use tool. See the computer use guide for more information.
pending_safety_checks: array of object { id, code, message } The pending safety checks for the computer call.
The pending safety checks for the computer call.
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.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
A click action.
A click action.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
Click object { button, type, x, 2 more } A click action.
A click action.
Drag object { path, type, keys } A drag action.
A drag action.
ComputerCallOutput object { id, call_id, output, 5 more }
status: "completed" or "incomplete" or "failed" or "in_progress"The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
acknowledged_safety_checks: optional array of object { id, code, message } The safety checks reported by the API that have been acknowledged by the
developer.
The safety checks reported by the API that have been acknowledged by the developer.
Reasoning object { id, summary, type, 4 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.
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.
ProgramOutput object { id, call_id, result, 3 more }
ToolSearchCall object { id, arguments, call_id, 5 more }
ToolSearchOutput object { id, call_id, execution, 5 more }
status: "in_progress" or "completed" or "incomplete"The status of the tool search output item that was recorded.
The status of the tool search output item that was recorded.
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreThe loaded tool definitions returned by tool search.
The loaded tool definitions returned by tool search.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
AdditionalTools object { id, role, tools, 2 more }
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreThe additional tool definitions made available at this item.
The additional tool definitions made available at this item.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
Compaction object { id, encrypted_content, type, 2 more } A compaction item generated by the v1/responses/compact API.
A compaction item generated by the v1/responses/compact API.
ImageGenerationCall object { id, result, status, 2 more } An image generation request made by the model.
An image generation request made by the model.
CodeInterpreterCall object { id, code, container_id, 4 more } A tool call to run code.
A tool call to run code.
outputs: array of object { logs, type } or object { type, url } The outputs generated by the code interpreter, such as logs or images.
Can be null if no outputs are available.
The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
status: "in_progress" or "completed" or "incomplete" or 2 moreThe status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
The status of the code interpreter tool call. Valid values are in_progress, completed, incomplete, interpreting, and failed.
LocalShellCall object { id, action, call_id, 3 more } A tool call to run a command on the local shell.
A tool call to run a command on the local shell.
LocalShellCallOutput object { id, output, type, 2 more } The output of a local shell tool call.
The output of a local shell tool call.
ShellCall object { id, action, call_id, 6 more } A tool call that executes one or more shell commands in a managed environment.
A tool call that executes one or more shell commands in a managed environment.
action: object { commands, max_output_length, timeout_ms } The shell commands and limits that describe how to run the tool call.
The shell commands and limits that describe how to run the tool call.
environment: BetaResponseLocalEnvironment { type } or BetaResponseContainerReference { container_id, type } Represents the use of a local environment to perform shell actions.
Represents the use of a local environment to perform shell actions.
status: "in_progress" or "completed" or "incomplete"The status of the shell call. One of in_progress, completed, or incomplete.
The status of the shell call. One of in_progress, completed, or incomplete.
ShellCallOutput object { id, call_id, max_output_length, 6 more } The output of a shell tool call that was emitted.
The output of a shell tool call that was emitted.
The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
output: array of object { outcome, stderr, stdout, created_by } An array of shell call output contents
An array of shell call output contents
status: "in_progress" or "completed" or "incomplete"The status of the shell call output. One of in_progress, completed, or incomplete.
The status of the shell call output. One of in_progress, completed, or incomplete.
ApplyPatchCall object { id, call_id, operation, 5 more } A tool call that applies file diffs by creating, deleting, or updating files.
A tool call that applies file diffs by creating, deleting, or updating files.
operation: object { diff, path, type } or object { path, type } or object { diff, path, type } One of the create_file, delete_file, or update_file operations applied via apply_patch.
One of the create_file, delete_file, or update_file operations applied via apply_patch.
status: "in_progress" or "completed"The status of the apply patch tool call. One of in_progress or completed.
The status of the apply patch tool call. One of in_progress or completed.
ApplyPatchCallOutput object { id, call_id, status, 5 more } The output emitted by an apply patch tool call.
The output emitted by an apply patch tool call.
The unique ID of the apply patch tool call output. Populated when this item is returned via API.
status: "completed" or "failed"The status of the apply patch tool call output. One of completed or failed.
The status of the apply patch tool call output. One of completed or failed.
McpCall object { id, arguments, name, 7 more } An invocation of a tool on an MCP server.
