# Live ## `client.live.connect(RequestOptionsoptions?): void` **** `` Connect to Live without query parameters. Send session.start with model and session configuration, then wait for session.started. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) before writing instructions. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.connect(); ``` ## Create session `client.live.create(LiveCreateParamsbody, RequestOptionsoptions?): LiveCreateResponse` **post** `/live/sessions` Create a Live WebRTC session. Start with the [Live prompting guide](/api/docs/guides/live-prompting). ### Parameters - `body: LiveCreateParams` - `session: MediaSessionConfig` Startup configuration for the Live session. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `audio?: Audio` Startup audio configuration. WebRTC and SIP negotiate their audio format on the media transport. - `output?: Output` Settings for speech generated by the Live model. Choose the voice before starting the session. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `transport: Transport` WebRTC transport with the browser's SDP offer. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` ### Returns - `LiveCreateResponse` The created Live session identifier and WebRTC answer. Apply transport.sdp as the peer's remote answer and wait for session.started on the data channel before sending commands. - `session: Session` The newly created Live session. Use its ID for session controls and sideband connections. - `id: string` Opaque session identifier. Preserve the returned value unchanged, including its prefix. - `transport: Transport` WebRTC transport with the SDP answer. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); const live = await client.live.create({ session: { model: 'gpt-live-1' }, transport: { sdp: 'x', type: 'webrtc' }, }); console.log(live.session); ``` #### Response ```json { "session": { "id": "live_123" }, "transport": { "type": "webrtc", "sdp": "" } } ``` ## Domain Types ### Audio Format - `AudioFormat = AudioPCM | AudioPCMU | AudioPCMA` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` ### Built In Voice - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` ### Client Config - `ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. ### Client Delegation - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` ### Client Event - `ClientEvent = SessionStartEvent | SessionUpdateEvent | InputAudioAppendEvent | 8 more` Client events for Live. Initialize a primary WebSocket with session.start and wait for session.started. WebRTC creation already starts the session. Audio append is primary WebSocket-only. See the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) before writing frontend instructions and delegation policies. - `SessionStartEvent` Start a Live session on a primary WebSocket. Send this event before other commands and wait for `session.started`. - `session: SessionConfig` Initial configuration for a primary WebSocket. Send session.start first and wait for session.started before application commands. WebRTC creation already starts the session; do not send this event again on its data channel. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.start"` The Live client event type. Always `session.start`. - `"session.start"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `SessionUpdateEvent` Update the delegation settings of an active Live session. The server acknowledges accepted changes with `session.updated`. - `session: SessionUpdateConfig` Sparse delegation updates. Omitted settings retain their values. The delegation type cannot change, including resetting Responses delegation to null or client. Model, frontend instructions, audio, and startup input are immutable. - `delegation?: ClientDelegation | Responses | null` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `Responses` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "session.update"` The Live client event type. Always `session.update`. - `"session.update"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioAppendEvent` Send audio to a Live session over its primary WebSocket. WebRTC and SIP sessions send audio over their media transport. - `audio: string` Base64-encoded raw audio in the startup-selected format, without a WAV or other container header. Primary WebSocket only; media transports use their audio track. Audio appends have no acknowledgment. Reflected sideband server events reuse this event type and audio key, with no timestamps or event_id; their audio is always mono PCM16LE at 24 kHz. - `type: "session.input_audio.append"` The Live client event type. Always `session.input_audio.append`. - `"session.input_audio.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioMuteEvent` Mute audio input to the Live model without closing the session. The server acknowledges with `session.input_audio.muted`. - `type: "session.input_audio.mute"` The Live client event type. Always `session.input_audio.mute`. - `"session.input_audio.mute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioUnmuteEvent` Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`. - `type: "session.input_audio.unmute"` The Live client event type. Always `session.input_audio.unmute`. - `"session.input_audio.unmute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InstructionsAppendEvent` Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation. - `content: string` Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.instructions.append"` The Live client event type. Always `session.instructions.append`. - `"session.instructions.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ThinkingAppendEvent` Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation. - `content: string` Silent reasoning or progress context, limited to 500 tokens. It does not directly request speech, but can influence later speech and is not a secrecy boundary. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.thinking.append"` The Live client event type. Always `session.thinking.append`. - `"session.thinking.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `CommentaryAppendEvent` Provide context the Live model can communicate to the user, optionally for an existing client delegation. - `content: string` Speakable context for the Live model, limited to 500 tokens. Use this for a result the model should communicate; use session.thinking.append for silent context. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.commentary.append"` The Live client event type. Always `session.commentary.append`. - `"session.commentary.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseItemCreateEvent` Add an input item to the Live session’s Responses backend. Requires Responses delegation; use `response.create` to request a response. - `item: ResponseInputItem` An input item to append to the Responses backend conversation, such as a user message or a function tool result. - `EasyInputMessage` A message input to the model with a role indicating instruction following hierarchy. Instructions given with the `developer` or `system` role take precedence over instructions given with the `user` role. Messages with the `assistant` role are presumed to have been generated by the model in previous interactions. - `content: string | ResponseInputMessageContentList` Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. - `string` - `ResponseInputMessageContentList = Array` A list of one or many input items to the model, containing different content types. - `ResponseInputText` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `detail: ImageDetail` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `"low"` - `"high"` - `"auto"` - `"original"` - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFile` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string` The content of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string` The URL of the file to be sent to the model. - `filename?: string` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `role: "user" | "assistant" | "system" | "developer"` The role of the message input. One of `user`, `assistant`, `system`, or `developer`. - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `type?: "message"` The type of the message input. Always `message`. - `"message"` - `Message` 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. - `content: ResponseInputMessageContentList` A list of one or many input items to the model, containing different content types. - `role: "user" | "system" | "developer"` The role of the message input. One of `user`, `system`, or `developer`. - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` The type of the message input. Always set to `message`. - `"message"` - `ResponseOutputMessage` An output message from the model. - `id: string` The unique ID of the output message. - `content: Array` The content of the output message. - `ResponseOutputText` A text output from the model. - `annotations: Array` The annotations of the text output. - `FileCitation` A citation to a file. - `file_id: string` The ID of the file. - `filename: string` The filename of the file cited. - `index: number` The index of the file in the list of files. - `type: "file_citation"` The type of the file citation. Always `file_citation`. - `"file_citation"` - `URLCitation` A citation for a web resource used to generate a model response. - `end_index: number` The index of the last character of the URL citation in the message. - `start_index: number` The index of the first character of the URL citation in the message. - `title: string` The title of the web resource. - `type: "url_citation"` The type of the URL citation. Always `url_citation`. - `"url_citation"` - `url: string` The URL of the web resource. - `ContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` The ID of the container file. - `end_index: number` The index of the last character of the container file citation in the message. - `file_id: string` The ID of the file. - `filename: string` The filename of the container file cited. - `start_index: number` The index of the first character of the container file citation in the message. - `type: "container_file_citation"` The type of the container file citation. Always `container_file_citation`. - `"container_file_citation"` - `FilePath` A path to a file. - `file_id: string` The ID of the file. - `index: number` The index of the file in the list of files. - `type: "file_path"` The type of the file path. Always `file_path`. - `"file_path"` - `text: string` The text output from the model. - `type: "output_text"` The type of the output text. Always `output_text`. - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `ResponseOutputRefusal` A refusal from the model. - `refusal: string` The refusal explanation from the model. - `type: "refusal"` The type of the refusal. Always `refusal`. - `"refusal"` - `role: "assistant"` The role of the output message. Always `assistant`. - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` The type of the output message. Always `message`. - `"message"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `ResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](/api/docs/guides/tools-file-search) for more information. - `id: string` The unique ID of the file search tool call. - `queries: Array` The queries used to search for files. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` The type of the file search tool call. Always `file_search_call`. - `"file_search_call"` - `results?: Array | null` The results of the file search tool call. - `attributes?: Record | null` Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers. - `string` - `number` - `boolean` - `file_id?: string` The unique ID of the file. - `filename?: string` The name of the file. - `score?: number` The relevance score of the file - a value between 0 and 1. - `text?: string` The text that was retrieved from the file. - `ResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](/api/docs/guides/tools-computer-use) for more information. - `id: string` The unique ID of the computer call. - `call_id: string` An identifier used when responding to the tool call with output. - `pending_safety_checks: Array` The pending safety checks for the computer call. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` The type of the computer call. Always `computer_call`. - `"computer_call"` - `action?: Click | DoubleClick | Drag | 6 more` A click action. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `actions?: ComputerActionList` Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `ComputerCallOutput` The output of a computer tool call. - `call_id: string` The ID of the computer tool call that produced the output. - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. - `"computer_screenshot"` - `file_id?: string` The identifier of an uploaded file that contains the screenshot. - `image_url?: string` The URL of the screenshot image. - `type: "computer_call_output"` The type of the computer tool call output. Always `computer_call_output`. - `"computer_call_output"` - `id?: string | null` The ID of the computer tool call output. - `acknowledged_safety_checks?: Array | null` The safety checks reported by the API that have been acknowledged by the developer. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](/api/docs/guides/tools-web-search) for more information. - `id: string` The unique ID of the web search tool call. - `action: Search | OpenPage | FindInPage` 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). - `Search` Action type "search" - Performs a web search query. - `type: "search"` The action type. - `"search"` - `queries?: Array` The search queries. - `query?: string` The search query. - `sources?: Array` The sources used in the search. - `type: "url"` The type of source. Always `url`. - `"url"` - `url: string` The URL of the source. - `OpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` The action type. - `"open_page"` - `url?: string | null` The URL opened by the model. - `FindInPage` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` The pattern or text to search for within the page. - `type: "find_in_page"` The action type. - `"find_in_page"` - `url: string` The URL of the page searched for the pattern. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the web search tool call. - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `"incomplete"` - `type: "web_search_call"` The type of the web search tool call. Always `web_search_call`. - `"web_search_call"` - `ResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](/api/docs/guides/function-calling) for more information. - `arguments: string` A JSON string of the arguments to pass to the function. - `call_id: string` The unique ID of the function tool call generated by the model. - `name: string` The name of the function to run. - `type: "function_call"` The type of the function tool call. Always `function_call`. - `"function_call"` - `id?: string` The unique ID of the function tool call. - `async?: boolean` Whether the function tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the function to run. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `FunctionCallOutput` The output of a function tool call. - `output: string | ResponseFunctionCallOutputItemList` Text, image, or file output of the function tool call. - `string` - `ResponseFunctionCallOutputItemList = Array` An array of content outputs (text, image, file) for the function tool call. - `ResponseInputTextContent` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision) - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `detail?: ImageDetail | null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string | null` The base64-encoded data of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string | null` The URL of the file to be sent to the model. - `filename?: string | null` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `type: "function_call_output"` The type of the function tool call output. Always `function_call_output`. - `"function_call_output"` - `id?: string | null` The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id?: string | null` The unique ID of the function tool call generated by the model. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `name?: string | null` The name of the tool that produced the output. - `namespace?: string | null` The namespace of the tool that produced the output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ToolSearchCall` - `arguments: unknown` The arguments supplied to the tool search call. - `type: "tool_search_call"` The item type. Always `tool_search_call`. - `"tool_search_call"` - `id?: string | null` The unique ID of this tool search call. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search call. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseToolSearchOutputItemParam` - `tools: Array` The loaded tool definitions returned by the tool search output. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `name: string` The name of the function to call. - `parameters: Record | null` A JSON schema object describing the parameters of the function. - `strict: boolean | null` Whether strict parameter validation is enforced for this function tool. - `type: "function"` The type of the function tool. Always `function`. - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` - `defer_loading?: boolean` Whether this function is deferred and loaded via tool search. - `description?: string | null` A description of the function. Used by the model to determine whether or not to call the function. - `output_schema?: Record | null` A JSON schema object describing the JSON value encoded in string outputs for this function. - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `type: "file_search"` The type of the file search tool. Always `file_search`. - `"file_search"` - `vector_store_ids: Array` The IDs of the vector stores to search. - `filters?: ComparisonFilter | CompoundFilter | null` A filter to apply. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` The key to compare against the value. - `type: "eq" | "ne" | "gt" | 5 more` Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`. - `eq`: equals - `ne`: not equal - `gt`: greater than - `gte`: greater than or equal - `lt`: less than - `lte`: less than or equal - `in`: in - `nin`: not in - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `"in"` - `"nin"` - `value: string | number | boolean | Array` The value to compare against the attribute key; supports string, number, or boolean types. - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `unknown` - `type: "and" | "or"` Type of operation: `and` or `or`. - `"and"` - `"or"` - `max_num_results?: number` The maximum number of results to return. This number should be between 1 and 50 inclusive. - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` The weight of the embedding in the reciprocal ranking fusion. - `text_weight: number` The weight of the text in the reciprocal ranking fusion. - `ranker?: "auto" | "default-2024-11-15"` The ranker to use for the file search. - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results. - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `type: "computer"` The type of the computer tool. Always `computer`. - `"computer"` - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `display_height: number` The height of the computer display. - `display_width: number` The width of the computer display. - `environment: "windows" | "mac" | "linux" | 2 more` The type of computer environment to control. - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` The type of the computer use tool. Always `computer_use_preview`. - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. - `"web_search"` - `"web_search_2025_08_26"` - `external_web_access?: boolean` Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content. - `filters?: Filters | null` Filters for the search. - `allowed_domains?: Array | null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. Example: `["pubmed.ncbi.nlm.nih.gov"]` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The approximate location of the user. - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `type?: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `server_label: string` A label for this MCP server, used to identify it in tool calls. - `type: "mcp"` The type of the MCP tool. Always `mcp`. - `"mcp"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `allowed_tools?: Array | McpToolFilter | null` List of allowed tool names or a filter object. - `Array` - `McpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `authorization?: string` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` 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](/api/docs/guides/tools-connectors-mcp#connectors). 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` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `defer_loading?: boolean` Whether this MCP tool is deferred and discovered via tool search. - `headers?: Record | null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval?: McpToolApprovalFilter | "always" | "never" | null` Specify which of the MCP server's tools require approval. - `McpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` Optional description of the MCP server, used to provide more context. - `server_url?: string` The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `tunnel_id?: string` The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterToolAuto` 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. - `string` - `CodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` Always `auto`. - `"auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the code interpreter container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `type: "disabled"` Disable outbound network access. Always `disabled`. - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` A list of allowed domains when type is `allowlist`. - `type: "allowlist"` Allow outbound network access only to specified domains. Always `allowlist`. - `"allowlist"` - `domain_secrets?: Array` Optional domain-scoped secrets for allowlisted domains. - `domain: string` The domain associated with the secret. - `name: string` The name of the secret to inject for the domain. - `value: string` The secret value to inject for the domain. - `type: "code_interpreter"` The type of the code interpreter tool. Always `code_interpreter`. - `"code_interpreter"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `ProgrammaticToolCalling` - `type: "programmatic_tool_calling"` The type of the tool. Always `programmatic_tool_calling`. - `"programmatic_tool_calling"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` The type of the image generation tool. Always `image_generation`. - `"image_generation"` - `action?: "generate" | "edit" | "auto"` Whether to generate a new image or edit an existing image. Default: `auto`. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`. - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low" | null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. 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`. - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` File ID for the mask image. - `image_url?: string` Base64-encoded mask image. - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` The image generation model to use. One of `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default: `gpt-image-1`. - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-2"` - `"gpt-image-2-2026-04-21"` - `"gpt-image-2.5-sunburst"` - `"gpt-image-2.5-sunburst-2026-09-08"` - `"gpt-image-2.5-flare"` - `"gpt-image-2.5-flare-2026-09-08"` - `"gpt-image-1.5"` - `"chatgpt-image-latest"` - `moderation?: "auto" | "low"` Moderation level for the generated image. Default: `auto`. - `"auto"` - `"low"` - `output_compression?: number` Compression level for the output image. Default: 100. - `output_format?: "png" | "webp" | "jpeg"` The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` Number of partial images to generate in streaming mode, from 0 (default value) to 3. - `quality?: "low" | "medium" | "high" | 3 more` The quality of the generated image. The GPT image models support `low`, `medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. Default: `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | "auto"` The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` The type of the local shell tool. Always `local_shell`. - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` The type of the shell tool. Always `shell`. - `"shell"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference | null` - `ContainerAuto` - `type: "container_auto"` Automatically creates a container for this request - `"container_auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` An optional list of skills referenced by id or inline data. - `SkillReference` - `skill_id: string` The ID of the referenced skill. - `type: "skill_reference"` References a skill created with the /v1/skills endpoint. - `"skill_reference"` - `version?: string` Optional skill version. Use a positive integer or 'latest'. Omit for default. - `InlineSkill` - `description: string` The description of the skill. - `name: string` The name of the skill. - `source: InlineSkillSource` Inline skill payload - `data: string` Base64-encoded skill zip bundle. - `media_type: "application/zip"` The media type of the inline skill payload. Must be `application/zip`. - `"application/zip"` - `type: "base64"` The type of the inline skill source. Must be `base64`. - `"base64"` - `type: "inline"` Defines an inline skill for this request. - `"inline"` - `LocalEnvironment` - `type: "local"` Use a local computer environment. - `"local"` - `skills?: Array` An optional list of skills. - `description: string` The description of the skill. - `name: string` The name of the skill. - `path: string` The path to the directory containing the skill. - `ContainerReference` - `container_id: string` The ID of the referenced container. - `type: "container_reference"` References a container created with the /v1/containers endpoint - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `name: string` The name of the custom tool, used to identify it in tool calls. - `type: "custom"` The type of the custom tool. Always `custom`. - `"custom"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this tool should be deferred and discovered via tool search. - `description?: string` Optional description of the custom tool, used to provide more context. - `format?: CustomToolInputFormat` The input format for the custom tool. Default is unconstrained text. - `Text` Unconstrained free-form text. - `type: "text"` Unconstrained text format. Always `text`. - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` The grammar definition. - `syntax: "lark" | "regex"` The syntax of the grammar definition. One of `lark` or `regex`. - `"lark"` - `"regex"` - `type: "grammar"` Grammar format. Always `grammar`. - `"grammar"` - `NamespaceTool` Groups function/custom tools under a shared namespace. - `description: string` A description of the namespace shown to the model. - `name: string` The namespace name used in tool calls (for example, `crm`). - `tools: Array` The function/custom tools available inside this namespace. - `Function` - `name: string` - `type: "function"` - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this function should be deferred and discovered via tool search. - `description?: string | null` - `output_schema?: Record | null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters?: unknown` - `strict?: boolean | null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `type: "namespace"` The type of the tool. Always `namespace`. - `"namespace"` - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `type: "tool_search"` The type of the tool. Always `tool_search`. - `"tool_search"` - `description?: string | null` Description shown to the model for a client-executed tool search tool. - `execution?: "server" | "client"` Whether tool search is executed by the server or by the client. - `"server"` - `"client"` - `parameters?: unknown` Parameter schema for a client-executed tool search tool. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search_preview" | "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`. - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_content_types?: Array<"text" | "image">` - `"text"` - `"image"` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The user's location. - `type: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` The type of the tool. Always `apply_patch`. - `"apply_patch"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `type: "tool_search_output"` The item type. Always `tool_search_output`. - `"tool_search_output"` - `id?: string | null` The unique ID of this tool search output. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search output. - `"in_progress"` - `"completed"` - `"incomplete"` - `AdditionalTools` - `role: "developer"` The role that provided the additional tools. Only `developer` is supported. - `"developer"` - `tools: Array` A list of additional tools made available at this item. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `ProgrammaticToolCalling` - `ImageGeneration` A tool that generates images using the GPT image models. - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `FunctionShellTool` A tool that allows the model to execute shell commands. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `NamespaceTool` Groups function/custom tools under a shared namespace. - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "additional_tools"` The item type. Always `additional_tools`. - `"additional_tools"` - `id?: string | null` The unique ID of this additional tools item. - `ResponseConfigurationUpdateItemParam` An update to the conversation's response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update. - `type: "configuration_update"` The item type. Always `configuration_update`. - `"configuration_update"` - `id?: string | null` The unique ID of the configuration update item. - `reasoning?: Reasoning` Updates to reasoning configuration. Only effort is supported. - `effort?: ReasoningEffort | null` The reasoning effort to use for subsequent responses until another configuration update replaces it. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `ResponseReasoningItem` 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](/api/docs/guides/conversation-state). - `id: string` The unique identifier of the reasoning content. - `summary: Array` Reasoning summary content. - `text: string` A summary of the reasoning output from the model so far. - `type: "summary_text"` The type of the object. Always `summary_text`. - `"summary_text"` - `type: "reasoning"` The type of the object. Always `reasoning`. - `"reasoning"` - `content?: Array` Reasoning text content. - `text: string` The reasoning text from the model. - `type: "reasoning_text"` The type of the reasoning text. Always `reasoning_text`. - `"reasoning_text"` - `encrypted_content?: string | null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket `response.create` requests. When streaming, use the completed reasoning item and its `encrypted_content` from the `response.output_item.done` event in subsequent requests. The `encrypted_content` in `response.output_item.added` may be incomplete. This is especially important when `store` is `false` or when using Zero Data Retention. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](/api/reference/resources/responses/methods/compact). - `encrypted_content: string` The encrypted content of the compaction summary. - `type: "compaction"` The type of the item. Always `compaction`. - `"compaction"` - `id?: string | null` The ID of the compaction item. - `ImageGenerationCall` An image generation request made by the model. - `id: string` The unique ID of the image generation call. - `result: string | null` The generated image encoded in base64. - `status: "in_progress" | "completed" | "generating" | "failed"` The status of the image generation call. - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` The type of the image generation call. Always `image_generation_call`. - `"image_generation_call"` - `action?: "generate" | "edit" | "auto" | null` The action used for image generation. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto" | null` The background setting used for generation. - `"transparent"` - `"opaque"` - `"auto"` - `output_format?: "png" | "webp" | "jpeg" | null` The output format used for generation. - `"png"` - `"webp"` - `"jpeg"` - `quality?: "low" | "medium" | "high" | 3 more | null` The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `revised_prompt?: string | null` The prompt that was used after any model prompt rewriting. - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | null` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `ResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` The unique ID of the code interpreter tool call. - `code: string | null` The code to run, or null if not available. - `container_id: string` The ID of the container used to run the code. - `outputs: Array | null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. - `Logs` The logs output from the code interpreter. - `logs: string` The logs output from the code interpreter. - `type: "logs"` The type of the output. Always `logs`. - `"logs"` - `Image` The image output from the code interpreter. - `type: "image"` The type of the output. Always `image`. - `"image"` - `url: string` The URL of the image output from the code interpreter. - `status: "in_progress" | "completed" | "incomplete" | 2 more` The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` The type of the code interpreter tool call. Always `code_interpreter_call`. - `"code_interpreter_call"` - `LocalShellCall` A tool call to run a command on the local shell. - `id: string` The unique ID of the local shell call. - `action: Action` Execute a shell command on the server. - `command: Array` The command to run. - `env: Record` Environment variables to set for the command. - `type: "exec"` The type of the local shell action. Always `exec`. - `"exec"` - `timeout_ms?: number | null` Optional timeout in milliseconds for the command. - `user?: string | null` Optional user to run the command as. - `working_directory?: string | null` Optional working directory to run the command in. - `call_id: string` The unique ID of the local shell tool call generated by the model. - `status: "in_progress" | "completed" | "incomplete"` The status of the local shell call. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` The type of the local shell call. Always `local_shell_call`. - `"local_shell_call"` - `LocalShellCallOutput` The output of a local shell tool call. - `id: string` The unique ID of the local shell tool call generated by the model. - `output: string` A JSON string of the output of the local shell tool call. - `type: "local_shell_call_output"` The type of the local shell tool call output. Always `local_shell_call_output`. - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` Ordered shell commands for the execution environment to run. - `max_output_length?: number | null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - `timeout_ms?: number | null` Maximum wall-clock time in milliseconds to allow the shell commands to run. - `call_id: string` The unique ID of the shell tool call generated by the model. - `type: "shell_call"` The type of the item. Always `shell_call`. - `"shell_call"` - `id?: string | null` The unique ID of the shell tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `environment?: LocalEnvironment | ContainerReference | null` The environment to execute the shell commands in. - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` The unique ID of the shell tool call generated by the model. - `output: Array` Captured chunks of stdout and stderr output, along with their associated outcomes. - `outcome: Timeout | Exit` The exit or timeout outcome associated with this shell call. - `Timeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` The outcome type. Always `timeout`. - `"timeout"` - `Exit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` The exit code returned by the shell process. - `type: "exit"` The outcome type. Always `exit`. - `"exit"` - `stderr: string` Captured stderr output for the shell call. - `stdout: string` Captured stdout output for the shell call. - `type: "shell_call_output"` The type of the item. Always `shell_call_output`. - `"shell_call_output"` - `id?: string | null` The unique ID of the shell tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `max_output_length?: number | null` The maximum number of UTF-8 characters captured for this shell call's combined output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call output. - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `operation: CreateFile | DeleteFile | UpdateFile` The specific create, delete, or update instruction for the apply_patch tool call. - `CreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` Unified diff content to apply when creating the file. - `path: string` Path of the file to create relative to the workspace root. - `type: "create_file"` The operation type. Always `create_file`. - `"create_file"` - `DeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` Path of the file to delete relative to the workspace root. - `type: "delete_file"` The operation type. Always `delete_file`. - `"delete_file"` - `UpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` Unified diff content to apply to the existing file. - `path: string` Path of the file to update relative to the workspace root. - `type: "update_file"` The operation type. Always `update_file`. - `"update_file"` - `status: "in_progress" | "completed"` The status of the apply patch tool call. One of `in_progress` or `completed`. - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` The type of the item. Always `apply_patch_call`. - `"apply_patch_call"` - `id?: string | null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `status: "completed" | "failed"` The status of the apply patch tool call output. One of `completed` or `failed`. - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` The type of the item. Always `apply_patch_call_output`. - `"apply_patch_call_output"` - `id?: string | null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `output?: string | null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). - `McpListTools` A list of tools available on an MCP server. - `id: string` The unique ID of the list. - `server_label: string` The label of the MCP server. - `tools: Array` The tools available on the server. - `input_schema: unknown` The JSON schema describing the tool's input. - `name: string` The name of the tool. - `annotations?: unknown` Additional annotations about the tool. - `description?: string | null` The description of the tool. - `type: "mcp_list_tools"` The type of the item. Always `mcp_list_tools`. - `"mcp_list_tools"` - `error?: string | null` Error message if the server could not list tools. - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` The unique ID of the approval request. - `arguments: string` A JSON string of arguments for the tool. - `name: string` The name of the tool to run. - `server_label: string` The label of the MCP server making the request. - `type: "mcp_approval_request"` The type of the item. Always `mcp_approval_request`. - `"mcp_approval_request"` - `McpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` The ID of the approval request being answered. - `approve: boolean` Whether the request was approved. - `type: "mcp_approval_response"` The type of the item. Always `mcp_approval_response`. - `"mcp_approval_response"` - `id?: string | null` The unique ID of the approval response - `reason?: string | null` Optional reason for the decision. - `McpCall` An invocation of a tool on an MCP server. - `id: string` The unique ID of the tool call. - `arguments: string` A JSON string of the arguments passed to the tool. - `name: string` The name of the tool that was run. - `server_label: string` The label of the MCP server running the tool. - `type: "mcp_call"` The type of the item. Always `mcp_call`. - `"mcp_call"` - `approval_request_id?: string | null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - `error?: McpToolCallError | null` The error from the tool call, if any. - `McpProtocolError` - `code: number` - `message: string` - `type: "mcp_protocol_error"` - `"mcp_protocol_error"` - `McpToolExecutionError` - `content: unknown` - `type: "mcp_tool_execution_error"` - `"mcp_tool_execution_error"` - `HTTPError` - `code: number` - `message: string` - `type: "http_error"` - `"http_error"` - `output?: string | null` The output from the tool call. - `status?: "in_progress" | "completed" | "incomplete" | 2 more` The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `ResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` The call ID, used to map this custom tool call output to a custom tool call. - `output: string | Array` The output from the custom tool call generated by your code. Can be a string or an list of output content. - `string` - `Array` - `ResponseInputText` A text input to the model. - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `ResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` The type of the custom tool call output. Always `custom_tool_call_output`. - `"custom_tool_call_output"` - `id?: string` The unique ID of the custom tool call output in the OpenAI platform. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` An identifier used to map this custom tool call to a tool call output. - `input: string` The input for the custom tool call generated by the model. - `name: string` The name of the custom tool being called. - `type: "custom_tool_call"` The type of the custom tool call. Always `custom_tool_call`. - `"custom_tool_call"` - `id?: string` The unique ID of the custom tool call in the OpenAI platform. - `async?: boolean` Whether the custom tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the custom tool being called. - `CompactionTrigger` Compacts the current context. Must be the final input item. - `type: "compaction_trigger"` The type of the item. Always `compaction_trigger`. - `"compaction_trigger"` - `ItemReference` An internal identifier for an item to reference. - `id: string` The ID of the item to reference. - `type?: "item_reference" | null` The type of item to reference. Always `item_reference`. - `"item_reference"` - `Program` - `id: string` The unique ID of this program item. - `call_id: string` The stable call ID of the program item. - `code: string` The JavaScript source executed by programmatic tool calling. - `fingerprint: string` Opaque program replay fingerprint that must be round-tripped. - `type: "program"` The item type. Always `program`. - `"program"` - `ProgramOutput` - `id: string` The unique ID of this program output item. - `call_id: string` The call ID of the program item. - `result: string` The result produced by the program item. - `status: "completed" | "incomplete"` The terminal status of the program output. - `"completed"` - `"incomplete"` - `type: "program_output"` The item type. Always `program_output`. - `"program_output"` - `type: "response.item.create"` The Live client event type. Always `response.item.create`. - `"response.item.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseCreateEvent` Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation. - `type: "response.create"` The Live client event type. Always `response.create`. - `"response.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `SessionCloseEvent` Request that the Live session close. The terminal `session.closed` event contains the close reason and final usage. - `type: "session.close"` The Live client event type. Always `session.close`. - `"session.close"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Commentary Append Event - `CommentaryAppendEvent` Provide context the Live model can communicate to the user, optionally for an existing client delegation. - `content: string` Speakable context for the Live model, limited to 500 tokens. Use this for a result the model should communicate; use session.thinking.append for silent context. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.commentary.append"` The Live client event type. Always `session.commentary.append`. - `"session.commentary.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Commentary Appended Event - `CommentaryAppendedEvent` Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.commentary.appended"` The event type, always `session.commentary.appended`. - `"session.commentary.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Custom Voice - `CustomVoice` - `id: string` ### Data Channel Config - `DataChannelConfig` Control which Live events an untrusted WebRTC frontend can send and receive over its data channel. These restrictions do not apply to trusted sideband connections. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. ### Delegation Created Event - `DelegationCreatedEvent` Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated. - `delegation: Delegation` The delegated work identifier and destination. This object contains metadata, not the task text. - `id: string` The unique ID of the delegation. Use this as delegation_id when replying to client-owned work or correlating Responses events. - `target: "client" | "responses"` Where the Live model delegated the work: `client` for your application, or `responses` for the configured Responses backend. - `"client" | "responses"` - `"client"` - `"responses"` - `type: "delegation"` The object type, always `delegation`. - `"delegation"` - `response_id?: string` The ID of the Responses API response associated with a Responses delegation. Omitted for client delegations. - `event_id: string` The unique ID of the Live server event. - `offset_ms: number` The position on the Live session timeline where the delegation was created, in milliseconds from the beginning of the session. - `type: "session.delegation.created"` The event type, always `session.delegation.created`. - `"session.delegation.created"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Error - `Error` Details of an error encountered by the Live session, including the affected parameter or client command when available. - `code: string` A machine-readable code identifying the Live error, such as `unknown_parameter`. - `message: string` A human-readable explanation of the Live error. - `type: string` The category of error, such as `invalid_request_error` for an invalid Live client command. - `client_event_id?: string` The event_id of the client command that caused the error, when supplied. - `param?: string` The parameter that caused the error, when applicable, such as `session.voice`. ### Error Event - `ErrorEvent` Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error. - `error: Error` Details of the Live error and the client command that caused it, when known. - `code: string` A machine-readable code identifying the Live error, such as `unknown_parameter`. - `message: string` A human-readable explanation of the Live error. - `type: string` The category of error, such as `invalid_request_error` for an invalid Live client command. - `client_event_id?: string` The event_id of the client command that caused the error, when supplied. - `param?: string` The parameter that caused the error, when applicable, such as `session.voice`. - `event_id: string` The unique ID of the Live server event. - `type: "error"` The event type, always `error`. - `"error"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Fork Session Config - `ForkSessionConfig` Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks. - `audio?: Audio` Audio format for a WebSocket fork. WebRTC forks negotiate their audio format and must omit this field. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `client?: ClientConfig` Frontend data-channel permissions for a WebRTC fork. Omitted permissions inherit the stored values. Not supported for WebSocket forks. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: Delegation` Overrides for the stored session’s Responses backend. Only supported when the stored session already uses Responses delegation; the delegation type cannot change. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `store?: boolean` Whether to store the forked session. Omission inherits the stored session's setting. ### Fork Session Start Event - `ForkSessionStartEvent` Start a Live session after connecting to a stored session’s fork WebSocket. Send an empty `session` object to use the stored configuration. - `session: ForkSessionConfig` Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks. - `audio?: Audio` Audio format for a WebSocket fork. WebRTC forks negotiate their audio format and must omit this field. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `client?: ClientConfig` Frontend data-channel permissions for a WebRTC fork. Omitted permissions inherit the stored values. Not supported for WebSocket forks. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: Delegation` Overrides for the stored session’s Responses backend. Only supported when the stored session already uses Responses delegation; the delegation type cannot change. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `store?: boolean` Whether to store the forked session. Omission inherits the stored session's setting. - `type: "session.start"` The Live client event type. Always `session.start`. - `"session.start"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Function Tool - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. ### Info Event - `InfoEvent` An informational notice about the Live session, such as the event permissions applied to a frontend data channel. - `code: string` A machine-readable code for the notice, such as `data_channel_permissions`. - `event_id: string` The unique ID of the Live server event. - `message: string` A human-readable explanation of the Live session notice. - `type: "info"` The event type, always `info`. - `"info"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Initial Item - `InitialItem = Developer | User | Assistant` A developer, user, or assistant message supplied as text history before the Live session starts. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` ### Input Audio Append Event - `InputAudioAppendEvent` Send audio to a Live session over its primary WebSocket. WebRTC and SIP sessions send audio over their media transport. - `audio: string` Base64-encoded raw audio in the startup-selected format, without a WAV or other container header. Primary WebSocket only; media transports use their audio track. Audio appends have no acknowledgment. Reflected sideband server events reuse this event type and audio key, with no timestamps or event_id; their audio is always mono PCM16LE at 24 kHz. - `type: "session.input_audio.append"` The Live client event type. Always `session.input_audio.append`. - `"session.input_audio.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Input Audio Mute Event - `InputAudioMuteEvent` Mute audio input to the Live model without closing the session. The server acknowledges with `session.input_audio.muted`. - `type: "session.input_audio.mute"` The Live client event type. Always `session.input_audio.mute`. - `"session.input_audio.mute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Input Audio Muted Event - `InputAudioMutedEvent` Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.muted"` The event type, always `session.input_audio.muted`. - `"session.input_audio.muted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Input Audio Unmute Event - `InputAudioUnmuteEvent` Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`. - `type: "session.input_audio.unmute"` The Live client event type. Always `session.input_audio.unmute`. - `"session.input_audio.unmute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Input Audio Unmuted Event - `InputAudioUnmutedEvent` Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.unmuted"` The event type, always `session.input_audio.unmuted`. - `"session.input_audio.unmuted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Input Transcript Delta Event - `InputTranscriptDeltaEvent` A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.input_transcript.delta"` The event type, always `session.input_transcript.delta`. - `"session.input_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Instructions Append Event - `InstructionsAppendEvent` Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation. - `content: string` Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.instructions.append"` The Live client event type. Always `session.instructions.append`. - `"session.instructions.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Instructions Appended Event - `InstructionsAppendedEvent` Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.instructions.appended"` The event type, always `session.instructions.appended`. - `"session.instructions.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Live Create Response - `LiveCreateResponse` The created Live session identifier and WebRTC answer. Apply transport.sdp as the peer's remote answer and wait for session.started on the data channel before sending commands. - `session: Session` The newly created Live session. Use its ID for session controls and sideband connections. - `id: string` Opaque session identifier. Preserve the returned value unchanged, including its prefix. - `transport: Transport` WebRTC transport with the SDP answer. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` ### Media Session Config - `MediaSessionConfig` Startup configuration for a Live media session. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when writing frontend instructions and the backend prompt under delegation.responses.instructions. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `audio?: Audio` Startup audio configuration. WebRTC and SIP negotiate their audio format on the media transport. - `output?: Output` Settings for speech generated by the Live model. Choose the voice before starting the session. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. ### Media Session Fork Config - `MediaSessionForkConfig` Optional overrides for a stored Live session. Omitted settings are inherited. The model, voice, frontend instructions, and prior conversation come from the stored session. WebRTC negotiates its audio format; audio.format is only supported on WebSocket forks. - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: Delegation` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `store?: boolean` Whether to store the forked session. Omission inherits the stored session's setting. ### Output Audio Delta Event - `OutputAudioDeltaEvent` An audio chunk generated by the Live model. Decode and play primary WebSocket chunks in delivery order using the configured session audio format. Sideband connections receive reflected output audio with timestamps. - `delta: string` Base64-encoded raw audio. Primary WebSocket events use the session's configured format; reflected sideband events use mono PCM16LE at 24 kHz. - `type: "session.output_audio.delta"` The event type, always `session.output_audio.delta`. - `"session.output_audio.delta"` - `end_ms?: number` Exclusive session-relative end in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. Dropped output frames leave gaps between reflected ranges. - `start_ms?: number` Inclusive session-relative start in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. ### Output Transcript Delta Event - `OutputTranscriptDeltaEvent` A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.output_transcript.delta"` The event type, always `session.output_transcript.delta`. - `"session.output_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Response Create Event - `ResponseCreateEvent` Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation. - `type: "response.create"` The Live client event type. Always `response.create`. - `"response.