# Sideband ## Connect Attach to an existing Live session. Do not send session.start again. **WebSocket** `wss://api.openai.com/v1/live/sessions/{session_id}/attach` ### Example ```ruby require "openai" require "async" # Use an eligible existing Live session ID owned by your project. client = OpenAI::Client.new Sync do |task| # Stop waiting if the peer never sends the expected events. task.with_timeout(60) do # This block releases only the observer, not the owner's session. client.live.sideband.connect('sess_123') do |connection| complete = false connection.each do |event| case event when OpenAI::Live::ErrorEvent raise "Live reported a session error." when OpenAI::Live::SessionUsageUpdatedEvent puts "Current cumulative usage: #{event.usage}" complete = true break when OpenAI::Live::SessionClosedEvent puts "Final usage: #{event.usage}" complete = true break end end raise "Observer disconnected before a usage update or session.closed" unless complete end end end ``` ## Domain Types ### Sideband Client Event - `SidebandClientEvent = SessionUpdateEvent | InputAudioMuteEvent | InputAudioUnmuteEvent | 11 more` Client events accepted by an attached Live sideband WebSocket. The session has already started. Send input audio over the primary connection. - `class SessionUpdateEvent` Update the delegation settings or transcript triggers of an active Live session. The server acknowledges accepted changes with `session.updated`. - `session: SessionUpdateConfig` Sparse delegation and trigger updates. Omitted settings retain their values. The delegation type cannot change. Model, frontend instructions, audio, and startup input are immutable. - `delegation: ClientDelegation | Responses{ type, acknowledgement_delay_ms, responses} | Decisions{ type, acknowledgement_delay_ms, decisions}` Delegation settings to update. The delegation type must match the current session; omitted settings retain their values. - `class 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` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `class 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` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `responses: ResponsesDelegationUpdateConfig` Responses backend settings to update. Omitted settings keep their existing values. - `instructions: String` 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: Integer` Maximum number of output tokens for each delegated response. `minimum: 16` - `model: String` The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model. - `parallel_tool_calls: bool` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning: Reasoning{ effort, summary}` Reasoning settings passed to each delegated Responses request. - `effort: :none | :minimal | :low | 3 more` 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` 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` Service tier for delegated Responses requests. - `:auto` - `:default` - `:fast_tier_temp_pilot` - `:flex` - `:priority` - `:ultrafast` - `text: Text{ verbosity}` Text generation settings passed to each delegated Responses request. - `verbosity: :low | :medium | :high` 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{ name, type} | LiveMCPToolChoiceParam{ name, server_label, type} | 11 more` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `LiveToolChoiceEnum = :auto | :none | :required` - `:auto` - `:none` - `:required` - `class LiveFunctionToolChoiceParam` - `name: String` `minLength: 1`, `maxLength: 64` - `type: :function` - `:function` - `class LiveMCPToolChoiceParam` - `name: String` `minLength: 1`, `maxLength: 64` - `server_label: String` `minLength: 1`, `maxLength: 64` - `type: :mcp` - `:mcp` - `class FileSearch` - `type: :file_search` The tool to call. Always `file_search`. - `:file_search` - `class WebSearch` - `type: :web_search` The tool to call. Always `web_search`. - `:web_search` - `class WebSearchPreview` - `type: :web_search_preview` The tool to call. Always `web_search_preview`. - `:web_search_preview` - `class ImageGeneration` - `type: :image_generation` The tool to call. Always `image_generation`. - `:image_generation` - `class Computer` - `type: :computer` The tool to call. Always `computer`. - `:computer` - `class CodeInterpreter` - `type: :code_interpreter` The tool to call. Always `code_interpreter`. - `:code_interpreter` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The tool to call. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class Shell` Forces the model to call the shell tool when a tool call is required. - `type: :shell` The tool to call. Always `shell`. - `:shell` - `class Custom` - `name: String` The name of the custom tool to call. - `type: :custom` The tool to call. Always `custom`. - `:custom` - `class ApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: :apply_patch` The tool to call. Always `apply_patch`. - `:apply_patch` - `class LiveAllowedToolsChoiceParam` - `tools: Array[Function{ name, type} | Mcp{ name, server_label, type} | FileSearch{ type} | 9 more]` The tools that the delegated Responses model may call. `minItems: 1`, `maxItems: 128` - `class Function` - `name: String` `minLength: 1`, `maxLength: 64` - `type: :function` - `:function` - `class Mcp` - `name: String` `minLength: 1`, `maxLength: 64` - `server_label: String` `minLength: 1`, `maxLength: 64` - `type: :mcp` - `:mcp` - `class FileSearch` - `type: :file_search` The tool to call. Always `file_search`. - `:file_search` - `class WebSearch` - `type: :web_search` The tool to call. Always `web_search`. - `:web_search` - `class WebSearchPreview` - `type: :web_search_preview` The tool to call. Always `web_search_preview`. - `:web_search_preview` - `class ImageGeneration` - `type: :image_generation` The tool to call. Always `image_generation`. - `:image_generation` - `class Computer` - `type: :computer` The tool to call. Always `computer`. - `:computer` - `class CodeInterpreter` - `type: :code_interpreter` The tool to call. Always `code_interpreter`. - `:code_interpreter` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The tool to call. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class Shell` Forces the model to call the shell tool when a tool call is required. - `type: :shell` The tool to call. Always `shell`. - `:shell` - `class Custom` - `name: String` The name of the custom tool to call. - `type: :custom` The tool to call. Always `custom`. - `:custom` - `class ApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: :apply_patch` The tool to call. Always `apply_patch`. - `:apply_patch` - `type: :allowed_tools` The tool choice type. Always `allowed_tools`. - `:allowed_tools` - `mode: :none | :auto | :required` How to select a tool from the allowed set. - `:none` - `:auto` - `:required` - `tools: Array[FunctionTool | WebSearch{ type} | FileSearch{ type} | 10 more]` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `class 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` What the function does and when the delegated Responses model should call it. - `parameters: Hash[Symbol, untyped]` A JSON Schema object describing the arguments accepted by the function. - `strict: bool` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `class WebSearch` A web search tool available to the Live session’s Responses backend. - `type: :web_search` The tool type. Always `web_search`. - `:web_search` - `class FileSearch` - `type: :file_search` - `:file_search` - `class CodeInterpreter` - `type: :code_interpreter` - `:code_interpreter` - `class Shell` A Responses shell tool. Use a hosted container or return local shell results with response.item.create. Domain secrets are not supported. - `type: :shell` - `:shell` - `environment: ContainerAuto{ type, file_ids, memory_limit, 2 more} | ContainerReference{ container_id, type} | Local{ type, skills}` - `class ContainerAuto` - `type: :container_auto` Automatically creates a container for this request - `:container_auto` - `file_ids: Array[String]` An optional list of uploaded files to make available to your code. `maxItems: 50` - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` The memory limit for the container. - `:"1g"` - `:"4g"` - `:"16g"` - `:"64g"` - `network_policy: Disabled{ type} | Allowlist{ allowed_domains, type}` Network access policy for the container. - `class Disabled` - `type: :disabled` Disable outbound network access. Always `disabled`. - `:disabled` - `class Allowlist` - `allowed_domains: Array[String]` A list of allowed domains when type is `allowlist`. `minItems: 1` - `type: :allowlist` Allow outbound network access only to specified domains. Always `allowlist`. - `:allowlist` - `skills: Array[SkillReference{ skill_id, type, version} | Inline{ description, name, source, type}]` An optional list of skills referenced by id or inline data. `maxItems: 200` - `class SkillReference` - `skill_id: String` The ID of the referenced skill. `minLength: 1`, `maxLength: 64` - `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. - `class Inline` - `description: String` The description of the skill. - `name: String` The name of the skill. - `source: Source{ data, media_type, type}` Inline skill payload - `data: String` Base64-encoded skill zip bundle. `minLength: 1`, `maxLength: 70254592` - `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` - `class ContainerReference` - `container_id: String` The ID of the referenced container. - `type: :container_reference` References a container created with the /v1/containers endpoint - `:container_reference` - `class Local` - `type: :local` Use a local computer environment. - `:local` - `skills: Array[Skill{ description, name, path}]` An optional list of skills. `maxItems: 200` - `description: String` The description of the skill. - `name: String` The name of the skill. - `path: String` The path to the directory containing the skill. - `class ImageGeneration` - `type: :image_generation` - `:image_generation` - `class Mcp` - `type: :mcp` - `:mcp` - `class Custom` - `type: :custom` - `:custom` - `class Namespace` - `type: :namespace` - `:namespace` - `class ToolSearch` - `type: :tool_search` - `:tool_search` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` - `:programmatic_tool_calling` - `class Computer` - `type: :computer` - `:computer` - `class ApplyPatch` - `type: :apply_patch` - `:apply_patch` - `class Decisions` - `type: :decisions` - `:decisions` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `decisions: DecisionsDelegationUpdateConfig` - `model: String` `minLength: 1` - `questions: Array[DecisionQuestion]` Native Decision API questions evaluated together, in order. `minItems: 1`, `maxItems: 64` - `class Choice` - `choices: Array[DecisionChoiceOption]` `minItems: 2`, `maxItems: 255` - `value: String | bool` - `String = String` - `UnionMember1 = bool` - `description: String` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `text: String` `minLength: 0`, `maxLength: 10485760` - `type: :input_text` - `:input_text` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `image_url: String` A base64-encoded image in a data URL or a publicly accessible HTTP(S) image URL. `minLength: 0`, `maxLength: 1073741824` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` The image detail level, using the selected model's image profile. Defaults to auto. - `:low` - `:high` - `:auto` - `:original` - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `data: Hash[Symbol, untyped] | Array[Hash[Symbol, untyped]]` - `UnionMember0 = Hash[Symbol, untyped]` - `UnionMember1 = Array[Hash[Symbol, untyped]]` - `type: :input_json` - `:input_json` - `type: :choice` - `:choice` - `name: String` - `class Predicate` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `type: :predicate` - `:predicate` - `name: String` - `class Score` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `levels: Array[Level{ label, description}]` `minItems: 2`, `maxItems: 10` - `label: String` - `description: String` - `type: :score` - `:score` - `name: String` - `triggers: Array[DecisionTrigger]` At most one Decisions trigger per transcript event type. Triggers run independently of delegation. On update, omit triggers to keep the current configuration, send a list to replace it, or send an empty list to disable triggers. `maxItems: 2` - `decisions: Decisions{ questions}` Questions evaluated using the current transcript and the session's shared Decision items. - `questions: Array[DecisionQuestion]` Native Decision API questions evaluated together, in order. `minItems: 1`, `maxItems: 64` - `class Choice` - `class Predicate` - `class Score` - `event_type: :"session.input_transcript.delta" | :"session.output_transcript.delta"` - `:"session.input_transcript.delta"` - `:"session.output_transcript.delta"` - `type: :decisions` - `:decisions` - `type: :"session.update"` The Live client event type. Always `session.update`. - `:"session.update"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class 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` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class InputAudioUnmuteEvent` Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`. An active audio fixture still pauses inference until playback finishes. - `type: :"session.input_audio.unmute"` The Live client event type. Always `session.input_audio.unmute`. - `:"session.input_audio.unmute"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class OutputAudioFixturePlayEvent` Play one complete audio fixture through the session output. Send this event over the primary WebSocket or a server sideband. Audio must be raw mono PCM16 little-endian at 24 kHz, regardless of the session audio format, and at most 30 seconds. The entire payload is validated before model speech is interrupted and input is muted. Only one fixture can be active. fixture.playing acknowledges acceptance and fixture.played reports server mixer drain. These notifications are not exact transport-media boundaries. Input arriving during playback is dropped and not replayed. - `audio: String` Base64-encoded raw mono PCM16 audio, little-endian, at 24 kHz. Do not include a WAV or other container header. `minLength: 1`, `maxLength: 1920000` - `type: :"session.output_audio.fixture.play"` - `:"session.output_audio.fixture.play"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class TransportDtmfSend` Send one DTMF keypress to the SIP trunk through a Live sideband connection. This command is supported only for SIP calls. A successful send emits `transport.dtmf.sent` on sideband. If you provide `event_id`, the success notification includes it as `client_event_id`; a failure includes it as `error.client_event_id`. Send separate events for multiple keypresses. - `event: String` The DTMF key to send: one of `0`–`9`, `A`–`D`, `*`, or `#`. `minLength: 1`, `maxLength: 1` - `type: :"transport.dtmf.send"` - `:"transport.dtmf.send"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class InstructionsAppendEvent` Append developer instructions to the Live conversation while it is running, optionally associating them with an existing client delegation. Rejected while an audio fixture is active. These instructions remain in conversation history through compaction and are included in future backend delegations. For external audio, describe content already delivered so the assistant does not repeat it. - `content: String` Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts. - `delegation_id: String` 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. `minLength: 1` - `type: :"session.instructions.append"` The Live client event type. Always `session.instructions.append`. - `:"session.instructions.append"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class ThinkingAppendEvent` Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation. Rejected while an audio fixture is active. - `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` 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. `minLength: 1` - `type: :"session.thinking.append"` The Live client event type. Always `session.thinking.append`. - `:"session.thinking.append"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class CommentaryAppendEvent` Provide context the Live model can communicate to the user, optionally for an existing client delegation. Rejected while an audio fixture is active. - `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` 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. `minLength: 1` - `type: :"session.commentary.append"` The Live client event type. Always `session.commentary.append`. - `:"session.commentary.append"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class DecisionCreateEvent` Evaluate the configured questions using the current conversation and Decision inputs. Reusing an event_id is rejected for the lifetime of the session. - `event_id: String` `minLength: 1`, `maxLength: 256` - `type: :"decision.create"` - `:"decision.create"` - `class DecisionItemCreateEvent` Append an input item for future decisions without starting an evaluation or changing Live voice context. - `item: DecisionUserMessage | DecisionDeveloperMessage | DecisionSystemMessage | 5 more` - `class DecisionUserMessage` - `content: String | Array[InputText{ text, type} | InputImage{ image_url, type, detail} | InputJSON{ data, type}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[InputText{ text, type} | InputImage{ image_url, type, detail} | InputJSON{ data, type}]` - `class InputText` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `:input_text` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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` - `class InputJSON` - `data: DecisionJSONObject | Array[DecisionJSONObject]` - `DecisionJSONObject = Hash[Symbol, untyped]` - `UnionMember1 = Array[DecisionJSONObject]` - `type: :input_json` - `:input_json` - `role: :user` The message role. Always `user`. - `:user` - `id: String` The unique ID of this message item. - `type: :message` - `:message` - `class DecisionDeveloperMessage` - `content: String | Array[DecisionInputText]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText]` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `:input_text` - `role: :developer` - `:developer` - `id: String` The unique ID of this message item. - `type: :message` - `:message` - `class DecisionSystemMessage` - `content: String | Array[DecisionInputText]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText]` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `role: :system` - `:system` - `id: String` The unique ID of this message item. - `type: :message` - `:message` - `class DecisionAssistantMessage` - `content: String | Array[OutputText{ text, type} | Refusal{ refusal, type}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[OutputText{ text, type} | Refusal{ refusal, type}]` - `class OutputText` - `text: String` The text content. `maxLength: 10485760` - `type: :output_text` - `:output_text` - `class Refusal` - `refusal: String` The refusal text. `maxLength: 10485760` - `type: :refusal` - `:refusal` - `role: :assistant` - `:assistant` - `id: String` The unique ID of this message item. - `phase: :commentary | :final_answer` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `:commentary` - `:final_answer` - `type: :message` - `:message` - `class FunctionCall` - `arguments: String` The function arguments as a JSON string. - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `name: String` `minLength: 1`, `maxLength: 128` - `type: :function_call` The item type. Always `function_call`. - `:function_call` - `id: String` The local Decision item ID. - `namespace: String` The namespace of the function to call. `minLength: 1`, `maxLength: 64` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class FunctionCallOutput` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `output: String | Array[DecisionInputText | InputImage{ image_url, type, detail}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText | InputImage{ image_url, type, detail}]` - `class DecisionInputText` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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: :function_call_output` The type of the function tool call output. Always `function_call_output`. - `:function_call_output` - `id: String` The local Decision item ID. - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class CustomToolCall` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `input: String` The input to the custom tool call. - `name: String` The name of the custom tool to call. `minLength: 1`, `maxLength: 64` - `type: :custom_tool_call` The item type. Always `custom_tool_call`. - `:custom_tool_call` - `id: String` The local Decision item ID. - `namespace: String` The namespace of the function to call. `minLength: 1`, `maxLength: 64` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class CustomToolCallOutput` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `output: String | Array[DecisionInputText | InputImage{ image_url, type, detail}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText | InputImage{ image_url, type, detail}]` - `class DecisionInputText` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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: :custom_tool_call_output` - `:custom_tool_call_output` - `id: String` The local Decision item ID. - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `type: :"decision.item.create"` - `:"decision.item.create"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class DecisionItemDeleteEvent` Delete an input item from future decisions without starting an evaluation or changing Live voice context. - `item_id: String` `minLength: 1` - `type: :"decision.item.delete"` - `:"decision.item.delete"` - `event_id: String` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class 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. - `class 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 = String` A text input to the model. - `ResponseInputMessageContentList = Array[ResponseInputContent]` A list of one or many input items to the model, containing different content types. - `class 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{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `class ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `detail: :low | :high | :auto | :original` 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` The ID of the file to be sent to the model. - `image_url: String` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. `format: uri` - `prompt_cache_breakpoint: PromptCacheBreakpoint{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `class 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` 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. `format: uri` - `filename: String` The name of the file to be sent to the model. - `prompt_cache_breakpoint: PromptCacheBreakpoint{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `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` 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` - `class 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` - `class ResponseOutputMessage` An output message from the model. - `id: String` The unique ID of the output message. - `content: Array[ResponseOutputText | ResponseOutputRefusal]` The content of the output message. - `class ResponseOutputText` A text output from the model. - `annotations: Array[FileCitation{ file_id, filename, index, type} | URLCitation{ end_index, start_index, title, 2 more} | ContainerFileCitation{ container_id, end_index, file_id, 3 more} | FilePath{ file_id, index, type}]` The annotations of the text output. - `class FileCitation` A citation to a file. - `file_id: String` The ID of the file. - `filename: String` The filename of the file cited. - `index: Integer` The index in the output text at which to insert the file citation. - `type: :file_citation` The type of the file citation. Always `file_citation`. - `:file_citation` - `class URLCitation` A citation for a web resource used to generate a model response. - `end_index: Integer` The index of the last character of the URL citation in the message. - `start_index: Integer` 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. `format: uri` - `class ContainerFileCitation` A citation for a container file used to generate a model response. - `container_id: String` The ID of the container file. - `end_index: Integer` 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: Integer` 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` - `class FilePath` A path to a file. - `file_id: String` The ID of the file. - `index: Integer` 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[Logprob{ token, bytes, logprob, top_logprobs}]` - `token: String` - `bytes: Array[Integer]` - `logprob: Float` - `top_logprobs: Array[TopLogprob{ token, bytes, logprob}]` - `token: String` - `bytes: Array[Integer]` - `logprob: Float` - `class 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` 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` - `class 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[String]` The queries used to search for files. - `status: :in_progress | :searching | :completed | 2 more` The status of the file search tool call. One of `in_progress`, `searching`, `incomplete` or `failed`, - `: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[Result{ attributes, file_id, filename, 2 more}]` The results of the file search tool call. - `attributes: Hash[Symbol, String | Float | bool]` 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 = String` - `Float = Float` - `UnionMember2 = bool` - `file_id: String` The unique ID of the file. - `filename: String` The name of the file. - `score: Float` The relevance score of the file - a value between 0 and 1. `format: float` - `text: String` The text that was retrieved from the file. - `class 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[PendingSafetyCheck{ id, code, message}]` The pending safety checks for the computer call. - `id: String` The ID of the pending safety check. - `code: String` The type of the pending safety check. - `message: String` 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{ button, type, x, 2 more} | DoubleClick{ keys, type, x, y_} | Drag{ path, type, keys} | 6 more` A click action. - `class 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: Integer` The x-coordinate where the click occurred. - `y_: Integer` The y-coordinate where the click occurred. - `keys: Array[String]` The keys being held while clicking. - `class DoubleClick` A double click action. - `keys: Array[String]` 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: Integer` The x-coordinate where the double click occurred. - `y_: Integer` The y-coordinate where the double click occurred. - `class Drag` A drag action. - `path: Array[Path{ x, y_}]` 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: Integer` The x-coordinate. - `y_: Integer` The y-coordinate. - `type: :drag` Specifies the event type. For a drag action, this property is always set to `drag`. - `:drag` - `keys: Array[String]` The keys being held while dragging the mouse. - `class Keypress` A collection of keypresses the model would like to perform. - `keys: Array[String]` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: :keypress` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `:keypress` - `class Move` A mouse move action. - `type: :move` Specifies the event type. For a move action, this property is always set to `move`. - `:move` - `x: Integer` The x-coordinate to move to. - `y_: Integer` The y-coordinate to move to. - `keys: Array[String]` The keys being held while moving the mouse. - `class Screenshot` A screenshot action. - `type: :screenshot` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `:screenshot` - `class Scroll` A scroll action. - `scroll_x: Integer` The horizontal scroll distance. - `scroll_y: Integer` The vertical scroll distance. - `type: :scroll` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `:scroll` - `x: Integer` The x-coordinate where the scroll occurred. - `y_: Integer` The y-coordinate where the scroll occurred. - `keys: Array[String]` The keys being held while scrolling. - `class 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` - `class 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. - `class 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: Integer` The x-coordinate where the click occurred. - `y_: Integer` The y-coordinate where the click occurred. - `keys: Array[String]` The keys being held while clicking. - `class DoubleClick` A double click action. - `keys: Array[String]` 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: Integer` The x-coordinate where the double click occurred. - `y_: Integer` The y-coordinate where the double click occurred. - `class Drag` A drag action. - `path: Array[Path{ x, y_}]` 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: Integer` The x-coordinate. - `y_: Integer` The y-coordinate. - `type: :drag` Specifies the event type. For a drag action, this property is always set to `drag`. - `:drag` - `keys: Array[String]` The keys being held while dragging the mouse. - `class Keypress` A collection of keypresses the model would like to perform. - `keys: Array[String]` The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key. - `type: :keypress` Specifies the event type. For a keypress action, this property is always set to `keypress`. - `:keypress` - `class Move` A mouse move action. - `type: :move` Specifies the event type. For a move action, this property is always set to `move`. - `:move` - `x: Integer` The x-coordinate to move to. - `y_: Integer` The y-coordinate to move to. - `keys: Array[String]` The keys being held while moving the mouse. - `class Screenshot` A screenshot action. - `type: :screenshot` Specifies the event type. For a screenshot action, this property is always set to `screenshot`. - `:screenshot` - `class Scroll` A scroll action. - `scroll_x: Integer` The horizontal scroll distance. - `scroll_y: Integer` The vertical scroll distance. - `type: :scroll` Specifies the event type. For a scroll action, this property is always set to `scroll`. - `:scroll` - `x: Integer` The x-coordinate where the scroll occurred. - `y_: Integer` The y-coordinate where the scroll occurred. - `keys: Array[String]` The keys being held while scrolling. - `class 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` - `class Wait` A wait action. - `type: :wait` Specifies the event type. For a wait action, this property is always set to `wait`. - `:wait` - `class ComputerCallOutput` The output of a computer tool call. - `call_id: String` The ID of the computer tool call that produced the output. `minLength: 1`, `maxLength: 64` - `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. `format: uri` - `type: :computer_call_output` The type of the computer tool call output. Always `computer_call_output`. - `:computer_call_output` - `id: String` The ID of the computer tool call output. - `acknowledged_safety_checks: Array[AcknowledgedSafetyCheck{ id, code, message}]` 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` The type of the pending safety check. - `message: String` Details about the pending safety check. - `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` - `class 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{ type, queries, query, sources} | OpenPage{ type, url} | FindInPage{ pattern, type, url}` An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page). - `class Search` Action type "search" - Performs a web search query. - `type: :search` The action type. - `:search` - `queries: Array[String]` The search queries. - `query: String` The search query. - `sources: Array[Source{ type, url}]` The sources used in the search. - `type: :url` The type of source. Always `url`. - `:url` - `url: String` The URL of the source. `format: uri` - `class OpenPage` Action type "open_page" - Opens a specific URL from search results. - `type: :open_page` The action type. - `:open_page` - `url: String` The URL opened by the model. `format: uri` - `class Find` 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. `format: uri` - `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` - `class 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: bool` Whether the function tool call runs asynchronously. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` - `:direct` - `class 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` - `class FunctionCallOutput` The output of a function tool call. - `output: String | ResponseFunctionCallOutputItemList` Text, image, or file output of the function tool call. - `String = String` A JSON string of the output of the function tool call. - `ResponseFunctionCallOutputItemList = Array[ResponseFunctionCallOutputItem]` An array of content outputs (text, image, file) for the function tool call. - `class ResponseInputTextContent` A text input to the model. - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` The type of the input item. Always `input_text`. - `:input_text` - `prompt_cache_breakpoint: PromptCacheBreakpoint{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `class 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: :low | :high | :auto | :original` 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` - `file_id: String` The ID of the file to be sent to the model. - `image_url: String` The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. `maxLength: 20971520`, `format: uri` - `prompt_cache_breakpoint: PromptCacheBreakpoint{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `class 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` The base64-encoded data of the file to be sent to the model. `maxLength: 73400320` - `file_id: String` 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. `format: uri` - `filename: String` The name of the file to be sent to the model. - `prompt_cache_breakpoint: PromptCacheBreakpoint{ mode, ttl}` Marks the exact end of a reusable prompt prefix. When `ttl` is omitted, the breakpoint inherits the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. - `mode: :explicit` The breakpoint mode. Always `explicit`. - `:explicit` - `ttl: :"30m" | :"12h"` The minimum lifetime of this cache breakpoint. Defaults to the request TTL. - `:"30m"` - `:"12h"` - `type: :function_call_output` The type of the function tool call output. Always `function_call_output`. - `:function_call_output` - `id: String` The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `name: String` The name of the tool that produced the output. `minLength: 1`, `maxLength: 128` - `namespace: String` The namespace of the tool that produced the output. `minLength: 1`, `maxLength: 64` - `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` - `class ToolSearchCall` - `arguments: untyped` The arguments supplied to the tool search call. - `type: :tool_search_call` The item type. Always `tool_search_call`. - `:tool_search_call` - `id: String` The unique ID of this tool search call. - `call_id: String` The unique ID of the tool search call generated by the model. `minLength: 1`, `maxLength: 64` - `execution: :server | :client` Whether tool search was executed by the server or by the client. - `:server` - `:client` - `status: :in_progress | :completed | :incomplete` The status of the tool search call. - `:in_progress` - `:completed` - `:incomplete` - `class ResponseToolSearchOutputItemParam` - `tools: Array[FunctionTool | FileSearchTool | ComputerTool | 13 more]` The loaded tool definitions returned by the tool search output. - `class 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: Hash[Symbol, untyped]` A JSON schema object describing the parameters of the function. - `strict: bool` 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]` The tool invocation context(s). - `:direct` - `:programmatic` - `async: bool` - `defer_loading: bool` Whether this function is deferred and loaded via tool search. - `description: String` A description of the function. Used by the model to determine whether or not to call the function. - `output_schema: Hash[Symbol, untyped]` A JSON schema object describing the JSON value encoded in string outputs for this function. - `class 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[String]` The IDs of the vector stores to search. - `filters: ComparisonFilter | CompoundFilter` A filter to apply. - `class 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 | Float | bool | Array[String | Float]` The value to compare against the attribute key; supports string, number, or boolean types. - `String = String` - `Float = Float` - `UnionMember2 = bool` - `UnionMember3 = Array[String | Float]` - `String = String` - `Float = Float` - `class CompoundFilter` Combine multiple filters using `and` or `or`. - `filters: Array[ComparisonFilter | untyped]` Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. - `class ComparisonFilter` A filter used to compare a specified attribute key to a given value using a defined comparison operation. - `UnionMember1 = untyped` - `type: :and | :or` Type of operation: `and` or `or`. - `:and` - `:or` - `max_num_results: Integer` The maximum number of results to return. This number should be between 1 and 50 inclusive. - `ranking_options: RankingOptions{ hybrid_search, ranker, score_threshold}` Ranking options for search. - `hybrid_search: HybridSearch{ embedding_weight, text_weight}` Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled. - `embedding_weight: Float` The weight of the embedding in the reciprocal ranking fusion. - `text_weight: Float` 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: Float` 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. - `class 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` - `class ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `display_height: Integer` The height of the computer display. - `display_width: Integer` 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` - `class 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: bool` 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{ allowed_domains}` Filters for the search. - `allowed_domains: Array[String]` 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{ city, country, region, 2 more}` The approximate location of the user. If omitted or null, defaults to the United States. To avoid this fallback, pass `{"type": "approximate"}` without location fields. To localize results, provide the relevant location fields. - `city: String` Free text input for the city of the user, e.g. `San Francisco`. - `country: String` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region: String` Free text input for the region of the user, e.g. `California`. - `timezone: String` 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` - `class 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]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `allowed_tools: Array[String] | McpToolFilter{ read_only, tool_names}` List of allowed tool names or a filter object. - `McpAllowedTools = Array[String]` A string array of allowed tool names - `class McpToolFilter` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `authorization: String` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id: :connector_dropbox | :connector_gmail | :connector_googlecalendar | 5 more` 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). This field is deprecated for models released after September 1, 2026. Use `server_url` to connect to a remote MCP server, or `tunnel_id` to connect through a Secure MCP Tunnel. Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` - `:connector_dropbox` - `:connector_gmail` - `:connector_googlecalendar` - `:connector_googledrive` - `:connector_microsoftteams` - `:connector_outlookcalendar` - `:connector_outlookemail` - `:connector_sharepoint` - `defer_loading: bool` Whether this MCP tool is deferred and discovered via tool search. - `headers: Hash[Symbol, String]` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval: McpToolApprovalFilter{ always, never} | :always | :never` Specify which of the MCP server's tools require approval. - `class 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{ read_only, tool_names}` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `never: Never{ read_only, tool_names}` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `McpToolApprovalSetting = :always | :never` Specify a single approval policy for all tools. One of `always` or `never`. When set to `always`, all tools will require approval. When set to `never`, all tools will not require approval. - `: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. `format: uri` - `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. - `class CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: String | CodeInterpreterToolAuto{ type, file_ids, memory_limit, network_policy}` The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional `memory_limit` setting. - `String = String` The container ID. - `class 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[String]` An optional list of uploaded files to make available to your code. `maxItems: 50` - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` The memory limit for the code interpreter container. - `:"1g"` - `:"4g"` - `:"16g"` - `:"64g"` - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `class ContainerNetworkPolicyDisabled` - `type: :disabled` Disable outbound network access. Always `disabled`. - `:disabled` - `class ContainerNetworkPolicyAllowlist` - `allowed_domains: Array[String]` A list of allowed domains when type is `allowlist`. `minItems: 1` - `type: :allowlist` Allow outbound network access only to specified domains. Always `allowlist`. - `:allowlist` - `domain_secrets: Array[ContainerNetworkPolicyDomainSecret]` Optional domain-scoped secrets for allowlisted domains. `minItems: 1` - `domain: String` The domain associated with the secret. `minLength: 1` - `name: String` The name of the secret to inject for the domain. `minLength: 1` - `value: String` The secret value to inject for the domain. `minLength: 1`, `maxLength: 10485760` - `type: :code_interpreter` The type of the code interpreter tool. Always `code_interpreter`. - `:code_interpreter` - `allowed_callers: Array[:direct | :programmatic]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The type of the tool. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class 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` - `complexity: :low | :medium | :high` Computation spent planning the image, independently of rendering quality. Overrides the outer response's `reasoning.effort` for image generation. When omitted, inherits a supported outer reasoning effort or uses the image model's configured default. For SVG output, controls the reference image, not the SVG author's reasoning. - `:low` - `:medium` - `:high` - `frame_count: Integer` Number of GIF frames. Requires `output_format` to be `gif`. Default: 9. `minimum: 2`, `maximum: 16` - `frame_duration_ms: Integer` Duration of each GIF frame in milliseconds, rounded to 10 ms. Requires `output_format` to be `gif`. Default: 200. `minimum: 20`, `maximum: 2000` - `input_fidelity: :high | :low` Control how much effort the model will exert to match the style and features, especially facial features, of input images. Supports `high` and `low` on `gpt-image-1.5`; `gpt-image-1-mini` supports only `low`. For `gpt-image-2`, omit this parameter. Defaults to `low` on supported models. - `:high` - `:low` - `input_image_mask: InputImageMask{ file_id, image_url}` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id: String` File ID for the mask image. - `image_url: String` Base64-encoded mask image. - `model: String | :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 9 more` The image generation model to use. One of `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`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-flare`, or `chatgpt-image-latest`. Default: `gpt-image-2`. `gpt-image-1` was shut down on October 23, 2026. Use `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead. - `String = String` - `Model = :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 9 more` The image generation model to use. One of `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`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-flare`, or `chatgpt-image-latest`. Default: `gpt-image-2`. `gpt-image-1` was shut down on October 23, 2026. Use `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead. - `:"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-2.6-sunburst"` - `:"gpt-image-2.6-flare"` - `:"gpt-image-1.5"` - `:"chatgpt-image-latest"` - `moderation: :auto | :low` Moderation level for the generated image. Default: `auto`. - `:auto` - `:low` - `output_compression: Integer` Compression level for the output image. Default: 100. `minimum: 0`, `maximum: 100` - `output_format: :png | :webp | :jpeg | 2 more` The output format of the generated image. One of `png`, `webp`, `jpeg`, `gif`, or `svg`. Default: `png`. GIF and SVG output require a model that supports the selected format. GIF output does not support partial image streaming (`partial_images` greater than `0`), `input_image_mask`, or custom `output_compression`. Responses lifecycle events can still be streamed for GIF output. - `:png` - `:webp` - `:jpeg` - `:gif` - `:svg` - `partial_images: Integer` Number of partial images to generate in streaming mode, from 0 (default value) to 3. `minimum: 0`, `maximum: 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. - `String = String` - `Size = :"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. - `:"1024x1024"` - `:"1024x1536"` - `:"1536x1024"` - `:auto` - `svg: Svg{ model, reasoning}` SVG author model settings. Requires `output_format` to be `svg`. When SVG model selection is enabled, omitting this object uses the outer response model. Otherwise, the default SVG author is used and explicit model overrides are unavailable. - `model: String` `minLength: 1` - `reasoning: Reasoning{ effort}` Reasoning effort for SVG authoring. When omitted, uses the author model's default in both Images and Responses. - `effort: :none | :minimal | :low | 4 more` Controls how much effort the model should spend on reasoning for this request. - `:none` - `:minimal` - `:low` - `:medium` - `:high` - `:xhigh` - `:max` - `class 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` - `class 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]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `environment: ContainerAuto | LocalEnvironment | ContainerReference` - `class ContainerAuto` - `type: :container_auto` Automatically creates a container for this request - `:container_auto` - `file_ids: Array[String]` An optional list of uploaded files to make available to your code. `maxItems: 50` - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` The memory limit for the container. - `:"1g"` - `:"4g"` - `:"16g"` - `:"64g"` - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `class ContainerNetworkPolicyDisabled` - `class ContainerNetworkPolicyAllowlist` - `skills: Array[SkillReference | InlineSkill]` An optional list of skills referenced by id or inline data. `maxItems: 200` - `class SkillReference` - `skill_id: String` The ID of the referenced skill. `minLength: 1`, `maxLength: 64` - `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. - `class 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. `minLength: 1`, `maxLength: 70254592` - `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` - `class LocalEnvironment` - `type: :local` Use a local computer environment. - `:local` - `skills: Array[LocalSkill]` An optional list of skills. `maxItems: 200` - `description: String` The description of the skill. - `name: String` The name of the skill. - `path: String` The path to the directory containing the skill. - `class ContainerReference` - `container_id: String` The ID of the referenced container. - `type: :container_reference` References a container created with the /v1/containers endpoint - `:container_reference` - `class 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]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `async: bool` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading: bool` 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. - `class Text` Unconstrained free-form text. - `type: :text` Unconstrained text format. Always `text`. - `:text` - `class 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` - `class ToolSearchOutputNamespaceTool` 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`). `minLength: 1` - `tools: Array[Function{ name, type, allowed_callers, 6 more} | CustomTool]` The function/custom tools loaded inside this namespace. `minItems: 1` - `class Function` - `name: String` The name of the loaded function tool. `minLength: 1`, `maxLength: 128` - `type: :function` - `:function` - `allowed_callers: Array[:direct | :programmatic]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `async: bool` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading: bool` Whether this function should be deferred and discovered via tool search. - `description: String` - `output_schema: Hash[Symbol, untyped]` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters: untyped` - `strict: bool` 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. - `class 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` - `class 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` 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: untyped` Parameter schema for a client-executed tool search tool. - `class 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{ type, city, country, 2 more}` The approximate location of the user. If omitted or null, defaults to the United States. To avoid this fallback, pass `{"type": "approximate"}` without location fields. To localize results, provide the relevant location fields. - `type: :approximate` The type of location approximation. Always `approximate`. - `:approximate` - `city: String` Free text input for the city of the user, e.g. `San Francisco`. - `country: String` The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`. - `region: String` Free text input for the region of the user, e.g. `California`. - `timezone: String` The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`. - `class 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]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `type: :tool_search_output` The item type. Always `tool_search_output`. - `:tool_search_output` - `id: String` The unique ID of this tool search output. - `call_id: String` The unique ID of the tool search call generated by the model. `minLength: 1`, `maxLength: 64` - `execution: :server | :client` Whether tool search was executed by the server or by the client. - `:server` - `:client` - `status: :in_progress | :completed | :incomplete` The status of the tool search output. - `:in_progress` - `:completed` - `:incomplete` - `class AdditionalTools` - `role: :developer` The role that provided the additional tools. Only `developer` is supported. - `:developer` - `tools: Array[Tool]` A list of additional tools made available at this item. - `class FunctionTool` Defines a function in your own code the model can choose to call. Learn more about [function calling](/api/docs/guides/function-calling). - `class FileSearchTool` A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](/api/docs/guides/tools-file-search). - `class ComputerTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `class ComputerUsePreviewTool` A tool that controls a virtual computer. Learn more about the [computer tool](/api/docs/guides/tools-computer-use). - `class WebSearchTool` Search the Internet for sources related to the prompt. Learn more about the [web search tool](/api/docs/guides/tools-web-search). - `class 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]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `allowed_tools: Array[String] | McpToolFilter{ read_only, tool_names}` List of allowed tool names or a filter object. - `McpAllowedTools = Array[String]` A string array of allowed tool names - `class McpToolFilter` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `authorization: String` An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `connector_id: :connector_dropbox | :connector_gmail | :connector_googlecalendar | 5 more` 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). This field is deprecated for models released after September 1, 2026. Use `server_url` to connect to a remote MCP server, or `tunnel_id` to connect through a Secure MCP Tunnel. Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` - `:connector_dropbox` - `:connector_gmail` - `:connector_googlecalendar` - `:connector_googledrive` - `:connector_microsoftteams` - `:connector_outlookcalendar` - `:connector_outlookemail` - `:connector_sharepoint` - `defer_loading: bool` Whether this MCP tool is deferred and discovered via tool search. - `headers: Hash[Symbol, String]` Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `require_approval: McpToolApprovalFilter{ always, never} | :always | :never` Specify which of the MCP server's tools require approval. - `class 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{ read_only, tool_names}` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `never: Never{ read_only, tool_names}` A filter object to specify which tools are allowed. - `read_only: bool` 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[String]` List of allowed tool names. - `McpToolApprovalSetting = :always | :never` Specify a single approval policy for all tools. One of `always` or `never`. When set to `always`, all tools will require approval. When set to `never`, all tools will not require approval. - `: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. `format: uri` - `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. - `class CodeInterpreter` A tool that runs Python code to help generate a response to a prompt. - `container: String | CodeInterpreterToolAuto{ type, file_ids, memory_limit, network_policy}` The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional `memory_limit` setting. - `String = String` The container ID. - `class 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[String]` An optional list of uploaded files to make available to your code. `maxItems: 50` - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` The memory limit for the code interpreter container. - `:"1g"` - `:"4g"` - `:"16g"` - `:"64g"` - `network_policy: ContainerNetworkPolicyDisabled | ContainerNetworkPolicyAllowlist` Network access policy for the container. - `class ContainerNetworkPolicyDisabled` - `class ContainerNetworkPolicyAllowlist` - `type: :code_interpreter` The type of the code interpreter tool. Always `code_interpreter`. - `:code_interpreter` - `allowed_callers: Array[:direct | :programmatic]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The type of the tool. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class 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` - `complexity: :low | :medium | :high` Computation spent planning the image, independently of rendering quality. Overrides the outer response's `reasoning.effort` for image generation. When omitted, inherits a supported outer reasoning effort or uses the image model's configured default. For SVG output, controls the reference image, not the SVG author's reasoning. - `:low` - `:medium` - `:high` - `frame_count: Integer` Number of GIF frames. Requires `output_format` to be `gif`. Default: 9. `minimum: 2`, `maximum: 16` - `frame_duration_ms: Integer` Duration of each GIF frame in milliseconds, rounded to 10 ms. Requires `output_format` to be `gif`. Default: 200. `minimum: 20`, `maximum: 2000` - `input_fidelity: :high | :low` Control how much effort the model will exert to match the style and features, especially facial features, of input images. Supports `high` and `low` on `gpt-image-1.5`; `gpt-image-1-mini` supports only `low`. For `gpt-image-2`, omit this parameter. Defaults to `low` on supported models. - `:high` - `:low` - `input_image_mask: InputImageMask{ file_id, image_url}` Optional mask for inpainting. Contains `image_url` (string, optional) and `file_id` (string, optional). - `file_id: String` File ID for the mask image. - `image_url: String` Base64-encoded mask image. - `model: String | :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 9 more` The image generation model to use. One of `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`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-flare`, or `chatgpt-image-latest`. Default: `gpt-image-2`. `gpt-image-1` was shut down on October 23, 2026. Use `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead. - `String = String` - `Model = :"gpt-image-1" | :"gpt-image-1-mini" | :"gpt-image-2" | 9 more` The image generation model to use. One of `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`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-flare`, or `chatgpt-image-latest`. Default: `gpt-image-2`. `gpt-image-1` was shut down on October 23, 2026. Use `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead. - `:"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-2.6-sunburst"` - `:"gpt-image-2.6-flare"` - `:"gpt-image-1.5"` - `:"chatgpt-image-latest"` - `moderation: :auto | :low` Moderation level for the generated image. Default: `auto`. - `:auto` - `:low` - `output_compression: Integer` Compression level for the output image. Default: 100. `minimum: 0`, `maximum: 100` - `output_format: :png | :webp | :jpeg | 2 more` The output format of the generated image. One of `png`, `webp`, `jpeg`, `gif`, or `svg`. Default: `png`. GIF and SVG output require a model that supports the selected format. GIF output does not support partial image streaming (`partial_images` greater than `0`), `input_image_mask`, or custom `output_compression`. Responses lifecycle events can still be streamed for GIF output. - `:png` - `:webp` - `:jpeg` - `:gif` - `:svg` - `partial_images: Integer` Number of partial images to generate in streaming mode, from 0 (default value) to 3. `minimum: 0`, `maximum: 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. - `String = String` - `Size = :"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. - `:"1024x1024"` - `:"1024x1536"` - `:"1536x1024"` - `:auto` - `svg: Svg{ model, reasoning}` SVG author model settings. Requires `output_format` to be `svg`. When SVG model selection is enabled, omitting this object uses the outer response model. Otherwise, the default SVG author is used and explicit model overrides are unavailable. - `model: String` `minLength: 1` - `reasoning: Reasoning{ effort}` Reasoning effort for SVG authoring. When omitted, uses the author model's default in both Images and Responses. - `effort: :none | :minimal | :low | 4 more` Controls how much effort the model should spend on reasoning for this request. - `:none` - `:minimal` - `:low` - `:medium` - `:high` - `:xhigh` - `:max` - `class 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` - `class FunctionShellTool` A tool that allows the model to execute shell commands. - `class CustomTool` A custom tool that processes input using a specified format. Learn more about [custom tools](/api/docs/guides/function-calling#custom-tools) - `class 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`). `minLength: 1` - `tools: Array[Function{ name, type, allowed_callers, 6 more} | CustomTool]` The function/custom tools available inside this namespace. `minItems: 1` - `class Function` - `name: String` `minLength: 1`, `maxLength: 128` - `type: :function` - `:function` - `allowed_callers: Array[:direct | :programmatic]` The tool invocation context(s). `minItems: 1` - `:direct` - `:programmatic` - `async: bool` Whether the tool response can be returned asynchronously versus immediately returned on next response creation. - `defer_loading: bool` Whether this function should be deferred and discovered via tool search. - `description: String` - `output_schema: Hash[Symbol, untyped]` A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs. - `parameters: untyped` - `strict: bool` 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. - `class 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` - `class ToolSearchTool` Hosted or BYOT tool search configuration for deferred tools. - `class 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). - `class 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` The unique ID of this additional tools item. - `class ResponseConfigurationUpdateItemParam` An update to the conversation's response configuration. Supply reasoning, text, or both. Each setting stays in effect until a later update replaces it. - `type: :configuration_update` The item type. Always `configuration_update`. - `:configuration_update` - `id: String` The unique ID of the configuration update item. - `reasoning: Reasoning{ effort}` Updates to reasoning configuration. Only effort is supported. - `effort: ReasoningEffort` The reasoning effort to use for subsequent responses until another configuration update replaces it. - `:none` - `:minimal` - `:low` - `:medium` - `:high` - `:xhigh` - `:max` - `text: Text{ format_}` The text output configuration for subsequent responses. - `format_: ResponseFormatText | ResponseFormatTextJSONSchemaConfig` Use a JSON schema for structured output or text to return to plain text. - `class ResponseFormatText` Default response format. Used to generate text responses. - `type: :text` The type of response format being defined. Always `text`. - `:text` - `class ResponseFormatTextJSONSchemaConfig` JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](/api/docs/guides/structured-outputs). - `name: String` The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - `schema: Hash[Symbol, untyped]` The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). - `type: :json_schema` The type of response format being defined. Always `json_schema`. - `:json_schema` - `description: String` A description of what the response format is for, used by the model to determine how to respond in the format. - `strict: bool` Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. To learn more, read the [Structured Outputs guide](/api/docs/guides/structured-outputs). - `class 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[Summary{ text, type}]` Reasoning summary content. - `text: String` A summary of the reasoning output from the model so far. - `type: :summary_text` The type of the object. Always `summary_text`. - `:summary_text` - `type: :reasoning` The type of the object. Always `reasoning`. - `:reasoning` - `content: Array[Content{ text, type}]` Reasoning text content. - `text: String` The reasoning text from the model. - `type: :reasoning_text` The type of the reasoning text. Always `reasoning_text`. - `:reasoning_text` - `encrypted_content: String` 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` - `class 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. `maxLength: 104857600` - `type: :compaction` The type of the item. Always `compaction`. - `:compaction` - `id: String` The ID of the compaction item. - `class ImageGenerationCall` An image generation request made by the model. - `id: String` The unique ID of the image generation call. - `result: String` 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` The action used for image generation. - `:generate` - `:edit` - `:auto` - `background: :transparent | :opaque | :auto` The background setting used for generation. - `:transparent` - `:opaque` - `:auto` - `error: Error{ code, message, param, 2 more}` Details of a moderation failure, when available. - `code: String` The error code. - `message: String` A description of the error. - `param: String` The related request parameter. - `type: String` The error type. - `moderation_details: ModerationDetails{ categories, moderation_stage}` Public details for a `moderation_blocked` error, when available. - `categories: Array[String]` Public moderation categories. New category values may be added over time. - `moderation_stage: :input | :output | :unknown` The stage where moderation blocked the image generation call. - `:input` - `:output` - `:unknown` - `output_format: :png | :webp | :jpeg | 2 more` The output format used for generation. - `:png` - `:webp` - `:jpeg` - `:gif` - `:svg` - `quality: :low | :medium | :high | 3 more` 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` The prompt that was used after any model prompt rewriting. - `size: String | :"1024x1024" | :"1024x1536" | :"1536x1024"` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `String = String` - `Size = :"1024x1024" | :"1024x1536" | :"1536x1024"` The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`. - `:"1024x1024"` - `:"1024x1536"` - `:"1536x1024"` - `svg_usage: SvgUsage{ input_tokens, model, output_tokens, 2 more}` - `input_tokens: Integer` - `model: String` - `output_tokens: Integer` - `reasoning_tokens: Integer` - `total_tokens: Integer` - `class ResponseCodeInterpreterToolCall` A tool call to run code. - `id: String` The unique ID of the code interpreter tool call. - `code: String` The code to run, or null if not available. - `container_id: String` The ID of the container used to run the code. - `outputs: Array[Logs{ logs, type} | Image{ type, url}]` The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available. - `class 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` - `class 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. `format: uri` - `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` - `class LocalShellCall` A tool call to run a command on the local shell. - `id: String` The unique ID of the local shell call. - `action: Action{ command, env, type, 3 more}` Execute a shell command on the server. - `command: Array[String]` The command to run. - `env: Hash[Symbol, String]` Environment variables to set for the command. - `type: :exec` The type of the local shell action. Always `exec`. - `:exec` - `timeout_ms: Integer` Optional timeout in milliseconds for the command. - `user: String` Optional user to run the command as. - `working_directory: String` 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` - `class 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` The status of the item. One of `in_progress`, `completed`, or `incomplete`. - `:in_progress` - `:completed` - `:incomplete` - `class ShellCall` A tool representing a request to execute one or more shell commands. - `action: Action{ commands, max_output_length, timeout_ms}` The shell commands and limits that describe how to run the tool call. - `commands: Array[String]` Ordered shell commands for the execution environment to run. - `max_output_length: Integer` Maximum number of UTF-8 characters to capture from combined stdout and stderr output. - `timeout_ms: Integer` 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. `minLength: 1`, `maxLength: 64` - `type: :shell_call` The type of the item. Always `shell_call`. - `:shell_call` - `id: String` The unique ID of the shell tool call. Populated when this item is returned via API. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `environment: LocalEnvironment | ContainerReference` The environment to execute the shell commands in. - `class LocalEnvironment` - `class ContainerReference` - `status: :in_progress | :completed | :incomplete` The status of the shell call. One of `in_progress`, `completed`, or `incomplete`. - `:in_progress` - `:completed` - `:incomplete` - `class 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. `minLength: 1`, `maxLength: 64` - `output: Array[ResponseFunctionShellCallOutputContent]` Captured chunks of stdout and stderr output, along with their associated outcomes. - `outcome: Timeout{ type} | Exit{ exit_code, type}` The exit or timeout outcome associated with this shell call. - `class Timeout` Indicates that the shell call exceeded its configured time limit. - `type: :timeout` The outcome type. Always `timeout`. - `:timeout` - `class Exit` Indicates that the shell commands finished and returned an exit code. - `exit_code: Integer` 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. `maxLength: 10485760` - `stdout: String` Captured stdout output for the shell call. `maxLength: 10485760` - `type: :shell_call_output` The type of the item. Always `shell_call_output`. - `:shell_call_output` - `id: String` The unique ID of the shell tool call output. Populated when this item is returned via API. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `max_output_length: Integer` The maximum number of UTF-8 characters captured for this shell call's combined output. - `status: :in_progress | :completed | :incomplete` The status of the shell call output. - `:in_progress` - `:completed` - `:incomplete` - `class 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. `minLength: 1`, `maxLength: 64` - `operation: CreateFile{ diff, path, type} | DeleteFile{ path, type} | UpdateFile{ diff, path, type}` The specific create, delete, or update instruction for the apply_patch tool call. - `class CreateFile` Instruction for creating a new file via the apply_patch tool. - `diff: String` Unified diff content to apply when creating the file. `maxLength: 10485760` - `path: String` Path of the file to create relative to the workspace root. `minLength: 1` - `type: :create_file` The operation type. Always `create_file`. - `:create_file` - `class 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. `minLength: 1` - `type: :delete_file` The operation type. Always `delete_file`. - `:delete_file` - `class UpdateFile` Instruction for updating an existing file via the apply_patch tool. - `diff: String` Unified diff content to apply to the existing file. `maxLength: 10485760` - `path: String` Path of the file to update relative to the workspace root. `minLength: 1` - `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` The unique ID of the apply patch tool call. Populated when this item is returned via API. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `class 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. `minLength: 1`, `maxLength: 64` - `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` The unique ID of the apply patch tool call output. Populated when this item is returned via API. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `output: String` Optional human-readable log text from the apply patch tool (e.g., patch results or errors). `maxLength: 10485760` - `class 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[Tool{ input_schema, name, annotations, description}]` The tools available on the server. - `input_schema: untyped` The JSON schema describing the tool's input. - `name: String` The name of the tool. - `annotations: untyped` Additional annotations about the tool. - `description: String` The description of the tool. - `type: :mcp_list_tools` The type of the item. Always `mcp_list_tools`. - `:mcp_list_tools` - `error: String` Error message if the server could not list tools. - `class 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` - `class McpApprovalResponse` A response to an MCP approval request. - `approval_request_id: String` The ID of the approval request being answered. - `approve: bool` Whether the request was approved. - `type: :mcp_approval_response` The type of the item. Always `mcp_approval_response`. - `:mcp_approval_response` - `id: String` The unique ID of the approval response - `reason: String` Optional reason for the decision. - `class 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` 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` The error from the tool call, if any. - `class McpProtocolError` - `code: Integer` - `message: String` - `type: :mcp_protocol_error` - `:mcp_protocol_error` - `class McpToolExecutionError` - `content: untyped` - `type: :mcp_tool_execution_error` - `:mcp_tool_execution_error` - `class HTTPError` - `code: Integer` - `message: String` - `type: :http_error` - `:http_error` - `output: String` 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` - `class 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[ResponseInputText | ResponseInputImage | ResponseInputFile]` The output from the custom tool call generated by your code. Can be a string or an list of output content. - `String = String` A string of the output of the custom tool call. - `OutputContentList = Array[ResponseInputText | ResponseInputImage | ResponseInputFile]` Text, image, or file output of the custom tool call. - `class ResponseInputText` A text input to the model. - `class ResponseInputImage` An image input to the model. Learn about [image inputs](/api/docs/guides/images-vision). - `class 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{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` The caller type. Always `direct`. - `:direct` - `class Program` - `caller_id: String` The call ID of the program item that produced this tool call. `minLength: 1`, `maxLength: 64` - `type: :program` The caller type. Always `program`. - `:program` - `class 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: bool` Whether the custom tool call runs asynchronously. - `caller_: Direct{ type} | Program{ caller_id, type}` The execution context that produced this tool call. - `class Direct` - `type: :direct` - `:direct` - `class 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. - `class CompactionTrigger` Compacts the current context. Must be the final input item. - `type: :compaction_trigger` The type of the item. Always `compaction_trigger`. - `:compaction_trigger` - `id: String` The unique ID of this compaction trigger. - `class ItemReference` An internal identifier for an item to reference. - `id: String` The ID of the item to reference. - `type: :item_reference` The type of item to reference. Always `item_reference`. - `:item_reference` - `class Program` - `id: String` The unique ID of this program item. - `call_id: String` The stable call ID of the program item. `minLength: 1`, `maxLength: 64` - `code: String` The JavaScript source executed by programmatic tool calling. `maxLength: 10485760` - `fingerprint: String` Opaque program replay fingerprint that must be round-tripped. `maxLength: 10485760` - `type: :program` The item type. Always `program`. - `:program` - `class ProgramOutput` - `id: String` The unique ID of this program output item. - `call_id: String` The call ID of the program item. `minLength: 1`, `maxLength: 64` - `result: String` The result produced by the program item. `maxLength: 10485760` - `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` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class 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` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` - `class 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` Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id. `maxLength: 512` ### Sideband Server Event - `SidebandServerEvent = SessionStartedEvent | SessionUpdatedEvent | InputAudioMutedEvent | 25 more` Server events received by an attached Live sideband WebSocket, including reflected input and output audio and transport notifications. - `class 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: Integer` 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 = String` - `Model = :"gpt-live-1"` The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter. - `:"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{ format_, output}` 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. - `class 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. `minimum: 16000`, `maximum: 24000` - `16000` - `24000` - `type: :"audio/pcm"` The audio encoding. Always `audio/pcm`. - `:"audio/pcm"` - `class AudioPCMU` Raw, mono G.711 μ-law audio for a Live WebSocket connection. - `rate: Integer` Audio sample rate in hertz. G.711 audio uses 8000 Hz. `minimum: 8000`, `maximum: 8000` - `type: :"audio/pcmu"` The audio encoding. Always `audio/pcmu`. - `:"audio/pcmu"` - `class AudioPCMA` Raw, mono G.711 A-law audio for a Live WebSocket connection. - `rate: Integer` Audio sample rate in hertz. G.711 audio uses 8000 Hz. `minimum: 8000`, `maximum: 8000` - `type: :"audio/pcma"` The audio encoding. Always `audio/pcma`. - `:"audio/pcma"` - `output: Output{ voice}` 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 = String` - `BuiltInVoice = :alloy | :ash | :ballad | 20 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` - `:shida` - `:shimmer` - `:stone` - `:tempo` - `:verse` - `:vesper` - `:willow` - `class