An invocation of a tool on an MCP server.
McpListTools object { id, server_label, tools, 3 more } A list of tools available on an MCP server.
A list of tools available on an MCP server.
McpApprovalRequest object { id, arguments, name, 3 more } A request for human approval of a tool invocation.
A request for human approval of a tool invocation.
McpApprovalResponse object { id, approval_request_id, approve, 3 more } A response to an MCP approval request.
A response to an MCP approval request.
CustomToolCall object { call_id, input, name, 5 more } A call to a custom tool created by the model.
A call to a custom tool created by the model.
CustomToolCallOutput object { id, call_id, output, 5 more }
output: string or array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { 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.
The output from the custom tool call generated by your code. Can be a string or an list of output content.
OutputContentList = array of BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } Text, image, or file output of the custom tool call.
Text, image, or file output of the custom tool call.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
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.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
The type of the custom tool call output. Always custom_tool_call_output.
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.
tool_choice: BetaToolChoiceOptions or BetaToolChoiceAllowed { mode, tools, type } or BetaToolChoiceTypes { type } or 6 moreHow 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.
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.
BetaToolChoiceOptions = "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.
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.
BetaToolChoiceAllowed object { mode, tools, type } Constrains the tools available to the model to a pre-defined set.
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.
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.
BetaToolChoiceTypes object { type } Indicates that the model should use a built-in tool to generate a response.
Learn more about built-in tools.
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 moreThe type of hosted tool the model should to use. Learn more about
built-in tools.
Allowed values are:
file_searchweb_search_previewcomputercomputer_use_previewcomputer_usecode_interpreterimage_generation
The type of hosted tool the model should to use. Learn more about built-in tools.
Allowed values are:
file_searchweb_search_previewcomputercomputer_use_previewcomputer_usecode_interpreterimage_generation
BetaToolChoiceFunction object { name, type } Use this option to force the model to call a specific function.
Use this option to force the model to call a specific function.
BetaToolChoiceMcp object { server_label, type, name } Use this option to force the model to call a specific tool on a remote MCP server.
Use this option to force the model to call a specific tool on a remote MCP server.
BetaToolChoiceCustom object { name, type } Use this option to force the model to call a specific custom tool.
Use this option to force the model to call a specific custom tool.
tools: array of object { name, parameters, strict, 5 more } or object { type, vector_store_ids, filters, 2 more } or object { type } or 13 moreAn 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.
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.
Function object { name, parameters, strict, 5 more } Defines a function in your own code the model can choose to call. Learn more about function calling.
Defines a function in your own code the model can choose to call. Learn more about function calling.
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.
A tool that searches for relevant content from uploaded files. Learn more about the file search tool.
filters: optional object { key, type, value } or object { filters, type } A filter to apply.
A filter to apply.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
CompoundFilter object { filters, type } Combine multiple filters using and or or.
Combine multiple filters using and or or.
filters: array of object { key, type, value } or unknownArray of filters to combine. Items can be ComparisonFilter or CompoundFilter.
Array of filters to combine. Items can be ComparisonFilter or CompoundFilter.
ComparisonFilter object { key, type, value } A filter used to compare a specified attribute key to a given value using a defined comparison operation.
A filter used to compare a specified attribute key to a given value using a defined comparison operation.
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.
Ranking options for search.
Computer object { type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
ComputerUsePreview object { display_height, display_width, environment, type } A tool that controls a virtual computer. Learn more about the computer tool.
A tool that controls a virtual computer. Learn more about the computer tool.
WebSearch object { type, filters, search_context_size, user_location } Search the Internet for sources related to the prompt. Learn more about the
web search tool.
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.
The type of the web search tool. One of web_search or web_search_2025_08_26.
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.
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.
user_location: optional object { city, country, region, 2 more } The approximate location of the user.
The approximate location of the user.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Give the model access to additional tools via remote Model Context Protocol (MCP) servers. Learn more about MCP.
allowed_tools: optional array of string or object { read_only, tool_names } List of allowed tool names or a filter object.
List of allowed tool names or a filter object.
McpToolFilter object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
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 moreIdentifier 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.
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
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.
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
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"Specify which of the MCP server’s tools require approval.
Specify which of the MCP server’s tools require approval.
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.
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.
A filter object to specify which tools are allowed.