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Response Event - `ResponseEvent` A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation. - `event: Record` The nested Responses streaming event. Dispatch on its type field. Response lifecycle snapshots omit input and clear instructions, tools, and output to keep messages small; consume granular output events for the generated content. - `event_id: string` The unique ID of the Live server event. - `type: "response.event"` The event type, always `response.event`. - `"response.event"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `delegation_id?: string | null` The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation. ### Response Item Create Event - `ResponseItemCreateEvent` Add an input item to the Live session’s Responses backend. Requires Responses delegation; use `response.create` to request a response. - `item: ResponseInputItem` An input item to append to the Responses backend conversation, such as a user message or a function tool result. - `EasyInputMessage` A message input to the model with a role indicating instruction following hierarchy. Instructions given with the `developer` or `system` role take precedence over instructions given with the `user` role. Messages with the `assistant` role are presumed to have been generated by the model in previous interactions. - `content: string | ResponseInputMessageContentList` Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. - `string` - `ResponseInputMessageContentList = Array` A list of one or many input items to the model, containing different content types. - `ResponseInputText` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `detail: ImageDetail` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `"low"` - `"high"` - `"auto"` - `"original"` - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFile` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string` The content of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string` The URL of the file to be sent to the model. - `filename?: string` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `role: "user" | "assistant" | "system" | "developer"` The role of the message input. One of `user`, `assistant`, `system`, or `developer`. - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `type?: "message"` The type of the message input. Always `message`. - `"message"` - `Message` 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. - `content: ResponseInputMessageContentList` A list of one or many input items to the model, containing different content types. - `role: "user" | "system" | "developer"` The role of the message input. One of `user`, `system`, or `developer`. - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` The type of the message input. Always set to `message`. - `"message"` - `ResponseOutputMessage` An output message from the model. - `id: string` The unique ID of the output message. - `content: Array` The content of the output message. - `ResponseOutputText` A text output from the model. - `annotations: Array` The annotations of the text output. - `FileCitation` A citation to a file. - `file_id: string` The ID of the file. - `filename: string` The filename of the file cited. - `index: number` The index of the file in the list of files. - `type: "file_citation"` The type of the file citation. Always `file_citation`. - `"file_citation"` - `URLCitation` A citation for a web resource used to generate a model response. - `end_index: number` The index of the last character of the URL citation in the message. - `start_index: number` The index of the first character of the URL citation in the message. - `title: string` The title of the web resource. - `type: "url_citation"` The type of the URL citation. Always `url_citation`. - `"url_citation"` - `url: string` The URL of the web resource. - `ContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` The ID of the container file. - `end_index: number` The index of the last character of the container file citation in the message. - `file_id: string` The ID of the file. - `filename: string` The filename of the container file cited. - `start_index: number` The index of the first character of the container file citation in the message. - `type: "container_file_citation"` The type of the container file citation. Always `container_file_citation`. - `"container_file_citation"` - `FilePath` A path to a file. - `file_id: string` The ID of the file. - `index: number` The index of the file in the list of files. - `type: "file_path"` The type of the file path. Always `file_path`. - `"file_path"` - `text: string` The text output from the model. - `type: "output_text"` The type of the output text. Always `output_text`. - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `ResponseOutputRefusal` A refusal from the model. - `refusal: string` The refusal explanation from the model. - `type: "refusal"` The type of the refusal. Always `refusal`. - `"refusal"` - `role: "assistant"` The role of the output message. Always `assistant`. - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` The type of the output message. Always `message`. - `"message"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `ResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](/api/docs/guides/tools-file-search) for more information. - `id: string` The unique ID of the file search tool call. - `queries: Array` The queries used to search for files. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` The type of the file search tool call. Always `file_search_call`. - `"file_search_call"` - `results?: Array | null` The results of the file search tool call. - `attributes?: Record | null` Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers. - `string` - `number` - `boolean` - `file_id?: string` The unique ID of the file. - `filename?: string` The name of the file. - `score?: number` The relevance score of the file - a value between 0 and 1. - `text?: string` The text that was retrieved from the file. - `ResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](/api/docs/guides/tools-computer-use) for more information. - `id: string` The unique ID of the computer call. - `call_id: string` An identifier used when responding to the tool call with output. - `pending_safety_checks: Array` The pending safety checks for the computer call. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` The type of the computer call. Always `computer_call`. - `"computer_call"` - `action?: Click | DoubleClick | Drag | 6 more` A click action. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `actions?: ComputerActionList` Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `ComputerCallOutput` The output of a computer tool call. - `call_id: string` The ID of the computer tool call that produced the output. - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. - `"computer_screenshot"` - `file_id?: string` The identifier of an uploaded file that contains the screenshot. - `image_url?: string` The URL of the screenshot image. - `type: "computer_call_output"` The type of the computer tool call output. Always `computer_call_output`. - `"computer_call_output"` - `id?: string | null` The ID of the computer tool call output. - `acknowledged_safety_checks?: Array | null` The safety checks reported by the API that have been acknowledged by the developer. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](/api/docs/guides/tools-web-search) for more information. - `id: string` The unique ID of the web search tool call. - `action: Search | OpenPage | FindInPage` 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). - `Search` Action type "search" - Performs a web search query. - `type: "search"` The action type. - `"search"` - `queries?: Array` The search queries. - `query?: string` The search query. - `sources?: Array` The sources used in the search. - `type: "url"` The type of source. Always `url`. - `"url"` - `url: string` The URL of the source. - `OpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` The action type. - `"open_page"` - `url?: string | null` The URL opened by the model. - `FindInPage` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` The pattern or text to search for within the page. - `type: "find_in_page"` The action type. - `"find_in_page"` - `url: string` The URL of the page searched for the pattern. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the web search tool call. - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `"incomplete"` - `type: "web_search_call"` The type of the web search tool call. Always `web_search_call`. - `"web_search_call"` - `ResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](/api/docs/guides/function-calling) for more information. - `arguments: string` A JSON string of the arguments to pass to the function. - `call_id: string` The unique ID of the function tool call generated by the model. - `name: string` The name of the function to run. - `type: "function_call"` The type of the function tool call. Always `function_call`. - `"function_call"` - `id?: string` The unique ID of the function tool call. - `async?: boolean` Whether the function tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the function to run. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `FunctionCallOutput` The output of a function tool call. - `output: string | ResponseFunctionCallOutputItemList` Text, image, or file output of the function tool call. - `string` - `ResponseFunctionCallOutputItemList = Array` An array of content outputs (text, image, file) for the function tool call. - `ResponseInputTextContent` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision) - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `detail?: ImageDetail | null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string | null` The base64-encoded data of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string | null` The URL of the file to be sent to the model. - `filename?: string | null` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `type: "function_call_output"` The type of the function tool call output. Always `function_call_output`. - `"function_call_output"` - `id?: string | null` The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id?: string | null` The unique ID of the function tool call generated by the model. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `name?: string | null` The name of the tool that produced the output. - `namespace?: string | null` The namespace of the tool that produced the output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ToolSearchCall` - `arguments: unknown` The arguments supplied to the tool search call. - `type: "tool_search_call"` The item type. Always `tool_search_call`. - `"tool_search_call"` - `id?: string | null` The unique ID of this tool search call. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search call. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseToolSearchOutputItemParam` - `tools: Array` The loaded tool definitions returned by the tool search output. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `name: string` The name of the function to call. - `parameters: Record | null` A JSON schema object describing the parameters of the function. - `strict: boolean | null` Whether strict parameter validation is enforced for this function tool. - `type: "function"` The type of the function tool. Always `function`. - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` - `defer_loading?: boolean` Whether this function is deferred and loaded via tool search. - `description?: string | null` A description of the function. Used by the model to determine whether or not to call the function. - `output_schema?: Record | null` A JSON schema object describing the JSON value encoded in string outputs for this function. - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `type: "file_search"` The type of the file search tool. Always `file_search`. - `"file_search"` - `vector_store_ids: Array` The IDs of the vector stores to search. - `filters?: ComparisonFilter | CompoundFilter | null` A filter to apply. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` The key to compare against the value. - `type: "eq" | "ne" | "gt" | 5 more` Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`. - `eq`: equals - `ne`: not equal - `gt`: greater than - `gte`: greater than or equal - `lt`: less than - `lte`: less than or equal - `in`: in - `nin`: not in - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `"in"` - `"nin"` - `value: string | number | boolean | Array` The value to compare against the attribute key; supports string, number, or boolean types. - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `unknown` - `type: "and" | "or"` Type of operation: `and` or `or`. - `"and"` - `"or"` - `max_num_results?: number` The maximum number of results to return. This number should be between 1 and 50 inclusive. - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` The weight of the embedding in the reciprocal ranking fusion. - `text_weight: number` The weight of the text in the reciprocal ranking fusion. - `ranker?: "auto" | "default-2024-11-15"` The ranker to use for the file search. - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results. - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `type: "computer"` The type of the computer tool. Always `computer`. - `"computer"` - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `display_height: number` The height of the computer display. - `display_width: number` The width of the computer display. - `environment: "windows" | "mac" | "linux" | 2 more` The type of computer environment to control. - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` The type of the computer use tool. Always `computer_use_preview`. - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. - `"web_search"` - `"web_search_2025_08_26"` - `external_web_access?: boolean` Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content. - `filters?: Filters | null` Filters for the search. - `allowed_domains?: Array | null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. Example: `["pubmed.ncbi.nlm.nih.gov"]` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The approximate location of the user. - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `type?: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `server_label: string` A label for this MCP server, used to identify it in tool calls. - `type: "mcp"` The type of the MCP tool. Always `mcp`. - `"mcp"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `allowed_tools?: Array | McpToolFilter | null` List of allowed tool names or a filter object. - `Array` - `McpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `authorization?: string` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` 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](/api/docs/guides/tools-connectors-mcp#connectors). 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` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `defer_loading?: boolean` Whether this MCP tool is deferred and discovered via tool search. - `headers?: Record | null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval?: McpToolApprovalFilter | "always" | "never" | null` Specify which of the MCP server's tools require approval. - `McpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` Optional description of the MCP server, used to provide more context. - `server_url?: string` The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `tunnel_id?: string` The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterToolAuto` 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. - `string` - `CodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` Always `auto`. - `"auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the code interpreter container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `type: "disabled"` Disable outbound network access. Always `disabled`. - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` A list of allowed domains when type is `allowlist`. - `type: "allowlist"` Allow outbound network access only to specified domains. Always `allowlist`. - `"allowlist"` - `domain_secrets?: Array` Optional domain-scoped secrets for allowlisted domains. - `domain: string` The domain associated with the secret. - `name: string` The name of the secret to inject for the domain. - `value: string` The secret value to inject for the domain. - `type: "code_interpreter"` The type of the code interpreter tool. Always `code_interpreter`. - `"code_interpreter"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `ProgrammaticToolCalling` - `type: "programmatic_tool_calling"` The type of the tool. Always `programmatic_tool_calling`. - `"programmatic_tool_calling"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` The type of the image generation tool. Always `image_generation`. - `"image_generation"` - `action?: "generate" | "edit" | "auto"` Whether to generate a new image or edit an existing image. Default: `auto`. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`. - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low" | null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. 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`. - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` File ID for the mask image. - `image_url?: string` Base64-encoded mask image. - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` The image generation model to use. One of `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default: `gpt-image-1`. - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-2"` - `"gpt-image-2-2026-04-21"` - `"gpt-image-2.5-sunburst"` - `"gpt-image-2.5-sunburst-2026-09-08"` - `"gpt-image-2.5-flare"` - `"gpt-image-2.5-flare-2026-09-08"` - `"gpt-image-1.5"` - `"chatgpt-image-latest"` - `moderation?: "auto" | "low"` Moderation level for the generated image. Default: `auto`. - `"auto"` - `"low"` - `output_compression?: number` Compression level for the output image. Default: 100. - `output_format?: "png" | "webp" | "jpeg"` The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` Number of partial images to generate in streaming mode, from 0 (default value) to 3. - `quality?: "low" | "medium" | "high" | 3 more` The quality of the generated image. The GPT image models support `low`, `medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. Default: `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | "auto"` The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` The type of the local shell tool. Always `local_shell`. - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` The type of the shell tool. Always `shell`. - `"shell"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference | null` - `ContainerAuto` - `type: "container_auto"` Automatically creates a container for this request - `"container_auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` An optional list of skills referenced by id or inline data. - `SkillReference` - `skill_id: string` The ID of the referenced skill. - `type: "skill_reference"` References a skill created with the /v1/skills endpoint. - `"skill_reference"` - `version?: string` Optional skill version. Use a positive integer or 'latest'. Omit for default. - `InlineSkill` - `description: string` The description of the skill. - `name: string` The name of the skill. - `source: InlineSkillSource` Inline skill payload - `data: string` Base64-encoded skill zip bundle. - `media_type: "application/zip"` The media type of the inline skill payload. Must be `application/zip`. - `"application/zip"` - `type: "base64"` The type of the inline skill source. Must be `base64`. - `"base64"` - `type: "inline"` Defines an inline skill for this request. - `"inline"` - `LocalEnvironment` - `type: "local"` Use a local computer environment. - `"local"` - `skills?: Array` An optional list of skills. - `description: string` The description of the skill. - `name: string` The name of the skill. - `path: string` The path to the directory containing the skill. - `ContainerReference` - `container_id: string` The ID of the referenced container. - `type: "container_reference"` References a container created with the /v1/containers endpoint - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `name: string` The name of the custom tool, used to identify it in tool calls. - `type: "custom"` The type of the custom tool. Always `custom`. - `"custom"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this tool should be deferred and discovered via tool search. - `description?: string` Optional description of the custom tool, used to provide more context. - `format?: CustomToolInputFormat` The input format for the custom tool. Default is unconstrained text. - `Text` Unconstrained free-form text. - `type: "text"` Unconstrained text format. Always `text`. - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` The grammar definition. - `syntax: "lark" | "regex"` The syntax of the grammar definition. One of `lark` or `regex`. - `"lark"` - `"regex"` - `type: "grammar"` Grammar format. Always `grammar`. - `"grammar"` - `NamespaceTool` Groups function/custom tools under a shared namespace. - `description: string` A description of the namespace shown to the model. - `name: string` The namespace name used in tool calls (for example, `crm`). - `tools: Array` The function/custom tools available inside this namespace. - `Function` - `name: string` - `type: "function"` - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this function should be deferred and discovered via tool search. - `description?: string | null` - `output_schema?: Record | null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters?: unknown` - `strict?: boolean | null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `type: "namespace"` The type of the tool. Always `namespace`. - `"namespace"` - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `type: "tool_search"` The type of the tool. Always `tool_search`. - `"tool_search"` - `description?: string | null` Description shown to the model for a client-executed tool search tool. - `execution?: "server" | "client"` Whether tool search is executed by the server or by the client. - `"server"` - `"client"` - `parameters?: unknown` Parameter schema for a client-executed tool search tool. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search_preview" | "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`. - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_content_types?: Array<"text" | "image">` - `"text"` - `"image"` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The user's location. - `type: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` The type of the tool. Always `apply_patch`. - `"apply_patch"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `type: "tool_search_output"` The item type. Always `tool_search_output`. - `"tool_search_output"` - `id?: string | null` The unique ID of this tool search output. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search output. - `"in_progress"` - `"completed"` - `"incomplete"` - `AdditionalTools` - `role: "developer"` The role that provided the additional tools. Only `developer` is supported. - `"developer"` - `tools: Array` A list of additional tools made available at this item. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `ProgrammaticToolCalling` - `ImageGeneration` A tool that generates images using the GPT image models. - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `FunctionShellTool` A tool that allows the model to execute shell commands. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `NamespaceTool` Groups function/custom tools under a shared namespace. - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "additional_tools"` The item type. Always `additional_tools`. - `"additional_tools"` - `id?: string | null` The unique ID of this additional tools item. - `ResponseConfigurationUpdateItemParam` An update to the conversation's response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update. - `type: "configuration_update"` The item type. Always `configuration_update`. - `"configuration_update"` - `id?: string | null` The unique ID of the configuration update item. - `reasoning?: Reasoning` Updates to reasoning configuration. Only effort is supported. - `effort?: ReasoningEffort | null` The reasoning effort to use for subsequent responses until another configuration update replaces it. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `ResponseReasoningItem` 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](/api/docs/guides/conversation-state). - `id: string` The unique identifier of the reasoning content. - `summary: Array` Reasoning summary content. - `text: string` A summary of the reasoning output from the model so far. - `type: "summary_text"` The type of the object. Always `summary_text`. - `"summary_text"` - `type: "reasoning"` The type of the object. Always `reasoning`. - `"reasoning"` - `content?: Array` Reasoning text content. - `text: string` The reasoning text from the model. - `type: "reasoning_text"` The type of the reasoning text. Always `reasoning_text`. - `"reasoning_text"` - `encrypted_content?: string | null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket `response.create` requests. When streaming, use the completed reasoning item and its `encrypted_content` from the `response.output_item.done` event in subsequent requests. The `encrypted_content` in `response.output_item.added` may be incomplete. This is especially important when `store` is `false` or when using Zero Data Retention. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](/api/reference/resources/responses/methods/compact). - `encrypted_content: string` The encrypted content of the compaction summary. - `type: "compaction"` The type of the item. Always `compaction`. - `"compaction"` - `id?: string | null` The ID of the compaction item. - `ImageGenerationCall` An image generation request made by the model. - `id: string` The unique ID of the image generation call. - `result: string | null` The generated image encoded in base64. - `status: "in_progress" | "completed" | "generating" | "failed"` The status of the image generation call. - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` The type of the image generation call. Always `image_generation_call`. - `"image_generation_call"` - `action?: "generate" | "edit" | "auto" | null` The action used for image generation. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto" | null` The background setting used for generation. - `"transparent"` - `"opaque"` - `"auto"` - `output_format?: "png" | "webp" | "jpeg" | null` The output format used for generation. - `"png"` - `"webp"` - `"jpeg"` - `quality?: "low" | "medium" | "high" | 3 more | null` The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `revised_prompt?: string | null` The prompt that was used after any model prompt rewriting. - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | null` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `ResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` The unique ID of the code interpreter tool call. - `code: string | null` The code to run, or null if not available. - `container_id: string` The ID of the container used to run the code. - `outputs: Array | null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. - `Logs` The logs output from the code interpreter. - `logs: string` The logs output from the code interpreter. - `type: "logs"` The type of the output. Always `logs`. - `"logs"` - `Image` The image output from the code interpreter. - `type: "image"` The type of the output. Always `image`. - `"image"` - `url: string` The URL of the image output from the code interpreter. - `status: "in_progress" | "completed" | "incomplete" | 2 more` The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` The type of the code interpreter tool call. Always `code_interpreter_call`. - `"code_interpreter_call"` - `LocalShellCall` A tool call to run a command on the local shell. - `id: string` The unique ID of the local shell call. - `action: Action` Execute a shell command on the server. - `command: Array` The command to run. - `env: Record` Environment variables to set for the command. - `type: "exec"` The type of the local shell action. Always `exec`. - `"exec"` - `timeout_ms?: number | null` Optional timeout in milliseconds for the command. - `user?: string | null` Optional user to run the command as. - `working_directory?: string | null` Optional working directory to run the command in. - `call_id: string` The unique ID of the local shell tool call generated by the model. - `status: "in_progress" | "completed" | "incomplete"` The status of the local shell call. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` The type of the local shell call. Always `local_shell_call`. - `"local_shell_call"` - `LocalShellCallOutput` The output of a local shell tool call. - `id: string` The unique ID of the local shell tool call generated by the model. - `output: string` A JSON string of the output of the local shell tool call. - `type: "local_shell_call_output"` The type of the local shell tool call output. Always `local_shell_call_output`. - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` Ordered shell commands for the execution environment to run. - `max_output_length?: number | null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - `timeout_ms?: number | null` Maximum wall-clock time in milliseconds to allow the shell commands to run. - `call_id: string` The unique ID of the shell tool call generated by the model. - `type: "shell_call"` The type of the item. Always `shell_call`. - `"shell_call"` - `id?: string | null` The unique ID of the shell tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `environment?: LocalEnvironment | ContainerReference | null` The environment to execute the shell commands in. - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` The unique ID of the shell tool call generated by the model. - `output: Array` Captured chunks of stdout and stderr output, along with their associated outcomes. - `outcome: Timeout | Exit` The exit or timeout outcome associated with this shell call. - `Timeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` The outcome type. Always `timeout`. - `"timeout"` - `Exit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` The exit code returned by the shell process. - `type: "exit"` The outcome type. Always `exit`. - `"exit"` - `stderr: string` Captured stderr output for the shell call. - `stdout: string` Captured stdout output for the shell call. - `type: "shell_call_output"` The type of the item. Always `shell_call_output`. - `"shell_call_output"` - `id?: string | null` The unique ID of the shell tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `max_output_length?: number | null` The maximum number of UTF-8 characters captured for this shell call's combined output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call output. - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `operation: CreateFile | DeleteFile | UpdateFile` The specific create, delete, or update instruction for the apply_patch tool call. - `CreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` Unified diff content to apply when creating the file. - `path: string` Path of the file to create relative to the workspace root. - `type: "create_file"` The operation type. Always `create_file`. - `"create_file"` - `DeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` Path of the file to delete relative to the workspace root. - `type: "delete_file"` The operation type. Always `delete_file`. - `"delete_file"` - `UpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` Unified diff content to apply to the existing file. - `path: string` Path of the file to update relative to the workspace root. - `type: "update_file"` The operation type. Always `update_file`. - `"update_file"` - `status: "in_progress" | "completed"` The status of the apply patch tool call. One of `in_progress` or `completed`. - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` The type of the item. Always `apply_patch_call`. - `"apply_patch_call"` - `id?: string | null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `status: "completed" | "failed"` The status of the apply patch tool call output. One of `completed` or `failed`. - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` The type of the item. Always `apply_patch_call_output`. - `"apply_patch_call_output"` - `id?: string | null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `output?: string | null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). - `McpListTools` A list of tools available on an MCP server. - `id: string` The unique ID of the list. - `server_label: string` The label of the MCP server. - `tools: Array` The tools available on the server. - `input_schema: unknown` The JSON schema describing the tool's input. - `name: string` The name of the tool. - `annotations?: unknown` Additional annotations about the tool. - `description?: string | null` The description of the tool. - `type: "mcp_list_tools"` The type of the item. Always `mcp_list_tools`. - `"mcp_list_tools"` - `error?: string | null` Error message if the server could not list tools. - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` The unique ID of the approval request. - `arguments: string` A JSON string of arguments for the tool. - `name: string` The name of the tool to run. - `server_label: string` The label of the MCP server making the request. - `type: "mcp_approval_request"` The type of the item. Always `mcp_approval_request`. - `"mcp_approval_request"` - `McpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` The ID of the approval request being answered. - `approve: boolean` Whether the request was approved. - `type: "mcp_approval_response"` The type of the item. Always `mcp_approval_response`. - `"mcp_approval_response"` - `id?: string | null` The unique ID of the approval response - `reason?: string | null` Optional reason for the decision. - `McpCall` An invocation of a tool on an MCP server. - `id: string` The unique ID of the tool call. - `arguments: string` A JSON string of the arguments passed to the tool. - `name: string` The name of the tool that was run. - `server_label: string` The label of the MCP server running the tool. - `type: "mcp_call"` The type of the item. Always `mcp_call`. - `"mcp_call"` - `approval_request_id?: string | null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - `error?: McpToolCallError | null` The error from the tool call, if any. - `McpProtocolError` - `code: number` - `message: string` - `type: "mcp_protocol_error"` - `"mcp_protocol_error"` - `McpToolExecutionError` - `content: unknown` - `type: "mcp_tool_execution_error"` - `"mcp_tool_execution_error"` - `HTTPError` - `code: number` - `message: string` - `type: "http_error"` - `"http_error"` - `output?: string | null` The output from the tool call. - `status?: "in_progress" | "completed" | "incomplete" | 2 more` The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `ResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` The call ID, used to map this custom tool call output to a custom tool call. - `output: string | Array` The output from the custom tool call generated by your code. Can be a string or an list of output content. - `string` - `Array` - `ResponseInputText` A text input to the model. - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `ResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` The type of the custom tool call output. Always `custom_tool_call_output`. - `"custom_tool_call_output"` - `id?: string` The unique ID of the custom tool call output in the OpenAI platform. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` An identifier used to map this custom tool call to a tool call output. - `input: string` The input for the custom tool call generated by the model. - `name: string` The name of the custom tool being called. - `type: "custom_tool_call"` The type of the custom tool call. Always `custom_tool_call`. - `"custom_tool_call"` - `id?: string` The unique ID of the custom tool call in the OpenAI platform. - `async?: boolean` Whether the custom tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the custom tool being called. - `CompactionTrigger` Compacts the current context. Must be the final input item. - `type: "compaction_trigger"` The type of the item. Always `compaction_trigger`. - `"compaction_trigger"` - `ItemReference` An internal identifier for an item to reference. - `id: string` The ID of the item to reference. - `type?: "item_reference" | null` The type of item to reference. Always `item_reference`. - `"item_reference"` - `Program` - `id: string` The unique ID of this program item. - `call_id: string` The stable call ID of the program item. - `code: string` The JavaScript source executed by programmatic tool calling. - `fingerprint: string` Opaque program replay fingerprint that must be round-tripped. - `type: "program"` The item type. Always `program`. - `"program"` - `ProgramOutput` - `id: string` The unique ID of this program output item. - `call_id: string` The call ID of the program item. - `result: string` The result produced by the program item. - `status: "completed" | "incomplete"` The terminal status of the program output. - `"completed"` - `"incomplete"` - `type: "program_output"` The item type. Always `program_output`. - `"program_output"` - `type: "response.item.create"` The Live client event type. Always `response.item.create`. - `"response.item.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Responses Delegation Config - `ResponsesDelegationConfig` Model, prompt, and tool settings for tasks delegated by the Live session to a Responses backend. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` ### Responses Delegation Update Config - `ResponsesDelegationUpdateConfig` Updates to the Responses backend of an existing Live session. Omitted settings retain their current values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` ### Server Event - `ServerEvent = SessionStartedEvent | SessionUpdatedEvent | InputAudioMutedEvent | 19 more` Server events for Live. Response lifecycle events are wrapped inside response.event; dispatch the nested event by its full type and tolerate new response event types. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when designing the conversation and delegation policy. - `SessionStartedEvent` Returned when a Live session has started. Contains the resolved session configuration, including server defaults. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.started"` The event type, always `session.started`. - `"session.started"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `SessionUpdatedEvent` Returned when a Live session update is accepted. Contains the resolved session configuration after the update. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.updated"` The event type, always `session.updated`. - `"session.updated"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioMutedEvent` Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.muted"` The event type, always `session.input_audio.muted`. - `"session.input_audio.muted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioUnmutedEvent` Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.unmuted"` The event type, always `session.input_audio.unmuted`. - `"session.input_audio.unmuted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InstructionsAppendedEvent` Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.instructions.appended"` The event type, always `session.instructions.appended`. - `"session.instructions.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ThinkingAppendedEvent` Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.thinking.appended"` The event type, always `session.thinking.appended`. - `"session.thinking.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `CommentaryAppendedEvent` Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.commentary.appended"` The event type, always `session.commentary.appended`. - `"session.commentary.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `SessionInputAudioAppend` Input audio received from the primary transport and reflected to a Live sideband connection before model-input muting. - `audio: string` Base64-encoded raw mono PCM16LE at 24 kHz received from the primary transport, reflected to the sideband before model-input muting. This server event uses the same audio key as the client command, but is not an acknowledgment of it. - `type: "session.input_audio.append"` The event type, always `session.input_audio.append`. - `"session.input_audio.append"` - `OutputAudioDeltaEvent` An audio chunk generated by the Live model. Decode and play primary WebSocket chunks in delivery order using the configured session audio format. Sideband connections receive reflected output audio with timestamps. - `delta: string` Base64-encoded raw audio. Primary WebSocket events use the session's configured format; reflected sideband events use mono PCM16LE at 24 kHz. - `type: "session.output_audio.delta"` The event type, always `session.output_audio.delta`. - `"session.output_audio.delta"` - `end_ms?: number` Exclusive session-relative end in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. Dropped output frames leave gaps between reflected ranges. - `start_ms?: number` Inclusive session-relative start in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. - `InputTranscriptDeltaEvent` A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.input_transcript.delta"` The event type, always `session.input_transcript.delta`. - `"session.input_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `OutputTranscriptDeltaEvent` A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.output_transcript.delta"` The event type, always `session.output_transcript.delta`. - `"session.output_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `DelegationCreatedEvent` Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated. - `delegation: Delegation` The delegated work identifier and destination. This object contains metadata, not the task text. - `id: string` The unique ID of the delegation. Use this as delegation_id when replying to client-owned work or correlating Responses events. - `target: "client" | "responses"` Where the Live model delegated the work: `client` for your application, or `responses` for the configured Responses backend. - `"client" | "responses"` - `"client"` - `"responses"` - `type: "delegation"` The object type, always `delegation`. - `"delegation"` - `response_id?: string` The ID of the Responses API response associated with a Responses delegation. Omitted for client delegations. - `event_id: string` The unique ID of the Live server event. - `offset_ms: number` The position on the Live session timeline where the delegation was created, in milliseconds from the beginning of the session. - `type: "session.delegation.created"` The event type, always `session.delegation.created`. - `"session.delegation.created"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ResponseEvent` A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation. - `event: Record` The nested Responses streaming event. Dispatch on its type field. Response lifecycle snapshots omit input and clear instructions, tools, and output to keep messages small; consume granular output events for the generated content. - `event_id: string` The unique ID of the Live server event. - `type: "response.event"` The event type, always `response.event`. - `"response.event"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `delegation_id?: string | null` The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation. - `SessionUsageUpdatedEvent` Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events. - `event_id: string` The unique ID of the Live server event. - `type: "session.usage.updated"` The event type, always `session.usage.updated`. - `"session.usage.updated"` - `usage: SessionUsage` The cumulative Live audio usage so far. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `context_window?: ContextWindow` The latest measured Live context-window usage. Omitted when the context limit is unknown. - `usage_ratio: number` The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames. - `SessionClosedEvent` Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization. - `event_id: string` The unique ID of the Live server event. - `reason: "close_requested" | "expired" | "content" | 2 more` Why the Live session ended: `close_requested` for an application close or hangup request, `expired` for the session duration limit, `content` for a safety filter, `remote_hangup` for a graceful remote disconnect, or `connection_lost` for an unexpected primary or upstream disconnection. - `"close_requested" | "expired" | "content" | 2 more` - `"close_requested"` - `"expired"` - `"content"` - `"remote_hangup"` - `"connection_lost"` - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.closed"` The event type, always `session.closed`. - `"session.closed"` - `usage: SessionUsage` The final cumulative Live audio usage after session finalization. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ErrorEvent` Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error. - `error: Error` Details of the Live error and the client command that caused it, when known. - `code: string` A machine-readable code identifying the Live error, such as `unknown_parameter`. - `message: string` A human-readable explanation of the Live error. - `type: string` The category of error, such as `invalid_request_error` for an invalid Live client command. - `client_event_id?: string` The event_id of the client command that caused the error, when supplied. - `param?: string` The parameter that caused the error, when applicable, such as `session.voice`. - `event_id: string` The unique ID of the Live server event. - `type: "error"` The event type, always `error`. - `"error"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InfoEvent` An informational notice about the Live session, such as the event permissions applied to a frontend data channel. - `code: string` A machine-readable code for the notice, such as `data_channel_permissions`. - `event_id: string` The unique ID of the Live server event. - `message: string` A human-readable explanation of the Live session notice. - `type: "info"` The event type, always `info`. - `"info"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `TransportDtmfReceived` A SIP DTMF keypress received from the caller. Delivered only to sideband observers. - `event: string` - `event_id: string` - `type: "transport.dtmf.received"` - `"transport.dtmf.received"` - `TransportDtmfSend` A SIP DTMF keypress successfully sent by the hosted tool. Delivered only to sideband observers; this is not a client command. - `event: string` - `event_id: string` - `type: "transport.dtmf.send"` - `"transport.dtmf.send"` - `TransportRinging` The outbound SIP provider leg is ringing or providing early media. Delivered only to sideband observers. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.ringing"` - `"transport.ringing"` - `TransportAnswered` The outbound SIP provider leg answered and media is established. Delivered only to sideband observers. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.answered"` - `"transport.answered"` - `TransportFailed` An asynchronous outbound SIP setup failure. Delivered only to sideband observers. - `error: Error` - `code: string` The call setup failure code. - `message: string` - `type: "call_error"` - `"call_error"` - `param?: string` The parameter related to the error, if any. Empty when no parameter applies. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.failed"` - `"transport.failed"` ### Server Event Selector - `ServerEventSelector` A Live server event selector for the WebRTC frontend data channel. - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. ### Session Close Event - `SessionCloseEvent` Request that the Live session close. The terminal `session.closed` event contains the close reason and final usage. - `type: "session.close"` The Live client event type. Always `session.close`. - `"session.close"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Session Closed Event - `SessionClosedEvent` Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization. - `event_id: string` The unique ID of the Live server event. - `reason: "close_requested" | "expired" | "content" | 2 more` Why the Live session ended: `close_requested` for an application close or hangup request, `expired` for the session duration limit, `content` for a safety filter, `remote_hangup` for a graceful remote disconnect, or `connection_lost` for an unexpected primary or upstream disconnection. - `"close_requested" | "expired" | "content" | 2 more` - `"close_requested"` - `"expired"` - `"content"` - `"remote_hangup"` - `"connection_lost"` - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.closed"` The event type, always `session.closed`. - `"session.closed"` - `usage: SessionUsage` The final cumulative Live audio usage after session finalization. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Session Config - `SessionConfig` Initial configuration for a Live session, including its model, conversation instructions, audio, and delegated task handling. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. ### Session Resource - `SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. ### Session Start Event - `SessionStartEvent` Start a Live session on a primary WebSocket. Send this event before other commands and wait for `session.started`. - `session: SessionConfig` Initial configuration for a primary WebSocket. Send session.start first and wait for session.started before application commands. WebRTC creation already starts the session; do not send this event again on its data channel. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.start"` The Live client event type. Always `session.start`. - `"session.start"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Session Started Event - `SessionStartedEvent` Returned when a Live session has started. Contains the resolved session configuration, including server defaults. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.started"` The event type, always `session.started`. - `"session.started"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Session Update Config - `SessionUpdateConfig` Changes to an active Live session. Only delegation backend settings can be updated after startup. - `delegation?: ClientDelegation | Responses | null` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` ### Session Update Event - `SessionUpdateEvent` Update the delegation settings of an active Live session. The server acknowledges accepted changes with `session.updated`. - `session: SessionUpdateConfig` Sparse delegation updates. Omitted settings retain their values. The delegation type cannot change, including resetting Responses delegation to null or client. Model, frontend instructions, audio, and startup input are immutable. - `delegation?: ClientDelegation | Responses | null` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "session.update"` The Live client event type. Always `session.update`. - `"session.update"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Session Updated Event - `SessionUpdatedEvent` Returned when a Live session update is accepted. Contains the resolved session configuration after the update. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.updated"` The event type, always `session.updated`. - `"session.updated"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. ### Session Usage - `SessionUsage` Cumulative audio duration for a Live session. Values are totals for the session, not increments to sum across usage events. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. ### Session Usage Updated Event - `SessionUsageUpdatedEvent` Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events. - `event_id: string` The unique ID of the Live server event. - `type: "session.usage.updated"` The event type, always `session.usage.updated`. - `"session.usage.updated"` - `usage: SessionUsage` The cumulative Live audio usage so far. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `context_window?: ContextWindow` The latest measured Live context-window usage. Omitted when the context limit is unknown. - `usage_ratio: number` The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames. ### Thinking Append Event - `ThinkingAppendEvent` Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation. - `content: string` Silent reasoning or progress context, limited to 500 tokens. It does not directly request speech, but can influence later speech and is not a secrecy boundary. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.thinking.append"` The Live client event type. Always `session.thinking.append`. - `"session.thinking.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Thinking Appended Event - `ThinkingAppendedEvent` Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.thinking.appended"` The event type, always `session.thinking.appended`. - `"session.thinking.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. # Forks ## `client.live.forks.connect(RequestOptionsoptions?): void` **** `` Fork a stored Live session over WebSocket. Send session.start with an overrides object (which may be empty), then wait for session.started. The model is inherited. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.forks.connect(); ``` ## Domain Types ### Fork Client Event - `ForkClientEvent = ForkSessionStartEvent | SessionUpdateEvent | InputAudioAppendEvent | 8 more` Client events for a Live fork WebSocket. First send session.start with an overrides object (which may be empty), then wait for session.started before sending other commands. The model and conversation are inherited from the stored session. - `ForkSessionStartEvent` Start a Live session after connecting to a stored session’s fork WebSocket. Send an empty `session` object to use the stored configuration. - `session: ForkSessionConfig` Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks. - `audio?: Audio` Audio format for a WebSocket fork. WebRTC forks negotiate their audio format and must omit this field. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `client?: ClientConfig` Frontend data-channel permissions for a WebRTC fork. Omitted permissions inherit the stored values. Not supported for WebSocket forks. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: Delegation` Overrides for the stored session’s Responses backend. Only supported when the stored session already uses Responses delegation; the delegation type cannot change. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `store?: boolean` Whether to store the forked session. Omission inherits the stored session's setting. - `type: "session.start"` The Live client event type. Always `session.start`. - `"session.start"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `SessionUpdateEvent` Update the delegation settings of an active Live session. The server acknowledges accepted changes with `session.updated`. - `session: SessionUpdateConfig` Sparse delegation updates. Omitted settings retain their values. The delegation type cannot change, including resetting Responses delegation to null or client. Model, frontend instructions, audio, and startup input are immutable. - `delegation?: ClientDelegation | Responses | null` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `type: "session.update"` The Live client event type. Always `session.update`. - `"session.update"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioAppendEvent` Send audio to a Live session over its primary WebSocket. WebRTC and SIP sessions send audio over their media transport. - `audio: string` Base64-encoded raw audio in the startup-selected format, without a WAV or other container header. Primary WebSocket only; media transports use their audio track. Audio appends have no acknowledgment. Reflected sideband server events reuse this event type and audio key, with no timestamps or event_id; their audio is always mono PCM16LE at 24 kHz. - `type: "session.input_audio.append"` The Live client event type. Always `session.input_audio.append`. - `"session.input_audio.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioMuteEvent` Mute audio input to the Live model without closing the session. The server acknowledges with `session.input_audio.muted`. - `type: "session.input_audio.mute"` The Live client event type. Always `session.input_audio.mute`. - `"session.input_audio.mute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioUnmuteEvent` Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`. - `type: "session.input_audio.unmute"` The Live client event type. Always `session.input_audio.unmute`. - `"session.input_audio.unmute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InstructionsAppendEvent` Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation. - `content: string` Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.instructions.append"` The Live client event type. Always `session.instructions.append`. - `"session.instructions.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ThinkingAppendEvent` Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation. - `content: string` Silent reasoning or progress context, limited to 500 tokens. It does not directly request speech, but can influence later speech and is not a secrecy boundary. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.thinking.append"` The Live client event type. Always `session.thinking.append`. - `"session.thinking.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `CommentaryAppendEvent` Provide context the Live model can communicate to the user, optionally for an existing client delegation. - `content: string` Speakable context for the Live model, limited to 500 tokens. Use this for a result the model should communicate; use session.thinking.append for silent context. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.commentary.append"` The Live client event type. Always `session.commentary.append`. - `"session.commentary.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseItemCreateEvent` Add an input item to the Live session’s Responses backend. Requires Responses delegation; use `response.create` to request a response. - `item: ResponseInputItem` An input item to append to the Responses backend conversation, such as a user message or a function tool result. - `EasyInputMessage` A message input to the model with a role indicating instruction following hierarchy. Instructions given with the `developer` or `system` role take precedence over instructions given with the `user` role. Messages with the `assistant` role are presumed to have been generated by the model in previous interactions. - `content: string | ResponseInputMessageContentList` Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. - `string` - `ResponseInputMessageContentList = Array` A list of one or many input items to the model, containing different content types. - `ResponseInputText` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `detail: ImageDetail` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `"low"` - `"high"` - `"auto"` - `"original"` - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFile` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string` The content of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string` The URL of the file to be sent to the model. - `filename?: string` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `role: "user" | "assistant" | "system" | "developer"` The role of the message input. One of `user`, `assistant`, `system`, or `developer`. - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `type?: "message"` The type of the message input. Always `message`. - `"message"` - `Message` 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. - `content: ResponseInputMessageContentList` A list of one or many input items to the model, containing different content types. - `role: "user" | "system" | "developer"` The role of the message input. One of `user`, `system`, or `developer`. - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` The type of the message input. Always set to `message`. - `"message"` - `ResponseOutputMessage` An output message from the model. - `id: string` The unique ID of the output message. - `content: Array` The content of the output message. - `ResponseOutputText` A text output from the model. - `annotations: Array` The annotations of the text output. - `FileCitation` A citation to a file. - `file_id: string` The ID of the file. - `filename: string` The filename of the file cited. - `index: number` The index of the file in the list of files. - `type: "file_citation"` The type of the file citation. Always `file_citation`. - `"file_citation"` - `URLCitation` A citation for a web resource used to generate a model response. - `end_index: number` The index of the last character of the URL citation in the message. - `start_index: number` The index of the first character of the URL citation in the message. - `title: string` The title of the web resource. - `type: "url_citation"` The type of the URL citation. Always `url_citation`. - `"url_citation"` - `url: string` The URL of the web resource. - `ContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` The ID of the container file. - `end_index: number` The index of the last character of the container file citation in the message. - `file_id: string` The ID of the file. - `filename: string` The filename of the container file cited. - `start_index: number` The index of the first character of the container file citation in the message. - `type: "container_file_citation"` The type of the container file citation. Always `container_file_citation`. - `"container_file_citation"` - `FilePath` A path to a file. - `file_id: string` The ID of the file. - `index: number` The index of the file in the list of files. - `type: "file_path"` The type of the file path. Always `file_path`. - `"file_path"` - `text: string` The text output from the model. - `type: "output_text"` The type of the output text. Always `output_text`. - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `ResponseOutputRefusal` A refusal from the model. - `refusal: string` The refusal explanation from the model. - `type: "refusal"` The type of the refusal. Always `refusal`. - `"refusal"` - `role: "assistant"` The role of the output message. Always `assistant`. - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` The type of the output message. Always `message`. - `"message"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `ResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](/api/docs/guides/tools-file-search) for more information. - `id: string` The unique ID of the file search tool call. - `queries: Array` The queries used to search for files. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` The type of the file search tool call. Always `file_search_call`. - `"file_search_call"` - `results?: Array | null` The results of the file search tool call. - `attributes?: Record | null` Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers. - `string` - `number` - `boolean` - `file_id?: string` The unique ID of the file. - `filename?: string` The name of the file. - `score?: number` The relevance score of the file - a value between 0 and 1. - `text?: string` The text that was retrieved from the file. - `ResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](/api/docs/guides/tools-computer-use) for more information. - `id: string` The unique ID of the computer call. - `call_id: string` An identifier used when responding to the tool call with output. - `pending_safety_checks: Array` The pending safety checks for the computer call. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` The type of the computer call. Always `computer_call`. - `"computer_call"` - `action?: Click | DoubleClick | Drag | 6 more` A click action. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `actions?: ComputerActionList` Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `ComputerCallOutput` The output of a computer tool call. - `call_id: string` The ID of the computer tool call that produced the output. - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. - `"computer_screenshot"` - `file_id?: string` The identifier of an uploaded file that contains the screenshot. - `image_url?: string` The URL of the screenshot image. - `type: "computer_call_output"` The type of the computer tool call output. Always `computer_call_output`. - `"computer_call_output"` - `id?: string | null` The ID of the computer tool call output. - `acknowledged_safety_checks?: Array | null` The safety checks reported by the API that have been acknowledged by the developer. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](/api/docs/guides/tools-web-search) for more information. - `id: string` The unique ID of the web search tool call. - `action: Search | OpenPage | FindInPage` 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). - `Search` Action type "search" - Performs a web search query. - `type: "search"` The action type. - `"search"` - `queries?: Array` The search queries. - `query?: string` The search query. - `sources?: Array` The sources used in the search. - `type: "url"` The type of source. Always `url`. - `"url"` - `url: string` The URL of the source. - `OpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` The action type. - `"open_page"` - `url?: string | null` The URL opened by the model. - `FindInPage` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` The pattern or text to search for within the page. - `type: "find_in_page"` The action type. - `"find_in_page"` - `url: string` The URL of the page searched for the pattern. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the web search tool call. - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `"incomplete"` - `type: "web_search_call"` The type of the web search tool call. Always `web_search_call`. - `"web_search_call"` - `ResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](/api/docs/guides/function-calling) for more information. - `arguments: string` A JSON string of the arguments to pass to the function. - `call_id: string` The unique ID of the function tool call generated by the model. - `name: string` The name of the function to run. - `type: "function_call"` The type of the function tool call. Always `function_call`. - `"function_call"` - `id?: string` The unique ID of the function tool call. - `async?: boolean` Whether the function tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the function to run. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `FunctionCallOutput` The output of a function tool call. - `output: string | ResponseFunctionCallOutputItemList` Text, image, or file output of the function tool call. - `string` - `ResponseFunctionCallOutputItemList = Array` An array of content outputs (text, image, file) for the function tool call. - `ResponseInputTextContent` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision) - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `detail?: ImageDetail | null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string | null` The base64-encoded data of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string | null` The URL of the file to be sent to the model. - `filename?: string | null` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `type: "function_call_output"` The type of the function tool call output. Always `function_call_output`. - `"function_call_output"` - `id?: string | null` The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id?: string | null` The unique ID of the function tool call generated by the model. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `name?: string | null` The name of the tool that produced the output. - `namespace?: string | null` The namespace of the tool that produced the output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ToolSearchCall` - `arguments: unknown` The arguments supplied to the tool search call. - `type: "tool_search_call"` The item type. Always `tool_search_call`. - `"tool_search_call"` - `id?: string | null` The unique ID of this tool search call. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search call. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseToolSearchOutputItemParam` - `tools: Array` The loaded tool definitions returned by the tool search output. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `name: string` The name of the function to call. - `parameters: Record | null` A JSON schema object describing the parameters of the function. - `strict: boolean | null` Whether strict parameter validation is enforced for this function tool. - `type: "function"` The type of the function tool. Always `function`. - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` - `defer_loading?: boolean` Whether this function is deferred and loaded via tool search. - `description?: string | null` A description of the function. Used by the model to determine whether or not to call the function. - `output_schema?: Record | null` A JSON schema object describing the JSON value encoded in string outputs for this function. - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `type: "file_search"` The type of the file search tool. Always `file_search`. - `"file_search"` - `vector_store_ids: Array` The IDs of the vector stores to search. - `filters?: ComparisonFilter | CompoundFilter | null` A filter to apply. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` The key to compare against the value. - `type: "eq" | "ne" | "gt" | 5 more` Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`. - `eq`: equals - `ne`: not equal - `gt`: greater than - `gte`: greater than or equal - `lt`: less than - `lte`: less than or equal - `in`: in - `nin`: not in - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `"in"` - `"nin"` - `value: string | number | boolean | Array` The value to compare against the attribute key; supports string, number, or boolean types. - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `unknown` - `type: "and" | "or"` Type of operation: `and` or `or`. - `"and"` - `"or"` - `max_num_results?: number` The maximum number of results to return. This number should be between 1 and 50 inclusive. - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` The weight of the embedding in the reciprocal ranking fusion. - `text_weight: number` The weight of the text in the reciprocal ranking fusion. - `ranker?: "auto" | "default-2024-11-15"` The ranker to use for the file search. - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results. - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `type: "computer"` The type of the computer tool. Always `computer`. - `"computer"` - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `display_height: number` The height of the computer display. - `display_width: number` The width of the computer display. - `environment: "windows" | "mac" | "linux" | 2 more` The type of computer environment to control. - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` The type of the computer use tool. Always `computer_use_preview`. - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. - `"web_search"` - `"web_search_2025_08_26"` - `external_web_access?: boolean` Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content. - `filters?: Filters | null` Filters for the search. - `allowed_domains?: Array | null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. Example: `["pubmed.ncbi.nlm.nih.gov"]` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The approximate location of the user. - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `type?: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `server_label: string` A label for this MCP server, used to identify it in tool calls. - `type: "mcp"` The type of the MCP tool. Always `mcp`. - `"mcp"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `allowed_tools?: Array | McpToolFilter | null` List of allowed tool names or a filter object. - `Array` - `McpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `authorization?: string` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` 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](/api/docs/guides/tools-connectors-mcp#connectors). 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` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `defer_loading?: boolean` Whether this MCP tool is deferred and discovered via tool search. - `headers?: Record | null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval?: McpToolApprovalFilter | "always" | "never" | null` Specify which of the MCP server's tools require approval. - `McpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` Optional description of the MCP server, used to provide more context. - `server_url?: string` The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `tunnel_id?: string` The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterToolAuto` 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. - `string` - `CodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` Always `auto`. - `"auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the code interpreter container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `type: "disabled"` Disable outbound network access. Always `disabled`. - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` A list of allowed domains when type is `allowlist`. - `type: "allowlist"` Allow outbound network access only to specified domains. Always `allowlist`. - `"allowlist"` - `domain_secrets?: Array` Optional domain-scoped secrets for allowlisted domains. - `domain: string` The domain associated with the secret. - `name: string` The name of the secret to inject for the domain. - `value: string` The secret value to inject for the domain. - `type: "code_interpreter"` The type of the code interpreter tool. Always `code_interpreter`. - `"code_interpreter"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `ProgrammaticToolCalling` - `type: "programmatic_tool_calling"` The type of the tool. Always `programmatic_tool_calling`. - `"programmatic_tool_calling"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` The type of the image generation tool. Always `image_generation`. - `"image_generation"` - `action?: "generate" | "edit" | "auto"` Whether to generate a new image or edit an existing image. Default: `auto`. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`. - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low" | null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. 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`. - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` File ID for the mask image. - `image_url?: string` Base64-encoded mask image. - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` The image generation model to use. One of `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default: `gpt-image-1`. - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-2"` - `"gpt-image-2-2026-04-21"` - `"gpt-image-2.5-sunburst"` - `"gpt-image-2.5-sunburst-2026-09-08"` - `"gpt-image-2.5-flare"` - `"gpt-image-2.5-flare-2026-09-08"` - `"gpt-image-1.5"` - `"chatgpt-image-latest"` - `moderation?: "auto" | "low"` Moderation level for the generated image. Default: `auto`. - `"auto"` - `"low"` - `output_compression?: number` Compression level for the output image. Default: 100. - `output_format?: "png" | "webp" | "jpeg"` The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` Number of partial images to generate in streaming mode, from 0 (default value) to 3. - `quality?: "low" | "medium" | "high" | 3 more` The quality of the generated image. The GPT image models support `low`, `medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. Default: `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | "auto"` The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` The type of the local shell tool. Always `local_shell`. - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` The type of the shell tool. Always `shell`. - `"shell"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference | null` - `ContainerAuto` - `type: "container_auto"` Automatically creates a container for this request - `"container_auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` An optional list of skills referenced by id or inline data. - `SkillReference` - `skill_id: string` The ID of the referenced skill. - `type: "skill_reference"` References a skill created with the /v1/skills endpoint. - `"skill_reference"` - `version?: string` Optional skill version. Use a positive integer or 'latest'. Omit for default. - `InlineSkill` - `description: string` The description of the skill. - `name: string` The name of the skill. - `source: InlineSkillSource` Inline skill payload - `data: string` Base64-encoded skill zip bundle. - `media_type: "application/zip"` The media type of the inline skill payload. Must be `application/zip`. - `"application/zip"` - `type: "base64"` The type of the inline skill source. Must be `base64`. - `"base64"` - `type: "inline"` Defines an inline skill for this request. - `"inline"` - `LocalEnvironment` - `type: "local"` Use a local computer environment. - `"local"` - `skills?: Array` An optional list of skills. - `description: string` The description of the skill. - `name: string` The name of the skill. - `path: string` The path to the directory containing the skill. - `ContainerReference` - `container_id: string` The ID of the referenced container. - `type: "container_reference"` References a container created with the /v1/containers endpoint - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `name: string` The name of the custom tool, used to identify it in tool calls. - `type: "custom"` The type of the custom tool. Always `custom`. - `"custom"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this tool should be deferred and discovered via tool search. - `description?: string` Optional description of the custom tool, used to provide more context. - `format?: CustomToolInputFormat` The input format for the custom tool. Default is unconstrained text. - `Text` Unconstrained free-form text. - `type: "text"` Unconstrained text format. Always `text`. - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` The grammar definition. - `syntax: "lark" | "regex"` The syntax of the grammar definition. One of `lark` or `regex`. - `"lark"` - `"regex"` - `type: "grammar"` Grammar format. Always `grammar`. - `"grammar"` - `NamespaceTool` Groups function/custom tools under a shared namespace. - `description: string` A description of the namespace shown to the model. - `name: string` The namespace name used in tool calls (for example, `crm`). - `tools: Array` The function/custom tools available inside this namespace. - `Function` - `name: string` - `type: "function"` - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this function should be deferred and discovered via tool search. - `description?: string | null` - `output_schema?: Record | null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters?: unknown` - `strict?: boolean | null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `type: "namespace"` The type of the tool. Always `namespace`. - `"namespace"` - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `type: "tool_search"` The type of the tool. Always `tool_search`. - `"tool_search"` - `description?: string | null` Description shown to the model for a client-executed tool search tool. - `execution?: "server" | "client"` Whether tool search is executed by the server or by the client. - `"server"` - `"client"` - `parameters?: unknown` Parameter schema for a client-executed tool search tool. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search_preview" | "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`. - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_content_types?: Array<"text" | "image">` - `"text"` - `"image"` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The user's location. - `type: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` The type of the tool. Always `apply_patch`. - `"apply_patch"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `type: "tool_search_output"` The item type. Always `tool_search_output`. - `"tool_search_output"` - `id?: string | null` The unique ID of this tool search output. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search output. - `"in_progress"` - `"completed"` - `"incomplete"` - `AdditionalTools` - `role: "developer"` The role that provided the additional tools. Only `developer` is supported. - `"developer"` - `tools: Array` A list of additional tools made available at this item. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `ProgrammaticToolCalling` - `ImageGeneration` A tool that generates images using the GPT image models. - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `FunctionShellTool` A tool that allows the model to execute shell commands. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `NamespaceTool` Groups function/custom tools under a shared namespace. - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "additional_tools"` The item type. Always `additional_tools`. - `"additional_tools"` - `id?: string | null` The unique ID of this additional tools item. - `ResponseConfigurationUpdateItemParam` An update to the conversation's response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update. - `type: "configuration_update"` The item type. Always `configuration_update`. - `"configuration_update"` - `id?: string | null` The unique ID of the configuration update item. - `reasoning?: Reasoning` Updates to reasoning configuration. Only effort is supported. - `effort?: ReasoningEffort | null` The reasoning effort to use for subsequent responses until another configuration update replaces it. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `ResponseReasoningItem` 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](/api/docs/guides/conversation-state). - `id: string` The unique identifier of the reasoning content. - `summary: Array` Reasoning summary content. - `text: string` A summary of the reasoning output from the model so far. - `type: "summary_text"` The type of the object. Always `summary_text`. - `"summary_text"` - `type: "reasoning"` The type of the object. Always `reasoning`. - `"reasoning"` - `content?: Array` Reasoning text content. - `text: string` The reasoning text from the model. - `type: "reasoning_text"` The type of the reasoning text. Always `reasoning_text`. - `"reasoning_text"` - `encrypted_content?: string | null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket `response.create` requests. When streaming, use the completed reasoning item and its `encrypted_content` from the `response.output_item.done` event in subsequent requests. The `encrypted_content` in `response.output_item.added` may be incomplete. This is especially important when `store` is `false` or when using Zero Data Retention. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](/api/reference/resources/responses/methods/compact). - `encrypted_content: string` The encrypted content of the compaction summary. - `type: "compaction"` The type of the item. Always `compaction`. - `"compaction"` - `id?: string | null` The ID of the compaction item. - `ImageGenerationCall` An image generation request made by the model. - `id: string` The unique ID of the image generation call. - `result: string | null` The generated image encoded in base64. - `status: "in_progress" | "completed" | "generating" | "failed"` The status of the image generation call. - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` The type of the image generation call. Always `image_generation_call`. - `"image_generation_call"` - `action?: "generate" | "edit" | "auto" | null` The action used for image generation. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto" | null` The background setting used for generation. - `"transparent"` - `"opaque"` - `"auto"` - `output_format?: "png" | "webp" | "jpeg" | null` The output format used for generation. - `"png"` - `"webp"` - `"jpeg"` - `quality?: "low" | "medium" | "high" | 3 more | null` The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `revised_prompt?: string | null` The prompt that was used after any model prompt rewriting. - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | null` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `ResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` The unique ID of the code interpreter tool call. - `code: string | null` The code to run, or null if not available. - `container_id: string` The ID of the container used to run the code. - `outputs: Array | null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. - `Logs` The logs output from the code interpreter. - `logs: string` The logs output from the code interpreter. - `type: "logs"` The type of the output. Always `logs`. - `"logs"` - `Image` The image output from the code interpreter. - `type: "image"` The type of the output. Always `image`. - `"image"` - `url: string` The URL of the image output from the code interpreter. - `status: "in_progress" | "completed" | "incomplete" | 2 more` The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` The type of the code interpreter tool call. Always `code_interpreter_call`. - `"code_interpreter_call"` - `LocalShellCall` A tool call to run a command on the local shell. - `id: string` The unique ID of the local shell call. - `action: Action` Execute a shell command on the server. - `command: Array` The command to run. - `env: Record` Environment variables to set for the command. - `type: "exec"` The type of the local shell action. Always `exec`. - `"exec"` - `timeout_ms?: number | null` Optional timeout in milliseconds for the command. - `user?: string | null` Optional user to run the command as. - `working_directory?: string | null` Optional working directory to run the command in. - `call_id: string` The unique ID of the local shell tool call generated by the model. - `status: "in_progress" | "completed" | "incomplete"` The status of the local shell call. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` The type of the local shell call. Always `local_shell_call`. - `"local_shell_call"` - `LocalShellCallOutput` The output of a local shell tool call. - `id: string` The unique ID of the local shell tool call generated by the model. - `output: string` A JSON string of the output of the local shell tool call. - `type: "local_shell_call_output"` The type of the local shell tool call output. Always `local_shell_call_output`. - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` Ordered shell commands for the execution environment to run. - `max_output_length?: number | null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - `timeout_ms?: number | null` Maximum wall-clock time in milliseconds to allow the shell commands to run. - `call_id: string` The unique ID of the shell tool call generated by the model. - `type: "shell_call"` The type of the item. Always `shell_call`. - `"shell_call"` - `id?: string | null` The unique ID of the shell tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `environment?: LocalEnvironment | ContainerReference | null` The environment to execute the shell commands in. - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` The unique ID of the shell tool call generated by the model. - `output: Array` Captured chunks of stdout and stderr output, along with their associated outcomes. - `outcome: Timeout | Exit` The exit or timeout outcome associated with this shell call. - `Timeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` The outcome type. Always `timeout`. - `"timeout"` - `Exit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` The exit code returned by the shell process. - `type: "exit"` The outcome type. Always `exit`. - `"exit"` - `stderr: string` Captured stderr output for the shell call. - `stdout: string` Captured stdout output for the shell call. - `type: "shell_call_output"` The type of the item. Always `shell_call_output`. - `"shell_call_output"` - `id?: string | null` The unique ID of the shell tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `max_output_length?: number | null` The maximum number of UTF-8 characters captured for this shell call's combined output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call output. - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `operation: CreateFile | DeleteFile | UpdateFile` The specific create, delete, or update instruction for the apply_patch tool call. - `CreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` Unified diff content to apply when creating the file. - `path: string` Path of the file to create relative to the workspace root. - `type: "create_file"` The operation type. Always `create_file`. - `"create_file"` - `DeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` Path of the file to delete relative to the workspace root. - `type: "delete_file"` The operation type. Always `delete_file`. - `"delete_file"` - `UpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` Unified diff content to apply to the existing file. - `path: string` Path of the file to update relative to the workspace root. - `type: "update_file"` The operation type. Always `update_file`. - `"update_file"` - `status: "in_progress" | "completed"` The status of the apply patch tool call. One of `in_progress` or `completed`. - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` The type of the item. Always `apply_patch_call`. - `"apply_patch_call"` - `id?: string | null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `status: "completed" | "failed"` The status of the apply patch tool call output. One of `completed` or `failed`. - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` The type of the item. Always `apply_patch_call_output`. - `"apply_patch_call_output"` - `id?: string | null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `output?: string | null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). - `McpListTools` A list of tools available on an MCP server. - `id: string` The unique ID of the list. - `server_label: string` The label of the MCP server. - `tools: Array` The tools available on the server. - `input_schema: unknown` The JSON schema describing the tool's input. - `name: string` The name of the tool. - `annotations?: unknown` Additional annotations about the tool. - `description?: string | null` The description of the tool. - `type: "mcp_list_tools"` The type of the item. Always `mcp_list_tools`. - `"mcp_list_tools"` - `error?: string | null` Error message if the server could not list tools. - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` The unique ID of the approval request. - `arguments: string` A JSON string of arguments for the tool. - `name: string` The name of the tool to run. - `server_label: string` The label of the MCP server making the request. - `type: "mcp_approval_request"` The type of the item. Always `mcp_approval_request`. - `"mcp_approval_request"` - `McpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` The ID of the approval request being answered. - `approve: boolean` Whether the request was approved. - `type: "mcp_approval_response"` The type of the item. Always `mcp_approval_response`. - `"mcp_approval_response"` - `id?: string | null` The unique ID of the approval response - `reason?: string | null` Optional reason for the decision. - `McpCall` An invocation of a tool on an MCP server. - `id: string` The unique ID of the tool call. - `arguments: string` A JSON string of the arguments passed to the tool. - `name: string` The name of the tool that was run. - `server_label: string` The label of the MCP server running the tool. - `type: "mcp_call"` The type of the item. Always `mcp_call`. - `"mcp_call"` - `approval_request_id?: string | null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - `error?: McpToolCallError | null` The error from the tool call, if any. - `McpProtocolError` - `code: number` - `message: string` - `type: "mcp_protocol_error"` - `"mcp_protocol_error"` - `McpToolExecutionError` - `content: unknown` - `type: "mcp_tool_execution_error"` - `"mcp_tool_execution_error"` - `HTTPError` - `code: number` - `message: string` - `type: "http_error"` - `"http_error"` - `output?: string | null` The output from the tool call. - `status?: "in_progress" | "completed" | "incomplete" | 2 more` The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `ResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` The call ID, used to map this custom tool call output to a custom tool call. - `output: string | Array` The output from the custom tool call generated by your code. Can be a string or an list of output content. - `string` - `Array` - `ResponseInputText` A text input to the model. - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `ResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` The type of the custom tool call output. Always `custom_tool_call_output`. - `"custom_tool_call_output"` - `id?: string` The unique ID of the custom tool call output in the OpenAI platform. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` An identifier used to map this custom tool call to a tool call output. - `input: string` The input for the custom tool call generated by the model. - `name: string` The name of the custom tool being called. - `type: "custom_tool_call"` The type of the custom tool call. Always `custom_tool_call`. - `"custom_tool_call"` - `id?: string` The unique ID of the custom tool call in the OpenAI platform. - `async?: boolean` Whether the custom tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the custom tool being called. - `CompactionTrigger` Compacts the current context. Must be the final input item. - `type: "compaction_trigger"` The type of the item. Always `compaction_trigger`. - `"compaction_trigger"` - `ItemReference` An internal identifier for an item to reference. - `id: string` The ID of the item to reference. - `type?: "item_reference" | null` The type of item to reference. Always `item_reference`. - `"item_reference"` - `Program` - `id: string` The unique ID of this program item. - `call_id: string` The stable call ID of the program item. - `code: string` The JavaScript source executed by programmatic tool calling. - `fingerprint: string` Opaque program replay fingerprint that must be round-tripped. - `type: "program"` The item type. Always `program`. - `"program"` - `ProgramOutput` - `id: string` The unique ID of this program output item. - `call_id: string` The call ID of the program item. - `result: string` The result produced by the program item. - `status: "completed" | "incomplete"` The terminal status of the program output. - `"completed"` - `"incomplete"` - `type: "program_output"` The item type. Always `program_output`. - `"program_output"` - `type: "response.item.create"` The Live client event type. Always `response.item.create`. - `"response.item.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseCreateEvent` Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation. - `type: "response.create"` The Live client event type. Always `response.create`. - `"response.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `SessionCloseEvent` Request that the Live session close. The terminal `session.closed` event contains the close reason and final usage. - `type: "session.close"` The Live client event type. Always `session.close`. - `"session.close"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Fork Server Event - `ForkServerEvent = SessionStartedEvent | SessionUpdatedEvent | InputAudioMutedEvent | 19 more` Server events for Live. Response lifecycle events are wrapped inside response.event; dispatch the nested event by its full type and tolerate new response event types. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when designing the conversation and delegation policy. - `SessionStartedEvent` Returned when a Live session has started. Contains the resolved session configuration, including server defaults. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.started"` The event type, always `session.started`. - `"session.started"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `SessionUpdatedEvent` Returned when a Live session update is accepted. Contains the resolved session configuration after the update. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.updated"` The event type, always `session.updated`. - `"session.updated"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioMutedEvent` Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.muted"` The event type, always `session.input_audio.muted`. - `"session.input_audio.muted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioUnmutedEvent` Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.unmuted"` The event type, always `session.input_audio.unmuted`. - `"session.input_audio.unmuted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InstructionsAppendedEvent` Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.instructions.appended"` The event type, always `session.instructions.appended`. - `"session.instructions.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ThinkingAppendedEvent` Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.thinking.appended"` The event type, always `session.thinking.appended`. - `"session.thinking.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `CommentaryAppendedEvent` Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.commentary.appended"` The event type, always `session.commentary.appended`. - `"session.commentary.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `SessionInputAudioAppend` Input audio received from the primary transport and reflected to a Live sideband connection before model-input muting. - `audio: string` Base64-encoded raw mono PCM16LE at 24 kHz received from the primary transport, reflected to the sideband before model-input muting. This server event uses the same audio key as the client command, but is not an acknowledgment of it. - `type: "session.input_audio.append"` The event type, always `session.input_audio.append`. - `"session.input_audio.append"` - `OutputAudioDeltaEvent` An audio chunk generated by the Live model. Decode and play primary WebSocket chunks in delivery order using the configured session audio format. Sideband connections receive reflected output audio with timestamps. - `delta: string` Base64-encoded raw audio. Primary WebSocket events use the session's configured format; reflected sideband events use mono PCM16LE at 24 kHz. - `type: "session.output_audio.delta"` The event type, always `session.output_audio.delta`. - `"session.output_audio.delta"` - `end_ms?: number` Exclusive session-relative end in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. Dropped output frames leave gaps between reflected ranges. - `start_ms?: number` Inclusive session-relative start in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. - `InputTranscriptDeltaEvent` A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.input_transcript.delta"` The event type, always `session.input_transcript.delta`. - `"session.input_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `OutputTranscriptDeltaEvent` A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.output_transcript.delta"` The event type, always `session.output_transcript.delta`. - `"session.output_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `DelegationCreatedEvent` Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated. - `delegation: Delegation` The delegated work identifier and destination. This object contains metadata, not the task text. - `id: string` The unique ID of the delegation. Use this as delegation_id when replying to client-owned work or correlating Responses events. - `target: "client" | "responses"` Where the Live model delegated the work: `client` for your application, or `responses` for the configured Responses backend. - `"client" | "responses"` - `"client"` - `"responses"` - `type: "delegation"` The object type, always `delegation`. - `"delegation"` - `response_id?: string` The ID of the Responses API response associated with a Responses delegation. Omitted for client delegations. - `event_id: string` The unique ID of the Live server event. - `offset_ms: number` The position on the Live session timeline where the delegation was created, in milliseconds from the beginning of the session. - `type: "session.delegation.created"` The event type, always `session.delegation.created`. - `"session.delegation.created"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ResponseEvent` A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation. - `event: Record` The nested Responses streaming event. Dispatch on its type field. Response lifecycle snapshots omit input and clear instructions, tools, and output to keep messages small; consume granular output events for the generated content. - `event_id: string` The unique ID of the Live server event. - `type: "response.event"` The event type, always `response.event`. - `"response.event"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `delegation_id?: string | null` The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation. - `SessionUsageUpdatedEvent` Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events. - `event_id: string` The unique ID of the Live server event. - `type: "session.usage.updated"` The event type, always `session.usage.updated`. - `"session.usage.updated"` - `usage: SessionUsage` The cumulative Live audio usage so far. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `context_window?: ContextWindow` The latest measured Live context-window usage. Omitted when the context limit is unknown. - `usage_ratio: number` The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames. - `SessionClosedEvent` Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization. - `event_id: string` The unique ID of the Live server event. - `reason: "close_requested" | "expired" | "content" | 2 more` Why the Live session ended: `close_requested` for an application close or hangup request, `expired` for the session duration limit, `content` for a safety filter, `remote_hangup` for a graceful remote disconnect, or `connection_lost` for an unexpected primary or upstream disconnection. - `"close_requested" | "expired" | "content" | 2 more` - `"close_requested"` - `"expired"` - `"content"` - `"remote_hangup"` - `"connection_lost"` - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.closed"` The event type, always `session.closed`. - `"session.closed"` - `usage: SessionUsage` The final cumulative Live audio usage after session finalization. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ErrorEvent` Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error. - `error: Error` Details of the Live error and the client command that caused it, when known. - `code: string` A machine-readable code identifying the Live error, such as `unknown_parameter`. - `message: string` A human-readable explanation of the Live error. - `type: string` The category of error, such as `invalid_request_error` for an invalid Live client command. - `client_event_id?: string` The event_id of the client command that caused the error, when supplied. - `param?: string` The parameter that caused the error, when applicable, such as `session.voice`. - `event_id: string` The unique ID of the Live server event. - `type: "error"` The event type, always `error`. - `"error"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InfoEvent` An informational notice about the Live session, such as the event permissions applied to a frontend data channel. - `code: string` A machine-readable code for the notice, such as `data_channel_permissions`. - `event_id: string` The unique ID of the Live server event. - `message: string` A human-readable explanation of the Live session notice. - `type: "info"` The event type, always `info`. - `"info"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `TransportDtmfReceived` A SIP DTMF keypress received from the caller. Delivered only to sideband observers. - `event: string` - `event_id: string` - `type: "transport.dtmf.received"` - `"transport.dtmf.received"` - `TransportDtmfSend` A SIP DTMF keypress successfully sent by the hosted tool. Delivered only to sideband observers; this is not a client command. - `event: string` - `event_id: string` - `type: "transport.dtmf.send"` - `"transport.dtmf.send"` - `TransportRinging` The outbound SIP provider leg is ringing or providing early media. Delivered only to sideband observers. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.ringing"` - `"transport.ringing"` - `TransportAnswered` The outbound SIP provider leg answered and media is established. Delivered only to sideband observers. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.answered"` - `"transport.answered"` - `TransportFailed` An asynchronous outbound SIP setup failure. Delivered only to sideband observers. - `error: Error` - `code: string` The call setup failure code. - `message: string` - `type: "call_error"` - `"call_error"` - `param?: string` The parameter related to the error, if any. Empty when no parameter applies. - `event_id: string` - `session_id: string` The canonical Live session ID. - `type: "transport.failed"` - `"transport.failed"` # Sessions ## Accept call `client.live.sessions.accept(stringsessionID, SessionAcceptParamsbody, RequestOptionsoptions?): void` **post** `/live/sessions/{session_id}/accept` Accept an incoming SIP call. Supply session with type live, the model, and startup configuration. Before accepting calls, follow the [Live prompting guide](/api/docs/guides/live-prompting) to write frontend conversation instructions and a separate backend prompt. SIP media format is negotiated; omit audio.format. ### Parameters - `sessionID: string` - `body: SessionAcceptParams` - `session: Session` Model and startup configuration for the Live session that answers the incoming SIP call. - `model: (string & {}) | "gpt-live-1"` The Live model to use for the accepted call. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `type: "live"` The session type. Always `live`. - `"live"` - `audio?: Audio` Startup audio output configuration. SIP negotiates the media format; audio.format is only accepted for primary WebSockets. Voice cannot change after startup. - `output?: Output` Settings for speech generated by the Live model. Choose the voice before starting the session. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.sessions.accept('session_id', { session: { model: 'gpt-live-1', type: 'live' } }); ``` ## Download recording `client.live.sessions.downloadRecording(stringsessionID, RequestOptionsoptions?): Response` **get** `/live/sessions/{session_id}/content` Get Live session content ### Parameters - `sessionID: string` The ID of the stored Live session to download. Use the session ID returned when the session started with storage enabled. ### Returns - `unnamed_schema_3 = Response` ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); const response = await client.live.sessions.downloadRecording('live_SQ'); console.log(response); const content = await response.blob(); console.log(content); ``` ## Fork session `client.live.sessions.fork(stringsessionID, SessionForkParamsbody, RequestOptionsoptions?): SessionForkResponse` **post** `/live/sessions/{session_id}/fork` Fork a stored Live session onto a new WebRTC connection. ### Parameters - `sessionID: string` - `body: SessionForkParams` - `transport: Transport` WebRTC transport with an SDP offer for the new connection to the forked session. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` - `session?: MediaSessionForkConfig` Optional configuration overrides for the new Live session. Omit this object or send an empty object to inherit the stored session's settings. - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: Delegation` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `store?: boolean` Whether to store the forked session. Omission inherits the stored session's setting. ### Returns - `SessionForkResponse` The created Live session identifier and WebRTC answer. Apply transport.sdp as the peer's remote answer and wait for session.started on the data channel before sending commands. - `session: Session` The newly created Live session. Use its ID for session controls and sideband connections. - `id: string` Opaque session identifier. Preserve the returned value unchanged, including its prefix. - `transport: Transport` WebRTC transport with the SDP answer. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); const response = await client.live.sessions.fork('session_id', { transport: { sdp: 'x', type: 'webrtc' }, }); console.log(response.session); ``` #### Response ```json { "session": { "id": "id" }, "transport": { "sdp": "x", "type": "webrtc" } } ``` ## Hang up session `client.live.sessions.hangup(stringsessionID, RequestOptionsoptions?): void` **post** `/live/sessions/{session_id}/hangup` End a SIP call identified by session_id. ### Parameters - `sessionID: string` ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.sessions.hangup('session_id'); ``` ## Transfer call `client.live.sessions.refer(stringsessionID, SessionReferParamsbody, RequestOptionsoptions?): void` **post** `/live/sessions/{session_id}/refer` Transfer a SIP call to another destination. Supply a nonblank target_uri for the SIP Refer-To header. ### Parameters - `sessionID: string` - `body: SessionReferParams` - `target_uri: string` Nonblank URI for the SIP Refer-To header, such as tel:+14155550123 or sip:agent@example.com. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.sessions.refer('session_id', { target_uri: 'tel:+14155550123' }); ``` ## Reject call `client.live.sessions.reject(stringsessionID, SessionRejectParamsbody, RequestOptionsoptions?): void` **post** `/live/sessions/{session_id}/reject` Reject an incoming SIP call. Send a required SIP rejection status_code between 300 and 699. ### Parameters - `sessionID: string` - `body: SessionRejectParams` - `status_code: number` SIP rejection status sent to the caller. This field is required. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.sessions.reject('session_id', { status_code: 486 }); ``` ## Domain Types ### Session Fork Response - `SessionForkResponse` The created Live session identifier and WebRTC answer. Apply transport.sdp as the peer's remote answer and wait for session.started on the data channel before sending commands. - `session: Session` The newly created Live session. Use its ID for session controls and sideband connections. - `id: string` Opaque session identifier. Preserve the returned value unchanged, including its prefix. - `transport: Transport` WebRTC transport with the SDP answer. - `sdp: string` Session Description Protocol message for the WebRTC connection. - `type: "webrtc"` The transport used for the Live session. Always `webrtc`. - `"webrtc"` # Sideband ## `client.live.sideband.connect(SidebandConnectParamsparams?, RequestOptionsoptions?): void` **** `` Attach to an existing Live session. Do not send session.start again. ### Parameters - `params: SidebandConnectParams` - `graceful_close?: boolean` Opt in to the graceful WebSocket closing handshake when the session ends. The server may also enable this behavior by default. ### Example ```typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: process.env['OPENAI_API_KEY'], // This is the default and can be omitted }); await client.live.sideband.connect(); ``` ## Domain Types ### Connect Client Event - `ConnectClientEvent = SessionUpdateEvent | InputAudioMuteEvent | InputAudioUnmuteEvent | 6 more` Client events accepted by an attached Live sideband WebSocket. The session is already started; send audio over the primary connection. - `SessionUpdateEvent` Update the delegation settings of an active Live session. The server acknowledges accepted changes with `session.updated`. - `session: SessionUpdateConfig` Sparse delegation updates. Omitted settings retain their values. The delegation type cannot change, including resetting Responses delegation to null or client. Model, frontend instructions, audio, and startup input are immutable. - `delegation?: ClientDelegation | Responses | null` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Update the Responses backend for an existing Live session without changing delegation ownership. - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `responses?: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `model?: string` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "session.update"` The Live client event type. Always `session.update`. - `"session.update"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioMuteEvent` Mute audio input to the Live model without closing the session. The server acknowledges with `session.input_audio.muted`. - `type: "session.input_audio.mute"` The Live client event type. Always `session.input_audio.mute`. - `"session.input_audio.mute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InputAudioUnmuteEvent` Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`. - `type: "session.input_audio.unmute"` The Live client event type. Always `session.input_audio.unmute`. - `"session.input_audio.unmute"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `InstructionsAppendEvent` Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation. - `content: string` Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.instructions.append"` The Live client event type. Always `session.instructions.append`. - `"session.instructions.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ThinkingAppendEvent` Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation. - `content: string` Silent reasoning or progress context, limited to 500 tokens. It does not directly request speech, but can influence later speech and is not a secrecy boundary. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.thinking.append"` The Live client event type. Always `session.thinking.append`. - `"session.thinking.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `CommentaryAppendEvent` Provide context the Live model can communicate to the user, optionally for an existing client delegation. - `content: string` Speakable context for the Live model, limited to 500 tokens. Use this for a result the model should communicate; use session.thinking.append for silent context. - `delegation_id: string | null` Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation. - `type: "session.commentary.append"` The Live client event type. Always `session.commentary.append`. - `"session.commentary.append"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseItemCreateEvent` Add an input item to the Live session’s Responses backend. Requires Responses delegation; use `response.create` to request a response. - `item: ResponseInputItem` An input item to append to the Responses backend conversation, such as a user message or a function tool result. - `EasyInputMessage` A message input to the model with a role indicating instruction following hierarchy. Instructions given with the `developer` or `system` role take precedence over instructions given with the `user` role. Messages with the `assistant` role are presumed to have been generated by the model in previous interactions. - `content: string | ResponseInputMessageContentList` Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses. - `string` - `ResponseInputMessageContentList = Array` A list of one or many input items to the model, containing different content types. - `ResponseInputText` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `detail: ImageDetail` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `"low"` - `"high"` - `"auto"` - `"original"` - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFile` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string` The content of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string` The URL of the file to be sent to the model. - `filename?: string` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `role: "user" | "assistant" | "system" | "developer"` The role of the message input. One of `user`, `assistant`, `system`, or `developer`. - `"user"` - `"assistant"` - `"system"` - `"developer"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `type?: "message"` The type of the message input. Always `message`. - `"message"` - `Message` 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. - `content: ResponseInputMessageContentList` A list of one or many input items to the model, containing different content types. - `role: "user" | "system" | "developer"` The role of the message input. One of `user`, `system`, or `developer`. - `"user"` - `"system"` - `"developer"` - `status?: "in_progress" | "completed" | "incomplete"` The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type?: "message"` The type of the message input. Always set to `message`. - `"message"` - `ResponseOutputMessage` An output message from the model. - `id: string` The unique ID of the output message. - `content: Array` The content of the output message. - `ResponseOutputText` A text output from the model. - `annotations: Array` The annotations of the text output. - `FileCitation` A citation to a file. - `file_id: string` The ID of the file. - `filename: string` The filename of the file cited. - `index: number` The index of the file in the list of files. - `type: "file_citation"` The type of the file citation. Always `file_citation`. - `"file_citation"` - `URLCitation` A citation for a web resource used to generate a model response. - `end_index: number` The index of the last character of the URL citation in the message. - `start_index: number` The index of the first character of the URL citation in the message. - `title: string` The title of the web resource. - `type: "url_citation"` The type of the URL citation. Always `url_citation`. - `"url_citation"` - `url: string` The URL of the web resource. - `ContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: string` The ID of the container file. - `end_index: number` The index of the last character of the container file citation in the message. - `file_id: string` The ID of the file. - `filename: string` The filename of the container file cited. - `start_index: number` The index of the first character of the container file citation in the message. - `type: "container_file_citation"` The type of the container file citation. Always `container_file_citation`. - `"container_file_citation"` - `FilePath` A path to a file. - `file_id: string` The ID of the file. - `index: number` The index of the file in the list of files. - `type: "file_path"` The type of the file path. Always `file_path`. - `"file_path"` - `text: string` The text output from the model. - `type: "output_text"` The type of the output text. Always `output_text`. - `"output_text"` - `logprobs?: Array` - `token: string` - `bytes: Array` - `logprob: number` - `top_logprobs: Array` - `token: string` - `bytes: Array` - `logprob: number` - `ResponseOutputRefusal` A refusal from the model. - `refusal: string` The refusal explanation from the model. - `type: "refusal"` The type of the refusal. Always `refusal`. - `"refusal"` - `role: "assistant"` The role of the output message. Always `assistant`. - `"assistant"` - `status: "in_progress" | "completed" | "incomplete"` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "message"` The type of the output message. Always `message`. - `"message"` - `phase?: "commentary" | "final_answer" | null` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `"commentary"` - `"final_answer"` - `ResponseFileSearchToolCall` The results of a file search tool call. See the [file search guide](/api/docs/guides/tools-file-search) for more information. - `id: string` The unique ID of the file search tool call. - `queries: Array` The queries used to search for files. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, - `"in_progress"` - `"searching"` - `"completed"` - `"incomplete"` - `"failed"` - `type: "file_search_call"` The type of the file search tool call. Always `file_search_call`. - `"file_search_call"` - `results?: Array | null` The results of the file search tool call. - `attributes?: Record | null` Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters, booleans, or numbers. - `string` - `number` - `boolean` - `file_id?: string` The unique ID of the file. - `filename?: string` The name of the file. - `score?: number` The relevance score of the file - a value between 0 and 1. - `text?: string` The text that was retrieved from the file. - `ResponseComputerToolCall` A tool call to a computer use tool. See the [computer use guide](/api/docs/guides/tools-computer-use) for more information. - `id: string` The unique ID of the computer call. - `call_id: string` An identifier used when responding to the tool call with output. - `pending_safety_checks: Array` The pending safety checks for the computer call. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "computer_call"` The type of the computer call. Always `computer_call`. - `"computer_call"` - `action?: Click | DoubleClick | Drag | 6 more` A click action. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `actions?: ComputerActionList` Flattened batched actions for `computer_use`. Each action includes an `type` discriminator and action-specific fields. - `Click` A click action. - `button: "left" | "right" | "wheel" | 2 more` Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. - `"left"` - `"right"` - `"wheel"` - `"back"` - `"forward"` - `type: "click"` Specifies the event type. For a click action, this property is always `click`. - `"click"` - `x: number` The x-coordinate where the click occurred. - `y: number` The y-coordinate where the click occurred. - `keys?: Array | null` The keys being held while clicking. - `DoubleClick` A double click action. - `keys: Array | null` The keys being held while double-clicking. - `type: "double_click"` Specifies the event type. For a double click action, this property is always set to `double_click`. - `"double_click"` - `x: number` The x-coordinate where the double click occurred. - `y: number` The y-coordinate where the double click occurred. - `Drag` A drag action. - `path: Array` An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg ``` [ { x: 100, y: 200 }, { x: 200, y: 300 } ] ``` - `x: number` The x-coordinate. - `y: number` The y-coordinate. - `type: "drag"` Specifies the event type. For a drag action, this property is always set to `drag`. - `"drag"` - `keys?: Array | null` The keys being held while dragging the mouse. - `Keypress` A collection of keypresses the model would like to perform. - `keys: Array` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: "keypress"` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `"keypress"` - `Move` A mouse move action. - `type: "move"` Specifies the event type. For a move action, this property is always set to `move`. - `"move"` - `x: number` The x-coordinate to move to. - `y: number` The y-coordinate to move to. - `keys?: Array | null` The keys being held while moving the mouse. - `Screenshot` A screenshot action. - `type: "screenshot"` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `"screenshot"` - `Scroll` A scroll action. - `scroll_x: number` The horizontal scroll distance. - `scroll_y: number` The vertical scroll distance. - `type: "scroll"` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `"scroll"` - `x: number` The x-coordinate where the scroll occurred. - `y: number` The y-coordinate where the scroll occurred. - `keys?: Array | null` The keys being held while scrolling. - `Type` An action to type in text. - `text: string` The text to type. - `type: "type"` Specifies the event type. For a type action, this property is always set to `type`. - `"type"` - `Wait` A wait action. - `type: "wait"` Specifies the event type. For a wait action, this property is always set to `wait`. - `"wait"` - `ComputerCallOutput` The output of a computer tool call. - `call_id: string` The ID of the computer tool call that produced the output. - `output: ResponseComputerToolCallOutputScreenshot` A computer screenshot image used with the computer use tool. - `type: "computer_screenshot"` Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`. - `"computer_screenshot"` - `file_id?: string` The identifier of an uploaded file that contains the screenshot. - `image_url?: string` The URL of the screenshot image. - `type: "computer_call_output"` The type of the computer tool call output. Always `computer_call_output`. - `"computer_call_output"` - `id?: string | null` The ID of the computer tool call output. - `acknowledged_safety_checks?: Array | null` The safety checks reported by the API that have been acknowledged by the developer. - `id: string` The ID of the pending safety check. - `code?: string | null` The type of the pending safety check. - `message?: string | null` Details about the pending safety check. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseFunctionWebSearch` The results of a web search tool call. See the [web search guide](/api/docs/guides/tools-web-search) for more information. - `id: string` The unique ID of the web search tool call. - `action: Search | OpenPage | FindInPage` 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). - `Search` Action type "search" - Performs a web search query. - `type: "search"` The action type. - `"search"` - `queries?: Array` The search queries. - `query?: string` The search query. - `sources?: Array` The sources used in the search. - `type: "url"` The type of source. Always `url`. - `"url"` - `url: string` The URL of the source. - `OpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: "open_page"` The action type. - `"open_page"` - `url?: string | null` The URL opened by the model. - `FindInPage` Action type "find_in_page": Searches for a pattern within a loaded page. - `pattern: string` The pattern or text to search for within the page. - `type: "find_in_page"` The action type. - `"find_in_page"` - `url: string` The URL of the page searched for the pattern. - `status: "in_progress" | "searching" | "completed" | 2 more` The status of the web search tool call. - `"in_progress"` - `"searching"` - `"completed"` - `"failed"` - `"incomplete"` - `type: "web_search_call"` The type of the web search tool call. Always `web_search_call`. - `"web_search_call"` - `ResponseFunctionToolCall` A tool call to run a function. See the [function calling guide](/api/docs/guides/function-calling) for more information. - `arguments: string` A JSON string of the arguments to pass to the function. - `call_id: string` The unique ID of the function tool call generated by the model. - `name: string` The name of the function to run. - `type: "function_call"` The type of the function tool call. Always `function_call`. - `"function_call"` - `id?: string` The unique ID of the function tool call. - `async?: boolean` Whether the function tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the function to run. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `FunctionCallOutput` The output of a function tool call. - `output: string | ResponseFunctionCallOutputItemList` Text, image, or file output of the function tool call. - `string` - `ResponseFunctionCallOutputItemList = Array` An array of content outputs (text, image, file) for the function tool call. - `ResponseInputTextContent` A text input to the model. - `text: string` The text input to the model. - `type: "input_text"` The type of the input item. Always `input_text`. - `"input_text"` - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputImageContent` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision) - `type: "input_image"` The type of the input item. Always `input_image`. - `"input_image"` - `detail?: ImageDetail | null` The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`. - `file_id?: string | null` The ID of the file to be sent to the model. - `image_url?: string | null` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `ResponseInputFileContent` A file input to the model. - `type: "input_file"` The type of the input item. Always `input_file`. - `"input_file"` - `detail?: "auto" | "low" | "high"` The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`. - `"auto"` - `"low"` - `"high"` - `file_data?: string | null` The base64-encoded data of the file to be sent to the model. - `file_id?: string | null` The ID of the file to be sent to the model. - `file_url?: string | null` The URL of the file to be sent to the model. - `filename?: string | null` The name of the file to be sent to the model. - `prompt_cache_breakpoint?: PromptCacheBreakpoint | null` Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: "explicit"` The breakpoint mode. Always `explicit`. - `"explicit"` - `type: "function_call_output"` The type of the function tool call output. Always `function_call_output`. - `"function_call_output"` - `id?: string | null` The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id?: string | null` The unique ID of the function tool call generated by the model. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `name?: string | null` The name of the tool that produced the output. - `namespace?: string | null` The namespace of the tool that produced the output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ToolSearchCall` - `arguments: unknown` The arguments supplied to the tool search call. - `type: "tool_search_call"` The item type. Always `tool_search_call`. - `"tool_search_call"` - `id?: string | null` The unique ID of this tool search call. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search call. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseToolSearchOutputItemParam` - `tools: Array` The loaded tool definitions returned by the tool search output. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `name: string` The name of the function to call. - `parameters: Record | null` A JSON schema object describing the parameters of the function. - `strict: boolean | null` Whether strict parameter validation is enforced for this function tool. - `type: "function"` The type of the function tool. Always `function`. - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` - `defer_loading?: boolean` Whether this function is deferred and loaded via tool search. - `description?: string | null` A description of the function. Used by the model to determine whether or not to call the function. - `output_schema?: Record | null` A JSON schema object describing the JSON value encoded in string outputs for this function. - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `type: "file_search"` The type of the file search tool. Always `file_search`. - `"file_search"` - `vector_store_ids: Array` The IDs of the vector stores to search. - `filters?: ComparisonFilter | CompoundFilter | null` A filter to apply. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `key: string` The key to compare against the value. - `type: "eq" | "ne" | "gt" | 5 more` Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`. - `eq`: equals - `ne`: not equal - `gt`: greater than - `gte`: greater than or equal - `lt`: less than - `lte`: less than or equal - `in`: in - `nin`: not in - `"eq"` - `"ne"` - `"gt"` - `"gte"` - `"lt"` - `"lte"` - `"in"` - `"nin"` - `value: string | number | boolean | Array` The value to compare against the attribute key; supports string, number, or boolean types. - `string` - `number` - `boolean` - `Array` - `string` - `number` - `CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array` Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. - `ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `unknown` - `type: "and" | "or"` Type of operation: `and` or `or`. - `"and"` - `"or"` - `max_num_results?: number` The maximum number of results to return. This number should be between 1 and 50 inclusive. - `ranking_options?: RankingOptions` Ranking options for search. - `hybrid_search?: HybridSearch` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: number` The weight of the embedding in the reciprocal ranking fusion. - `text_weight: number` The weight of the text in the reciprocal ranking fusion. - `ranker?: "auto" | "default-2024-11-15"` The ranker to use for the file search. - `"auto"` - `"default-2024-11-15"` - `score_threshold?: number` The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results. - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `type: "computer"` The type of the computer tool. Always `computer`. - `"computer"` - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `display_height: number` The height of the computer display. - `display_width: number` The width of the computer display. - `environment: "windows" | "mac" | "linux" | 2 more` The type of computer environment to control. - `"windows"` - `"mac"` - `"linux"` - `"ubuntu"` - `"browser"` - `type: "computer_use_preview"` The type of the computer use tool. Always `computer_use_preview`. - `"computer_use_preview"` - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search" | "web_search_2025_08_26"` The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. - `"web_search"` - `"web_search_2025_08_26"` - `external_web_access?: boolean` Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content. - `filters?: Filters | null` Filters for the search. - `allowed_domains?: Array | null` Allowed domains for the search. If not provided, all domains are allowed. Subdomains of the provided domains are allowed as well. Example: `["pubmed.ncbi.nlm.nih.gov"]` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The approximate location of the user. - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `type?: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `server_label: string` A label for this MCP server, used to identify it in tool calls. - `type: "mcp"` The type of the MCP tool. Always `mcp`. - `"mcp"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `allowed_tools?: Array | McpToolFilter | null` List of allowed tool names or a filter object. - `Array` - `McpToolFilter` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `authorization?: string` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id?: "connector_dropbox" | "connector_gmail" | "connector_googlecalendar" | 5 more` 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](/api/docs/guides/tools-connectors-mcp#connectors). 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` - `"connector_dropbox"` - `"connector_gmail"` - `"connector_googlecalendar"` - `"connector_googledrive"` - `"connector_microsoftteams"` - `"connector_outlookcalendar"` - `"connector_outlookemail"` - `"connector_sharepoint"` - `defer_loading?: boolean` Whether this MCP tool is deferred and discovered via tool search. - `headers?: Record | null` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval?: McpToolApprovalFilter | "always" | "never" | null` Specify which of the MCP server's tools require approval. - `McpToolApprovalFilter` Specify which of the MCP server's tools require approval. Can be `always`, `never`, or a filter object associated with tools that require approval. - `always?: Always` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `never?: Never` A filter object to specify which tools are allowed. - `read_only?: boolean` Indicates whether or not a tool modifies data or is read-only. If an MCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint), it will match this filter. - `tool_names?: Array` List of allowed tool names. - `"always" | "never"` - `"always"` - `"never"` - `server_description?: string` Optional description of the MCP server, used to provide more context. - `server_url?: string` The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `tunnel_id?: string` The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: string | CodeInterpreterToolAuto` 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. - `string` - `CodeInterpreterToolAuto` Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on. - `type: "auto"` Always `auto`. - `"auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the code interpreter container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `type: "disabled"` Disable outbound network access. Always `disabled`. - `"disabled"` - `ContainerNetworkPolicyAllowlist` - `allowed_domains: Array` A list of allowed domains when type is `allowlist`. - `type: "allowlist"` Allow outbound network access only to specified domains. Always `allowlist`. - `"allowlist"` - `domain_secrets?: Array` Optional domain-scoped secrets for allowlisted domains. - `domain: string` The domain associated with the secret. - `name: string` The name of the secret to inject for the domain. - `value: string` The secret value to inject for the domain. - `type: "code_interpreter"` The type of the code interpreter tool. Always `code_interpreter`. - `"code_interpreter"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `ProgrammaticToolCalling` - `type: "programmatic_tool_calling"` The type of the tool. Always `programmatic_tool_calling`. - `"programmatic_tool_calling"` - `ImageGeneration` A tool that generates images using the GPT image models. - `type: "image_generation"` The type of the image generation tool. Always `image_generation`. - `"image_generation"` - `action?: "generate" | "edit" | "auto"` Whether to generate a new image or edit an existing image. Default: `auto`. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto"` Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`. - `"transparent"` - `"opaque"` - `"auto"` - `input_fidelity?: "high" | "low" | null` Control how much effort the model will exert to match the style and features, especially facial features, of input images. 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`. - `"high"` - `"low"` - `input_image_mask?: InputImageMask` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id?: string` File ID for the mask image. - `image_url?: string` Base64-encoded mask image. - `model?: (string & {}) | "gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` The image generation model to use. One of `gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default: `gpt-image-1`. - `(string & {})` - `"gpt-image-1" | "gpt-image-1-mini" | "gpt-image-2" | 7 more` - `"gpt-image-1"` - `"gpt-image-1-mini"` - `"gpt-image-2"` - `"gpt-image-2-2026-04-21"` - `"gpt-image-2.5-sunburst"` - `"gpt-image-2.5-sunburst-2026-09-08"` - `"gpt-image-2.5-flare"` - `"gpt-image-2.5-flare-2026-09-08"` - `"gpt-image-1.5"` - `"chatgpt-image-latest"` - `moderation?: "auto" | "low"` Moderation level for the generated image. Default: `auto`. - `"auto"` - `"low"` - `output_compression?: number` Compression level for the output image. Default: 100. - `output_format?: "png" | "webp" | "jpeg"` The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. - `"png"` - `"webp"` - `"jpeg"` - `partial_images?: number` Number of partial images to generate in streaming mode, from 0 (default value) to 3. - `quality?: "low" | "medium" | "high" | 3 more` The quality of the generated image. The GPT image models support `low`, `medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. Default: `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | "auto"` The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024" | "auto"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `"auto"` - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `type: "local_shell"` The type of the local shell tool. Always `local_shell`. - `"local_shell"` - `FunctionShellTool` A tool that allows the model to execute shell commands. - `type: "shell"` The type of the shell tool. Always `shell`. - `"shell"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `environment?: ContainerAuto | LocalEnvironment | ContainerReference | null` - `ContainerAuto` - `type: "container_auto"` Automatically creates a container for this request - `"container_auto"` - `file_ids?: Array` An optional list of uploaded files to make available to your code. - `memory_limit?: "1g" | "4g" | "16g" | "64g" | null` The memory limit for the container. - `"1g"` - `"4g"` - `"16g"` - `"64g"` - `network_policy?: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `ContainerNetworkPolicyDisabled` - `ContainerNetworkPolicyAllowlist` - `skills?: Array` An optional list of skills referenced by id or inline data. - `SkillReference` - `skill_id: string` The ID of the referenced skill. - `type: "skill_reference"` References a skill created with the /v1/skills endpoint. - `"skill_reference"` - `version?: string` Optional skill version. Use a positive integer or 'latest'. Omit for default. - `InlineSkill` - `description: string` The description of the skill. - `name: string` The name of the skill. - `source: InlineSkillSource` Inline skill payload - `data: string` Base64-encoded skill zip bundle. - `media_type: "application/zip"` The media type of the inline skill payload. Must be `application/zip`. - `"application/zip"` - `type: "base64"` The type of the inline skill source. Must be `base64`. - `"base64"` - `type: "inline"` Defines an inline skill for this request. - `"inline"` - `LocalEnvironment` - `type: "local"` Use a local computer environment. - `"local"` - `skills?: Array` An optional list of skills. - `description: string` The description of the skill. - `name: string` The name of the skill. - `path: string` The path to the directory containing the skill. - `ContainerReference` - `container_id: string` The ID of the referenced container. - `type: "container_reference"` References a container created with the /v1/containers endpoint - `"container_reference"` - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `name: string` The name of the custom tool, used to identify it in tool calls. - `type: "custom"` The type of the custom tool. Always `custom`. - `"custom"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this tool should be deferred and discovered via tool search. - `description?: string` Optional description of the custom tool, used to provide more context. - `format?: CustomToolInputFormat` The input format for the custom tool. Default is unconstrained text. - `Text` Unconstrained free-form text. - `type: "text"` Unconstrained text format. Always `text`. - `"text"` - `Grammar` A grammar defined by the user. - `definition: string` The grammar definition. - `syntax: "lark" | "regex"` The syntax of the grammar definition. One of `lark` or `regex`. - `"lark"` - `"regex"` - `type: "grammar"` Grammar format. Always `grammar`. - `"grammar"` - `NamespaceTool` Groups function/custom tools under a shared namespace. - `description: string` A description of the namespace shown to the model. - `name: string` The namespace name used in tool calls (for example, `crm`). - `tools: Array` The function/custom tools available inside this namespace. - `Function` - `name: string` - `type: "function"` - `"function"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `async?: boolean` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading?: boolean` Whether this function should be deferred and discovered via tool search. - `description?: string | null` - `output_schema?: Record | null` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters?: unknown` - `strict?: boolean | null` Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `type: "namespace"` The type of the tool. Always `namespace`. - `"namespace"` - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `type: "tool_search"` The type of the tool. Always `tool_search`. - `"tool_search"` - `description?: string | null` Description shown to the model for a client-executed tool search tool. - `execution?: "server" | "client"` Whether tool search is executed by the server or by the client. - `"server"` - `"client"` - `parameters?: unknown` Parameter schema for a client-executed tool search tool. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `type: "web_search_preview" | "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`. - `"web_search_preview"` - `"web_search_preview_2025_03_11"` - `search_content_types?: Array<"text" | "image">` - `"text"` - `"image"` - `search_context_size?: "low" | "medium" | "high"` High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. - `"low"` - `"medium"` - `"high"` - `user_location?: UserLocation | null` The user's location. - `type: "approximate"` The type of location approximation. Always `approximate`. - `"approximate"` - `city?: string | null` Free text input for the city of the user, e.g. `San Francisco`. - `country?: string | null` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region?: string | null` Free text input for the region of the user, e.g. `California`. - `timezone?: string | null` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "apply_patch"` The type of the tool. Always `apply_patch`. - `"apply_patch"` - `allowed_callers?: Array<"direct" | "programmatic"> | null` The tool invocation context(s). - `"direct"` - `"programmatic"` - `type: "tool_search_output"` The item type. Always `tool_search_output`. - `"tool_search_output"` - `id?: string | null` The unique ID of this tool search output. - `call_id?: string | null` The unique ID of the tool search call generated by the model. - `execution?: "server" | "client"` Whether tool search was executed by the server or by the client. - `"server"` - `"client"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the tool search output. - `"in_progress"` - `"completed"` - `"incomplete"` - `AdditionalTools` - `role: "developer"` The role that provided the additional tools. Only `developer` is supported. - `"developer"` - `tools: Array` A list of additional tools made available at this item. - `FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `Mcp` Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](/api/docs/guides/tools-connectors-mcp). - `CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `ProgrammaticToolCalling` - `ImageGeneration` A tool that generates images using the GPT image models. - `LocalShell` A tool that allows the model to execute shell commands in a local environment. - `FunctionShellTool` A tool that allows the model to execute shell commands. - `CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `NamespaceTool` Groups function/custom tools under a shared namespace. - `ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `WebSearchPreviewTool` This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `ApplyPatchTool` Allows the assistant to create, delete, or update files using unified diffs. - `type: "additional_tools"` The item type. Always `additional_tools`. - `"additional_tools"` - `id?: string | null` The unique ID of this additional tools item. - `ResponseConfigurationUpdateItemParam` An update to the conversation's response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update. - `type: "configuration_update"` The item type. Always `configuration_update`. - `"configuration_update"` - `id?: string | null` The unique ID of the configuration update item. - `reasoning?: Reasoning` Updates to reasoning configuration. Only effort is supported. - `effort?: ReasoningEffort | null` The reasoning effort to use for subsequent responses until another configuration update replaces it. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `ResponseReasoningItem` 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](/api/docs/guides/conversation-state). - `id: string` The unique identifier of the reasoning content. - `summary: Array` Reasoning summary content. - `text: string` A summary of the reasoning output from the model so far. - `type: "summary_text"` The type of the object. Always `summary_text`. - `"summary_text"` - `type: "reasoning"` The type of the object. Always `reasoning`. - `"reasoning"` - `content?: Array` Reasoning text content. - `text: string` The reasoning text from the model. - `type: "reasoning_text"` The type of the reasoning text. Always `reasoning_text`. - `"reasoning_text"` - `encrypted_content?: string | null` The encrypted content of the reasoning item. This is populated by default for reasoning items returned by `POST /v1/responses` and WebSocket `response.create` requests. When streaming, use the completed reasoning item and its `encrypted_content` from the `response.output_item.done` event in subsequent requests. The `encrypted_content` in `response.output_item.added` may be incomplete. This is especially important when `store` is `false` or when using Zero Data Retention. - `status?: "in_progress" | "completed" | "incomplete"` The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API. - `"in_progress"` - `"completed"` - `"incomplete"` - `ResponseCompactionItemParam` A compaction item generated by the [`v1/responses/compact` API](/api/reference/resources/responses/methods/compact). - `encrypted_content: string` The encrypted content of the compaction summary. - `type: "compaction"` The type of the item. Always `compaction`. - `"compaction"` - `id?: string | null` The ID of the compaction item. - `ImageGenerationCall` An image generation request made by the model. - `id: string` The unique ID of the image generation call. - `result: string | null` The generated image encoded in base64. - `status: "in_progress" | "completed" | "generating" | "failed"` The status of the image generation call. - `"in_progress"` - `"completed"` - `"generating"` - `"failed"` - `type: "image_generation_call"` The type of the image generation call. Always `image_generation_call`. - `"image_generation_call"` - `action?: "generate" | "edit" | "auto" | null` The action used for image generation. - `"generate"` - `"edit"` - `"auto"` - `background?: "transparent" | "opaque" | "auto" | null` The background setting used for generation. - `"transparent"` - `"opaque"` - `"auto"` - `output_format?: "png" | "webp" | "jpeg" | null` The output format used for generation. - `"png"` - `"webp"` - `"jpeg"` - `quality?: "low" | "medium" | "high" | 3 more | null` The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `"auto"` - `revised_prompt?: string | null` The prompt that was used after any model prompt rewriting. - `size?: (string & {}) | "1024x1024" | "1024x1536" | "1536x1024" | null` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `(string & {})` - `"1024x1024" | "1024x1536" | "1536x1024"` - `"1024x1024"` - `"1024x1536"` - `"1536x1024"` - `ResponseCodeInterpreterToolCall` A tool call to run code. - `id: string` The unique ID of the code interpreter tool call. - `code: string | null` The code to run, or null if not available. - `container_id: string` The ID of the container used to run the code. - `outputs: Array | null` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. - `Logs` The logs output from the code interpreter. - `logs: string` The logs output from the code interpreter. - `type: "logs"` The type of the output. Always `logs`. - `"logs"` - `Image` The image output from the code interpreter. - `type: "image"` The type of the output. Always `image`. - `"image"` - `url: string` The URL of the image output from the code interpreter. - `status: "in_progress" | "completed" | "incomplete" | 2 more` The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"interpreting"` - `"failed"` - `type: "code_interpreter_call"` The type of the code interpreter tool call. Always `code_interpreter_call`. - `"code_interpreter_call"` - `LocalShellCall` A tool call to run a command on the local shell. - `id: string` The unique ID of the local shell call. - `action: Action` Execute a shell command on the server. - `command: Array` The command to run. - `env: Record` Environment variables to set for the command. - `type: "exec"` The type of the local shell action. Always `exec`. - `"exec"` - `timeout_ms?: number | null` Optional timeout in milliseconds for the command. - `user?: string | null` Optional user to run the command as. - `working_directory?: string | null` Optional working directory to run the command in. - `call_id: string` The unique ID of the local shell tool call generated by the model. - `status: "in_progress" | "completed" | "incomplete"` The status of the local shell call. - `"in_progress"` - `"completed"` - `"incomplete"` - `type: "local_shell_call"` The type of the local shell call. Always `local_shell_call`. - `"local_shell_call"` - `LocalShellCallOutput` The output of a local shell tool call. - `id: string` The unique ID of the local shell tool call generated by the model. - `output: string` A JSON string of the output of the local shell tool call. - `type: "local_shell_call_output"` The type of the local shell tool call output. Always `local_shell_call_output`. - `"local_shell_call_output"` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the item. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action` The shell commands and limits that describe how to run the tool call. - `commands: Array` Ordered shell commands for the execution environment to run. - `max_output_length?: number | null` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - `timeout_ms?: number | null` Maximum wall-clock time in milliseconds to allow the shell commands to run. - `call_id: string` The unique ID of the shell tool call generated by the model. - `type: "shell_call"` The type of the item. Always `shell_call`. - `"shell_call"` - `id?: string | null` The unique ID of the shell tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `environment?: LocalEnvironment | ContainerReference | null` The environment to execute the shell commands in. - `LocalEnvironment` - `ContainerReference` - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. - `"in_progress"` - `"completed"` - `"incomplete"` - `ShellCallOutput` The streamed output items emitted by a shell tool call. - `call_id: string` The unique ID of the shell tool call generated by the model. - `output: Array` Captured chunks of stdout and stderr output, along with their associated outcomes. - `outcome: Timeout | Exit` The exit or timeout outcome associated with this shell call. - `Timeout` Indicates that the shell call exceeded its configured time limit. - `type: "timeout"` The outcome type. Always `timeout`. - `"timeout"` - `Exit` Indicates that the shell commands finished and returned an exit code. - `exit_code: number` The exit code returned by the shell process. - `type: "exit"` The outcome type. Always `exit`. - `"exit"` - `stderr: string` Captured stderr output for the shell call. - `stdout: string` Captured stdout output for the shell call. - `type: "shell_call_output"` The type of the item. Always `shell_call_output`. - `"shell_call_output"` - `id?: string | null` The unique ID of the shell tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `max_output_length?: number | null` The maximum number of UTF-8 characters captured for this shell call's combined output. - `status?: "in_progress" | "completed" | "incomplete" | null` The status of the shell call output. - `"in_progress"` - `"completed"` - `"incomplete"` - `ApplyPatchCall` A tool call representing a request to create, delete, or update files using diff patches. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `operation: CreateFile | DeleteFile | UpdateFile` The specific create, delete, or update instruction for the apply_patch tool call. - `CreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: string` Unified diff content to apply when creating the file. - `path: string` Path of the file to create relative to the workspace root. - `type: "create_file"` The operation type. Always `create_file`. - `"create_file"` - `DeleteFile` Instruction for deleting an existing file via the apply_patch tool. - `path: string` Path of the file to delete relative to the workspace root. - `type: "delete_file"` The operation type. Always `delete_file`. - `"delete_file"` - `UpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: string` Unified diff content to apply to the existing file. - `path: string` Path of the file to update relative to the workspace root. - `type: "update_file"` The operation type. Always `update_file`. - `"update_file"` - `status: "in_progress" | "completed"` The status of the apply patch tool call. One of `in_progress` or `completed`. - `"in_progress"` - `"completed"` - `type: "apply_patch_call"` The type of the item. Always `apply_patch_call`. - `"apply_patch_call"` - `id?: string | null` The unique ID of the apply patch tool call. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ApplyPatchCallOutput` The streamed output emitted by an apply patch tool call. - `call_id: string` The unique ID of the apply patch tool call generated by the model. - `status: "completed" | "failed"` The status of the apply patch tool call output. One of `completed` or `failed`. - `"completed"` - `"failed"` - `type: "apply_patch_call_output"` The type of the item. Always `apply_patch_call_output`. - `"apply_patch_call_output"` - `id?: string | null` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `output?: string | null` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). - `McpListTools` A list of tools available on an MCP server. - `id: string` The unique ID of the list. - `server_label: string` The label of the MCP server. - `tools: Array` The tools available on the server. - `input_schema: unknown` The JSON schema describing the tool's input. - `name: string` The name of the tool. - `annotations?: unknown` Additional annotations about the tool. - `description?: string | null` The description of the tool. - `type: "mcp_list_tools"` The type of the item. Always `mcp_list_tools`. - `"mcp_list_tools"` - `error?: string | null` Error message if the server could not list tools. - `McpApprovalRequest` A request for human approval of a tool invocation. - `id: string` The unique ID of the approval request. - `arguments: string` A JSON string of arguments for the tool. - `name: string` The name of the tool to run. - `server_label: string` The label of the MCP server making the request. - `type: "mcp_approval_request"` The type of the item. Always `mcp_approval_request`. - `"mcp_approval_request"` - `McpApprovalResponse` A response to an MCP approval request. - `approval_request_id: string` The ID of the approval request being answered. - `approve: boolean` Whether the request was approved. - `type: "mcp_approval_response"` The type of the item. Always `mcp_approval_response`. - `"mcp_approval_response"` - `id?: string | null` The unique ID of the approval response - `reason?: string | null` Optional reason for the decision. - `McpCall` An invocation of a tool on an MCP server. - `id: string` The unique ID of the tool call. - `arguments: string` A JSON string of the arguments passed to the tool. - `name: string` The name of the tool that was run. - `server_label: string` The label of the MCP server running the tool. - `type: "mcp_call"` The type of the item. Always `mcp_call`. - `"mcp_call"` - `approval_request_id?: string | null` Unique identifier for the MCP tool call approval request. Include this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call. - `error?: McpToolCallError | null` The error from the tool call, if any. - `McpProtocolError` - `code: number` - `message: string` - `type: "mcp_protocol_error"` - `"mcp_protocol_error"` - `McpToolExecutionError` - `content: unknown` - `type: "mcp_tool_execution_error"` - `"mcp_tool_execution_error"` - `HTTPError` - `code: number` - `message: string` - `type: "http_error"` - `"http_error"` - `output?: string | null` The output from the tool call. - `status?: "in_progress" | "completed" | "incomplete" | 2 more` The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`. - `"in_progress"` - `"completed"` - `"incomplete"` - `"calling"` - `"failed"` - `ResponseCustomToolCallOutput` The output of a custom tool call from your code, being sent back to the model. - `call_id: string` The call ID, used to map this custom tool call output to a custom tool call. - `output: string | Array` The output from the custom tool call generated by your code. Can be a string or an list of output content. - `string` - `Array` - `ResponseInputText` A text input to the model. - `ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `ResponseInputFile` A file input to the model. - `type: "custom_tool_call_output"` The type of the custom tool call output. Always `custom_tool_call_output`. - `"custom_tool_call_output"` - `id?: string` The unique ID of the custom tool call output in the OpenAI platform. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` The caller type. Always `direct`. - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` The caller type. Always `program`. - `"program"` - `ResponseCustomToolCall` A call to a custom tool created by the model. - `call_id: string` An identifier used to map this custom tool call to a tool call output. - `input: string` The input for the custom tool call generated by the model. - `name: string` The name of the custom tool being called. - `type: "custom_tool_call"` The type of the custom tool call. Always `custom_tool_call`. - `"custom_tool_call"` - `id?: string` The unique ID of the custom tool call in the OpenAI platform. - `async?: boolean` Whether the custom tool call runs asynchronously. - `caller?: Direct | Program | null` The execution context that produced this tool call. - `Direct` - `type: "direct"` - `"direct"` - `Program` - `caller_id: string` The call ID of the program item that produced this tool call. - `type: "program"` - `"program"` - `namespace?: string` The namespace of the custom tool being called. - `CompactionTrigger` Compacts the current context. Must be the final input item. - `type: "compaction_trigger"` The type of the item. Always `compaction_trigger`. - `"compaction_trigger"` - `ItemReference` An internal identifier for an item to reference. - `id: string` The ID of the item to reference. - `type?: "item_reference" | null` The type of item to reference. Always `item_reference`. - `"item_reference"` - `Program` - `id: string` The unique ID of this program item. - `call_id: string` The stable call ID of the program item. - `code: string` The JavaScript source executed by programmatic tool calling. - `fingerprint: string` Opaque program replay fingerprint that must be round-tripped. - `type: "program"` The item type. Always `program`. - `"program"` - `ProgramOutput` - `id: string` The unique ID of this program output item. - `call_id: string` The call ID of the program item. - `result: string` The result produced by the program item. - `status: "completed" | "incomplete"` The terminal status of the program output. - `"completed"` - `"incomplete"` - `type: "program_output"` The item type. Always `program_output`. - `"program_output"` - `type: "response.item.create"` The Live client event type. Always `response.item.create`. - `"response.item.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `ResponseCreateEvent` Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation. - `type: "response.create"` The Live client event type. Always `response.create`. - `"response.create"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. - `SessionCloseEvent` Request that the Live session close. The terminal `session.closed` event contains the close reason and final usage. - `type: "session.close"` The Live client event type. Always `session.close`. - `"session.close"` - `event_id?: string | null` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. ### Connect Server Event - `ConnectServerEvent = SessionStartedEvent | SessionUpdatedEvent | InputAudioMutedEvent | 12 more` Server events received by an attached Live sideband WebSocket. Audio deltas are delivered over the primary connection. - `SessionStartedEvent` Returned when a Live session has started. Contains the resolved session configuration, including server defaults. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `id: string` The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download. - `expires_at: number` The Unix timestamp, in seconds, at which the Live session expires. - `model: (string & {}) | "gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `(string & {})` - `"gpt-live-1"` - `"gpt-live-1"` - `status: "active"` The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed. - `"active"` - `audio?: Audio` Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup. - `format?: AudioFormat` Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately. - `AudioPCM` Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection. - `rate: 16000 | 24000` Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz. - `16000` - `24000` - `type: "audio/pcm"` The audio encoding. Always `audio/pcm`. - `"audio/pcm"` - `AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `"audio/pcmu"` - `AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: number` Audio sample rate in hertz. G.711 audio uses 8000 Hz. - `type: "audio/pcma"` The audio encoding. Always `audio/pcma`. - `"audio/pcma"` - `output?: Output` The voice used for speech generated by the Live model. - `voice?: string | BuiltInVoice | CustomVoice` The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup. - `string` - `BuiltInVoice = "alloy" | "ash" | "ballad" | 19 more` A built-in voice available for Live speech. - `"alloy"` - `"ash"` - `"ballad"` - `"beacon"` - `"bossa"` - `"cedar"` - `"cinder"` - `"coral"` - `"delta"` - `"echo"` - `"gleam"` - `"marin"` - `"meridian"` - `"quartz"` - `"ripple"` - `"sage"` - `"shimmer"` - `"stone"` - `"tempo"` - `"verse"` - `"vesper"` - `"willow"` - `CustomVoice` - `id: string` - `client?: ClientConfig` Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected. - `data_channel: DataChannelConfig` Client and server event permissions for the WebRTC frontend data channel. - `allowed_client_events?: "all" | Array` Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior. - `"all"` - `"all"` - `Array` - `allowed_server_events?: "all" | Array` Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector. - `"all"` - `"all"` - `Array` - `type: string` The outer Live server event type. Use 'response.event' for Responses events. - `response_event?: string` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. - `delegation?: ClientDelegation | Responses | null` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend. - `ClientDelegation` Delegate tasks to your application. The Live session emits delegation events that your backend handles. - `type: "client"` The delegation owner. Always `client` for tasks handled by your application. - `"client"` - `Responses` Delegate tasks to a Responses model managed by the Live session. - `responses: ResponsesDelegationConfig` Backend model, prompt, and tools used when the Live session delegates a task to Responses. - `model: string` The model used for server-owned Responses delegations. - `instructions?: string | null` Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). - `max_output_tokens?: number | null` Maximum number of output tokens for each delegated response. - `parallel_tool_calls?: boolean | null` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning?: Reasoning | null` Reasoning settings passed to each delegated Responses request. - `effort?: "none" | "minimal" | "low" | 3 more | null` How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model. - `"none"` - `"minimal"` - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `summary?: "concise" | "detailed" | "auto" | null` The reasoning summary to request from the delegated Responses model, when supported. - `"concise"` - `"detailed"` - `"auto"` - `service_tier?: "auto" | "default" | "fast_tier_temp_pilot" | 3 more | null` Service tier for delegated Responses requests. - `"auto"` - `"default"` - `"fast_tier_temp_pilot"` - `"flex"` - `"priority"` - `"ultrafast"` - `text?: Text | null` Text generation settings passed to each delegated Responses request. - `verbosity?: "low" | "medium" | "high" | null` The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery. - `"low"` - `"medium"` - `"high"` - `tool_choice?: "auto" | "none" | "required" | LiveFunctionToolChoiceParam | LiveMCPToolChoiceParam` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `"auto" | "none" | "required"` - `"auto"` - `"none"` - `"required"` - `LiveFunctionToolChoiceParam` - `name: string` - `type: "function"` - `"function"` - `LiveMCPToolChoiceParam` - `name: string` - `server_label: string` - `type: "mcp"` - `"mcp"` - `tools?: Array` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `FunctionTool` A function tool available to the Responses backend when the Live model delegates a task. - `name: string` The name the delegated Responses model uses when calling this function. - `type: "function"` The tool type. Always `function`. - `"function"` - `description?: string | null` What the function does and when the delegated Responses model should call it. - `parameters?: Record | null` A JSON Schema object describing the arguments accepted by the function. - `strict?: boolean | null` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `WebSearch` A web search tool available to the Live session’s Responses backend. - `type: "web_search"` The tool type. Always `web_search`. - `"web_search"` - `type: "responses"` The delegation owner. Always `responses` for tasks handled by the Responses API. - `"responses"` - `input?: Array` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total. - `Developer` A developer message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "developer"` The author of this history message. Always `developer`. - `"developer"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `User` A user message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "input_text"` The text content type. Always `input_text`. - `"input_text"` - `role: "user"` The author of this history message. Always `user`. - `"user"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `Assistant` An assistant message included in the initial text history of a Live session. - `content: Array` The message content. Supply exactly one text part for the initial Live conversation history. - `Text` Assistant text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type?: "text"` The text content type. Always `text`. - `"text"` - `OutputText` Assistant output text supplied as conversation history when starting a Live session. - `text: string` The message text to include in the Live session’s initial conversation history. - `type: "output_text"` The text content type. Always `output_text`. - `"output_text"` - `role: "assistant"` The author of this history message. Always `assistant`. - `"assistant"` - `id?: string | null` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status?: "incomplete" | "completed" | null` The supplied message’s status. Live uses its text as history and does not resume an incomplete message. - `"incomplete"` - `"completed"` - `type?: "message"` The history item type. Always `message`. - `"message"` - `instructions?: string | null` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup. - `store?: boolean` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `type: "session.started"` The event type, always `session.started`. - `"session.started"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `SessionUpdatedEvent` Returned when a Live session update is accepted. Contains the resolved session configuration after the update. - `event_id: string` The unique ID of the Live server event. - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.updated"` The event type, always `session.updated`. - `"session.updated"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioMutedEvent` Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.muted"` The event type, always `session.input_audio.muted`. - `"session.input_audio.muted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputAudioUnmutedEvent` Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again. - `event_id: string` The unique ID of the Live server event. - `type: "session.input_audio.unmuted"` The event type, always `session.input_audio.unmuted`. - `"session.input_audio.unmuted"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InstructionsAppendedEvent` Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.instructions.appended"` The event type, always `session.instructions.appended`. - `"session.instructions.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ThinkingAppendedEvent` Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.thinking.appended"` The event type, always `session.thinking.appended`. - `"session.thinking.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `CommentaryAppendedEvent` Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.commentary.appended"` The event type, always `session.commentary.appended`. - `"session.commentary.appended"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InputTranscriptDeltaEvent` A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.input_transcript.delta"` The event type, always `session.input_transcript.delta`. - `"session.input_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `OutputTranscriptDeltaEvent` A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event. - `delta: string` The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript. - `end_ms: number` The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms. - `event_id: string` The unique ID of the Live server event. - `start_ms: number` The start of this event on the Live session timeline, in milliseconds from the beginning of the session. - `type: "session.output_transcript.delta"` The event type, always `session.output_transcript.delta`. - `"session.output_transcript.delta"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `DelegationCreatedEvent` Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated. - `delegation: Delegation` The delegated work identifier and destination. This object contains metadata, not the task text. - `id: string` The unique ID of the delegation. Use this as delegation_id when replying to client-owned work or correlating Responses events. - `target: "client" | "responses"` Where the Live model delegated the work: `client` for your application, or `responses` for the configured Responses backend. - `"client" | "responses"` - `"client"` - `"responses"` - `type: "delegation"` The object type, always `delegation`. - `"delegation"` - `response_id?: string` The ID of the Responses API response associated with a Responses delegation. Omitted for client delegations. - `event_id: string` The unique ID of the Live server event. - `offset_ms: number` The position on the Live session timeline where the delegation was created, in milliseconds from the beginning of the session. - `type: "session.delegation.created"` The event type, always `session.delegation.created`. - `"session.delegation.created"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ResponseEvent` A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation. - `event: Record` The nested Responses streaming event. Dispatch on its type field. Response lifecycle snapshots omit input and clear instructions, tools, and output to keep messages small; consume granular output events for the generated content. - `event_id: string` The unique ID of the Live server event. - `type: "response.event"` The event type, always `response.event`. - `"response.event"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `delegation_id?: string | null` The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation. - `SessionUsageUpdatedEvent` Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events. - `event_id: string` The unique ID of the Live server event. - `type: "session.usage.updated"` The event type, always `session.usage.updated`. - `"session.usage.updated"` - `usage: SessionUsage` The cumulative Live audio usage so far. - `seconds: number` The cumulative Live audio duration in seconds. Do not sum this value across usage events. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `context_window?: ContextWindow` The latest measured Live context-window usage. Omitted when the context limit is unknown. - `usage_ratio: number` The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames. - `SessionClosedEvent` Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization. - `event_id: string` The unique ID of the Live server event. - `reason: "close_requested" | "expired" | "content" | 2 more` Why the Live session ended: `close_requested` for an application close or hangup request, `expired` for the session duration limit, `content` for a safety filter, `remote_hangup` for a graceful remote disconnect, or `connection_lost` for an unexpected primary or upstream disconnection. - `"close_requested" | "expired" | "content" | 2 more` - `"close_requested"` - `"expired"` - `"content"` - `"remote_hangup"` - `"connection_lost"` - `session: SessionResource` The resolved Live session configuration and server-assigned session metadata. - `type: "session.closed"` The event type, always `session.closed`. - `"session.closed"` - `usage: SessionUsage` The final cumulative Live audio usage after session finalization. - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `ErrorEvent` Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error. - `error: Error` Details of the Live error and the client command that caused it, when known. - `code: string` A machine-readable code identifying the Live error, such as `unknown_parameter`. - `message: string` A human-readable explanation of the Live error. - `type: string` The category of error, such as `invalid_request_error` for an invalid Live client command. - `client_event_id?: string` The event_id of the client command that caused the error, when supplied. - `param?: string` The parameter that caused the error, when applicable, such as `session.voice`. - `event_id: string` The unique ID of the Live server event. - `type: "error"` The event type, always `error`. - `"error"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied. - `InfoEvent` An informational notice about the Live session, such as the event permissions applied to a frontend data channel. - `code: string` A machine-readable code for the notice, such as `data_channel_permissions`. - `event_id: string` The unique ID of the Live server event. - `message: string` A human-readable explanation of the Live session notice. - `type: "info"` The event type, always `info`. - `"info"` - `client_event_id?: string` The event_id of the client command associated with this server event, when supplied.