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.
never: optional object { read_only, tool_names } A filter object to specify which tools are allowed.
A filter object to specify which tools are allowed.
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.
Optional description of the MCP server, used to provide more context.
CodeInterpreter object { container, type, allowed_callers } A tool that runs Python code to help generate a response to a prompt.
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.
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.
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.
Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.
An optional list of uploaded files to make available to your code.
memory_limit: optional "1g" or "4g" or "16g" or "64g"The memory limit for the code interpreter container.
The memory limit for the code interpreter container.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
ImageGeneration object { type, action, background, 9 more } A tool that generates images using the GPT image models.
A tool that generates images using the GPT image models.
action: optional "generate" or "edit" or "auto"Whether to generate a new image or edit an existing image. Default: auto.
Whether to generate a new image or edit an existing image. Default: auto.
background: optional "transparent" or "opaque" or "auto"Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
Background type for the generated image. One of transparent,
opaque, or auto. Default: auto.
input_fidelity: optional "high" or "low"Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
input_image_mask: optional object { file_id, image_url } Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
Optional mask for inpainting. Contains image_url
(string, optional) and file_id (string, optional).
model: optional string or "gpt-image-1" or "gpt-image-1-mini" or "gpt-image-1.5"The image generation model to use. Default: gpt-image-1.
The image generation model to use. Default: gpt-image-1.
Compression level for the output image. Default: 100.
output_format: optional "png" or "webp" or "jpeg"The output format of the generated image. One of png, webp, or
jpeg. Default: png.
The output format of the generated image. One of png, webp, or
jpeg. Default: png.
Number of partial images to generate in streaming mode, from 0 (default value) to 3.
quality: optional "low" or "medium" or "high" or "auto"The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
The quality of the generated image. One of low, medium, high,
or auto. Default: auto.
size: optional string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
"1024x1024" or "1024x1536" or "1536x1024" or "auto"The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, 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. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
LocalShell object { type } A tool that allows the model to execute shell commands in a local environment.
A tool that allows the model to execute shell commands in a local environment.
Shell object { type, allowed_callers, environment } A tool that allows the model to execute shell commands.
A tool that allows the model to execute shell commands.
environment: optional BetaContainerAuto { type, file_ids, memory_limit, 2 more } or BetaLocalEnvironment { type, skills } or BetaContainerReference { container_id, type }
BetaContainerAuto object { type, file_ids, memory_limit, 2 more }
An optional list of uploaded files to make available to your code.
network_policy: optional BetaContainerNetworkPolicyDisabled { type } or BetaContainerNetworkPolicyAllowlist { allowed_domains, type, domain_secrets } Network access policy for the container.
Network access policy for the container.
skills: optional array of BetaSkillReference { skill_id, type, version } or BetaInlineSkill { description, name, source, type } An optional list of skills referenced by id or inline data.
An optional list of skills referenced by id or inline data.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
Namespace object { description, name, tools, type } Groups function/custom tools under a shared namespace.
Groups function/custom tools under a shared namespace.
tools: array of object { name, type, allowed_callers, 5 more } or object { name, type, allowed_callers, 3 more } The function/custom tools available inside this namespace.
The function/custom tools available inside this namespace.
Function object { name, type, allowed_callers, 5 more }
Whether this function should be deferred and discovered via tool search.
Custom object { name, type, allowed_callers, 3 more } A custom tool that processes input using a specified format. Learn more about custom tools
A custom tool that processes input using a specified format. Learn more about custom tools
ToolSearch object { type, description, execution, parameters } Hosted or BYOT tool search configuration for deferred tools.
Hosted or BYOT tool search configuration for deferred tools.
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.
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.
The type of the web search tool. One of web_search_preview or web_search_preview_2025_03_11.
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.
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.
user_location: optional object { type, city, country, 2 more } The user’s location.
The user’s location.
The two-letter ISO country code of the user, e.g. US.
The IANA timezone of the user, e.g. America/Los_Angeles.
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.
Whether to run the model response in the background. Learn more.
Unix timestamp (in seconds) of when this Response was completed.
Only present when the status is completed.
conversation: optional object { id } The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
moderation: optional object { input, output } Moderation results for the response input and output, if moderated completions were requested.
Moderation results for the response input and output, if moderated completions were requested.
input: object { categories, category_applied_input_types, category_scores, 3 more } or object { code, message, type } Moderation for the response input.
Moderation for the response input.
ModerationResult object { categories, category_applied_input_types, category_scores, 3 more } A moderation result produced for the response input or output.
A moderation result produced for the response input or output.
output: object { categories, category_applied_input_types, category_scores, 3 more } or object { code, message, type } Moderation for the response output.
Moderation for the response output.
ModerationResult object { categories, category_applied_input_types, category_scores, 3 more } A moderation result produced for the response input or output.
A moderation result produced for the response input or output.
SDK-only convenience property that contains the aggregated text output
from all output_text items in the output array, if any are present.
Supported in the Python and JavaScript SDKs.
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.
Reference to a prompt template and its variables.
Learn more.
Reference to a prompt template and its variables. Learn more.
variables: optional map[string or BetaResponseInputText { text, type, prompt_cache_breakpoint } or BetaResponseInputImage { detail, type, file_id, 2 more } or BetaResponseInputFile { type, detail, file_data, 4 more } ]Optional map of values to substitute in for variables in your
prompt. The substitution values can either be strings, or other
Response input types like images or files.
Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files.
BetaResponseInputImage object { detail, type, file_id, 2 more } An image input to the model. Learn about image inputs.
An image input to the model. Learn about image inputs.
BetaResponseInputFile object { type, detail, file_data, 4 more } A file input to the model.
A file input to the model.
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.
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.
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 { mode, ttl } The prompt-caching options that were applied to the response. Supported for gpt-5.6 and later models.
The prompt-caching options that were applied to the response. Supported for gpt-5.6 and later models.
Deprecatedprompt_cache_retention: optional "in_memory" or "24h"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.
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_memorywhenprompt_cache_retentionis not specified.
reasoning: optional object { context, effort, generate_summary, 2 more } gpt-5 and o-series models only
Configuration options for
reasoning models.
gpt-5 and o-series models only
Configuration options for reasoning models.
context: optional "auto" or "current_turn" or "all_turns"Controls which reasoning items are rendered back to the model on later turns.
When returned on a response, this is the effective reasoning context mode
used for the response.
Controls which reasoning items are rendered back to the model on later turns. When returned on a response, this is the effective reasoning context mode used for the response.
effort: optional "none" or "minimal" or "low" or 4 moreConstrains effort on reasoning for reasoning models. Currently supported
values are none, minimal, low, medium, high, xhigh, and max.
Reducing reasoning effort can result in faster responses and fewer tokens
used on reasoning in a response. Not all reasoning models support every
value. See the
reasoning guide
for model-specific support.
Constrains effort on reasoning for reasoning models. Currently supported
values are none, minimal, low, medium, high, xhigh, and max.
Reducing reasoning effort can result in faster responses and fewer tokens
used on reasoning in a response. Not all reasoning models support every
value. See the
reasoning guide
for model-specific support.
Deprecatedgenerate_summary: optional "auto" or "concise" or "detailed"Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
Deprecated: use summary instead.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
mode: optional string or "standard" or "pro"Controls the reasoning execution mode for the request.
When returned on a response, this is the effective execution mode.
Controls the reasoning execution mode for the request.
When returned on a response, this is the effective execution mode.
summary: optional "auto" or "concise" or "detailed"A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
A summary of the reasoning performed by the model. This can be
useful for debugging and understanding the model’s reasoning process.
One of auto, concise, or detailed.
concise is supported for computer-use-preview models and all reasoning models after gpt-5.
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.
service_tier: optional "auto" or "default" or "flex" or 2 moreSpecifies 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’ or ‘priority’, then the request will be processed with the corresponding service tier.
- 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.
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’ or ‘priority’, then the request will be processed with the corresponding service tier.
- 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.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
The status of the response generation. One of completed, failed,
in_progress, cancelled, queued, or incomplete.
Configuration options for a text response from the model. Can be plain
text or structured JSON data. Learn more:
Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
An object specifying the format that the model must output.
Configuring { "type": "json_schema" } enables Structured Outputs,
which ensures the model will match your supplied JSON schema. Learn more in the
Structured Outputs guide.
The default format is { "type": "text" } with no additional options.
Not recommended for gpt-4o and newer models:
Setting to { "type": "json_object" } enables the older JSON mode, which
ensures the message the model generates is valid JSON. Using json_schema
is preferred for models that support it.
An object specifying the format that the model must output.
Configuring { "type": "json_schema" } enables Structured Outputs,
which ensures the model will match your supplied JSON schema. Learn more in the
Structured Outputs guide.
The default format is { "type": "text" } with no additional options.
Not recommended for gpt-4o and newer models:
Setting to { "type": "json_object" } enables the older JSON mode, which
ensures the message the model generates is valid JSON. Using json_schema
is preferred for models that support it.
BetaResponseFormatTextJSONSchemaConfig object { name, schema, type, 2 more } JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
A description of what the response format is for, used by the model to determine how to respond in the format.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
truncation: optional "auto" or "disabled"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.
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.
Represents token usage details including input tokens, output tokens,
a breakdown of output tokens, and the total tokens used.
Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
input_tokens_details: object { cache_write_tokens, cached_tokens } A detailed breakdown of the input tokens.
A detailed breakdown of the input tokens.
The number of tokens that were retrieved from the cache. More on prompt caching.
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.
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"input": "Tell me a three sentence bedtime story about a unicorn."
}'
{
"id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
"object": "response",
"created_at": 1741476542,
"status": "completed",
"completed_at": 1741476543,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 36,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 87,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 123
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"input": [
{
"role": "user",
"content": [
{"type": "input_text", "text": "what is in this image?"},
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
]
}
]
}'
{
"id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
"object": "response",
"created_at": 1741476777,
"status": "completed",
"completed_at": 1741476778,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 52,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 380
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"input": [
{
"role": "user",
"content": [
{"type": "input_text", "text": "what is in this file?"},
{
"type": "input_file",
"file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf",
"detail": "auto"
}
]
}
]
}'
{
"id": "resp_686eef60237881a2bd1180bb8b13de430e34c516d176ff86",
"object": "response",
"created_at": 1752100704,
"status": "completed",
"completed_at": 1752100705,
"background": false,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"max_tool_calls": null,
"model": "gpt-5.4",
"output": [
{
"id": "msg_686eef60d3e081a29283bdcbc4322fd90e34c516d176ff86",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "The file seems to contain excerpts from a letter to the shareholders of Berkshire Hathaway Inc., likely written by Warren Buffett. It covers several topics:\n\n1. **Communication Philosophy**: Buffett emphasizes the importance of transparency and candidness in reporting mistakes and successes to shareholders.\n\n2. **Mistakes and Learnings**: The letter acknowledges past mistakes in business assessments and management hires, highlighting the importance of correcting errors promptly.\n\n3. **CEO Succession**: Mention of Greg Abel stepping in as the new CEO and continuing the tradition of honest communication.\n\n4. **Pete Liegl Story**: A detailed account of acquiring Forest River and the relationship with its founder, highlighting trust and effective business decisions.\n\n5. **2024 Performance**: Overview of business performance, particularly in insurance and investment activities, with a focus on GEICO's improvement.\n\n6. **Tax Contributions**: Discussion of significant tax payments to the U.S. Treasury, credited to shareholders' reinvestments.\n\n7. **Investment Strategy**: A breakdown of Berkshire\u2019s investments in both controlled subsidiaries and marketable equities, along with a focus on long-term holding strategies.\n\n8. **American Capitalism**: Reflections on America\u2019s economic development and Berkshire\u2019s role within it.\n\n9. **Property-Casualty Insurance**: Insights into the P/C insurance business model and its challenges and benefits.\n\n10. **Japanese Investments**: Information about Berkshire\u2019s investments in Japanese companies and future plans.\n\n11. **Annual Meeting**: Details about the upcoming annual gathering in Omaha, including schedule changes and new book releases.\n\n12. **Personal Anecdotes**: Light-hearted stories about family and interactions, conveying Buffett's personable approach.\n\n13. **Financial Performance Data**: Tables comparing Berkshire\u2019s annual performance to the S&P 500, showing impressive long-term gains.\n\nOverall, the letter reinforces Berkshire Hathaway's commitment to transparency, investment in both its businesses and the wider economy, and emphasizes strong leadership and prudent financial management."
}
],
"role": "assistant"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"service_tier": "default",
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 8438,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 398,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 8836
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"tools": [{ "type": "web_search_preview" }],
"input": "What was a positive news story from today?"
}'
{
"id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c",
"object": "response",
"created_at": 1741484430,
"status": "completed",
"completed_at": 1741484431,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "web_search_call",
"id": "ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c",
"status": "completed"
},
{
"type": "message",
"id": "msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "As of today, March 9, 2025, one notable positive news story...",
"annotations": [
{
"type": "url_citation",
"start_index": 442,
"end_index": 557,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 962,
"end_index": 1077,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 1336,
"end_index": 1451,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "web_search_preview",
"domains": [],
"search_context_size": "medium",
"user_location": {
"type": "approximate",
"city": null,
"country": "US",
"region": null,
"timezone": null
}
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 356,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 684
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"tools": [{
"type": "file_search",
"vector_store_ids": ["vs_1234567890"],
"max_num_results": 20
}],
"input": "What are the attributes of an ancient brown dragon?"
}'
{
"id": "resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7",
"object": "response",
"created_at": 1741485253,
"status": "completed",
"completed_at": 1741485254,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "file_search_call",
"id": "fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7",
"status": "completed",
"queries": [
"attributes of an ancient brown dragon"
],
"results": null
},
{
"type": "message",
"id": "msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The attributes of an ancient brown dragon include...",
"annotations": [
{
"type": "file_citation",
"index": 320,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 576,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1156,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1225,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "file_search",
"filters": null,
"max_num_results": 20,
"ranking_options": {
"ranker": "auto",
"score_threshold": 0.0
},
"vector_store_ids": [
"vs_1234567890"
]
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 18307,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 348,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 18655
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"instructions": "You are a helpful assistant.",
"input": "Hello!",
"stream": true
}'
event: response.created
data: {"type":"response.created","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.in_progress
data: {"type":"response.in_progress","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"in_progress","role":"assistant","content":[]}}
event: response.content_part.added
data: {"type":"response.content_part.added","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"","annotations":[]}}
event: response.output_text.delta
data: {"type":"response.output_text.delta","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"delta":"Hi"}
...
event: response.output_text.done
data: {"type":"response.output_text.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"text":"Hi there! How can I assist you today?"}
event: response.content_part.done
data: {"type":"response.content_part.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}}
event: response.output_item.done
data: {"type":"response.output_item.done","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}}
event: response.completed
data: {"type":"response.completed","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"completed","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":{"input_tokens":37,"output_tokens":11,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":48},"user":null,"metadata":{}}}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"input": "What is the weather like in Boston today?",
"tools": [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location", "unit"]
}
}
],
"tool_choice": "auto"
}'
{
"id": "resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0",
"object": "response",
"created_at": 1741294021,
"status": "completed",
"completed_at": 1741294022,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "function_call",
"id": "fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0",
"call_id": "call_unLAR8MvFNptuiZK6K6HCy5k",
"name": "get_current_weather",
"arguments": "{\"location\":\"Boston, MA\",\"unit\":\"celsius\"}",
"status": "completed"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "function",
"description": "Get the current weather in a given location",
"name": "get_current_weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
},
"strict": true
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 291,
"output_tokens": 23,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 314
},
"user": null,
"metadata": {}
}
Create a model response
curl https://api.openai.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "o3-mini",
"input": "How much wood would a woodchuck chuck?",
"reasoning": {
"effort": "high"
}
}'
{
"id": "resp_67ccd7eca01881908ff0b5146584e408072912b2993db808",
"object": "response",
"created_at": 1741477868,
"status": "completed",
"completed_at": 1741477869,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "o1-2024-12-17",
"output": [
{
"type": "message",
"id": "msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The classic tongue twister...",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": "high",
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 81,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 1035,
"output_tokens_details": {
"reasoning_tokens": 832
},
"total_tokens": 1116
},
"user": null,
"metadata": {}
}
Returns Examples
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
],
"text": "text",
"type": "output_text"
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"agent": {
"agent_name": "agent_name"
},
"phase": "commentary"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"allowed_callers": [
"direct"
],
"defer_loading": true,
"description": "description",
"output_schema": {
"foo": "bar"
}
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"moderation": {
"input": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
},
"output": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
}
},
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_options": {
"mode": "implicit",
"ttl": "30m"
},
"prompt_cache_retention": "in_memory",
"reasoning": {
"context": "auto",
"effort": "none",
"generate_summary": "auto",
"mode": "standard",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cache_write_tokens": 0,
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}