CustomVoice` - `id: String` `minLength: 1`, `maxLength: 128` - `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[String]` 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. - `AllowedClientEvents = :all` - `:all` - `UnionMember1 = Array[String]` - `allowed_server_events: :all | Array[ServerEventSelector]` 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. - `AllowedServerEvents = :all` - `:all` - `EventSelectors = Array[ServerEventSelector]` - `type: String` The outer Live server event type. Use 'response.event' for Responses events. `minLength: 1`, `maxLength: 256` - `response_event: String` The nested Responses event type. Required when type is 'response.event'; forbidden for other event types. `minLength: 1`, `maxLength: 256` - `delegation: ClientDelegation | Responses{ responses, type, acknowledgement_delay_ms} | Decisions{ decisions, type, acknowledgement_delay_ms}` Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` or `decisions` to delegate to the corresponding API. - `class 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` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `class 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` 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: Integer` Maximum number of output tokens for each delegated response. `minimum: 16` - `parallel_tool_calls: bool` Whether the delegated Responses model may request multiple tool calls in a single response. - `reasoning: Reasoning{ effort, summary}` Reasoning settings passed to each delegated Responses request. - `effort: :none | :minimal | :low | 3 more` 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` 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` Service tier for delegated Responses requests. - `:auto` - `:default` - `:fast_tier_temp_pilot` - `:flex` - `:priority` - `:ultrafast` - `text: Text{ verbosity}` Text generation settings passed to each delegated Responses request. - `verbosity: :low | :medium | :high` 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{ name, type} | LiveMCPToolChoiceParam{ name, server_label, type} | 11 more` Controls which tool the Responses backend uses when handling a task delegated by the Live model. - `LiveToolChoiceEnum = :auto | :none | :required` - `:auto` - `:none` - `:required` - `class LiveFunctionToolChoiceParam` - `name: String` `minLength: 1`, `maxLength: 64` - `type: :function` - `:function` - `class LiveMCPToolChoiceParam` - `name: String` `minLength: 1`, `maxLength: 64` - `server_label: String` `minLength: 1`, `maxLength: 64` - `type: :mcp` - `:mcp` - `class FileSearch` - `type: :file_search` The tool to call. Always `file_search`. - `:file_search` - `class WebSearch` - `type: :web_search` The tool to call. Always `web_search`. - `:web_search` - `class WebSearchPreview` - `type: :web_search_preview` The tool to call. Always `web_search_preview`. - `:web_search_preview` - `class ImageGeneration` - `type: :image_generation` The tool to call. Always `image_generation`. - `:image_generation` - `class Computer` - `type: :computer` The tool to call. Always `computer`. - `:computer` - `class CodeInterpreter` - `type: :code_interpreter` The tool to call. Always `code_interpreter`. - `:code_interpreter` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The tool to call. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class Shell` Forces the model to call the shell tool when a tool call is required. - `type: :shell` The tool to call. Always `shell`. - `:shell` - `class Custom` - `name: String` The name of the custom tool to call. - `type: :custom` The tool to call. Always `custom`. - `:custom` - `class ApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: :apply_patch` The tool to call. Always `apply_patch`. - `:apply_patch` - `class LiveAllowedToolsChoiceParam` - `tools: Array[Function{ name, type} | Mcp{ name, server_label, type} | FileSearch{ type} | 9 more]` The tools that the delegated Responses model may call. `minItems: 1`, `maxItems: 128` - `class Function` - `name: String` `minLength: 1`, `maxLength: 64` - `type: :function` - `:function` - `class Mcp` - `name: String` `minLength: 1`, `maxLength: 64` - `server_label: String` `minLength: 1`, `maxLength: 64` - `type: :mcp` - `:mcp` - `class FileSearch` - `type: :file_search` The tool to call. Always `file_search`. - `:file_search` - `class WebSearch` - `type: :web_search` The tool to call. Always `web_search`. - `:web_search` - `class WebSearchPreview` - `type: :web_search_preview` The tool to call. Always `web_search_preview`. - `:web_search_preview` - `class ImageGeneration` - `type: :image_generation` The tool to call. Always `image_generation`. - `:image_generation` - `class Computer` - `type: :computer` The tool to call. Always `computer`. - `:computer` - `class CodeInterpreter` - `type: :code_interpreter` The tool to call. Always `code_interpreter`. - `:code_interpreter` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` The tool to call. Always `programmatic_tool_calling`. - `:programmatic_tool_calling` - `class Shell` Forces the model to call the shell tool when a tool call is required. - `type: :shell` The tool to call. Always `shell`. - `:shell` - `class Custom` - `name: String` The name of the custom tool to call. - `type: :custom` The tool to call. Always `custom`. - `:custom` - `class ApplyPatch` Forces the model to call the apply_patch tool when executing a tool call. - `type: :apply_patch` The tool to call. Always `apply_patch`. - `:apply_patch` - `type: :allowed_tools` The tool choice type. Always `allowed_tools`. - `:allowed_tools` - `mode: :none | :auto | :required` How to select a tool from the allowed set. - `:none` - `:auto` - `:required` - `tools: Array[FunctionTool | WebSearch{ type} | FileSearch{ type} | 10 more]` Tools available to the Responses backend while it handles tasks delegated by the Live model. - `class 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` What the function does and when the delegated Responses model should call it. - `parameters: Hash[Symbol, untyped]` A JSON Schema object describing the arguments accepted by the function. - `strict: bool` Whether the delegated Responses model must follow the function’s parameter schema exactly. - `class WebSearch` A web search tool available to the Live session’s Responses backend. - `type: :web_search` The tool type. Always `web_search`. - `:web_search` - `class FileSearch` - `type: :file_search` - `:file_search` - `class CodeInterpreter` - `type: :code_interpreter` - `:code_interpreter` - `class Shell` A Responses shell tool. Use a hosted container or return local shell results with response.item.create. Domain secrets are not supported. - `type: :shell` - `:shell` - `environment: ContainerAuto{ type, file_ids, memory_limit, 2 more} | ContainerReference{ container_id, type} | Local{ type, skills}` - `class ContainerAuto` - `type: :container_auto` Automatically creates a container for this request - `:container_auto` - `file_ids: Array[String]` An optional list of uploaded files to make available to your code. `maxItems: 50` - `memory_limit: :"1g" | :"4g" | :"16g" | :"64g"` The memory limit for the container. - `:"1g"` - `:"4g"` - `:"16g"` - `:"64g"` - `network_policy: Disabled{ type} | Allowlist{ allowed_domains, type}` Network access policy for the container. - `class Disabled` - `type: :disabled` Disable outbound network access. Always `disabled`. - `:disabled` - `class Allowlist` - `allowed_domains: Array[String]` A list of allowed domains when type is `allowlist`. `minItems: 1` - `type: :allowlist` Allow outbound network access only to specified domains. Always `allowlist`. - `:allowlist` - `skills: Array[SkillReference{ skill_id, type, version} | Inline{ description, name, source, type}]` An optional list of skills referenced by id or inline data. `maxItems: 200` - `class SkillReference` - `skill_id: String` The ID of the referenced skill. `minLength: 1`, `maxLength: 64` - `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. - `class Inline` - `description: String` The description of the skill. - `name: String` The name of the skill. - `source: Source{ data, media_type, type}` Inline skill payload - `data: String` Base64-encoded skill zip bundle. `minLength: 1`, `maxLength: 70254592` - `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` - `class ContainerReference` - `container_id: String` The ID of the referenced container. - `type: :container_reference` References a container created with the /v1/containers endpoint - `:container_reference` - `class Local` - `type: :local` Use a local computer environment. - `:local` - `skills: Array[Skill{ description, name, path}]` An optional list of skills. `maxItems: 200` - `description: String` The description of the skill. - `name: String` The name of the skill. - `path: String` The path to the directory containing the skill. - `class ImageGeneration` - `type: :image_generation` - `:image_generation` - `class Mcp` - `type: :mcp` - `:mcp` - `class Custom` - `type: :custom` - `:custom` - `class Namespace` - `type: :namespace` - `:namespace` - `class ToolSearch` - `type: :tool_search` - `:tool_search` - `class ProgrammaticToolCalling` - `type: :programmatic_tool_calling` - `:programmatic_tool_calling` - `class Computer` - `type: :computer` - `:computer` - `class ApplyPatch` - `type: :apply_patch` - `:apply_patch` - `type: :responses` The delegation owner. Always `responses` for tasks handled by the Responses API. - `:responses` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `class Decisions` - `decisions: DecisionsDelegationConfig` - `model: String` `minLength: 1` - `questions: Array[DecisionQuestion]` Native Decision API questions evaluated together, in order. `minItems: 1`, `maxItems: 64` - `class Choice` - `choices: Array[DecisionChoiceOption]` `minItems: 2`, `maxItems: 255` - `value: String | bool` - `String = String` - `UnionMember1 = bool` - `description: String` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `text: String` `minLength: 0`, `maxLength: 10485760` - `type: :input_text` - `:input_text` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `image_url: String` A base64-encoded image in a data URL or a publicly accessible HTTP(S) image URL. `minLength: 0`, `maxLength: 1073741824` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` The image detail level, using the selected model's image profile. Defaults to auto. - `:low` - `:high` - `:auto` - `:original` - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `data: Hash[Symbol, untyped] | Array[Hash[Symbol, untyped]]` - `UnionMember0 = Hash[Symbol, untyped]` - `UnionMember1 = Array[Hash[Symbol, untyped]]` - `type: :input_json` - `:input_json` - `type: :choice` - `:choice` - `name: String` - `class Predicate` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `type: :predicate` - `:predicate` - `name: String` - `class Score` - `instructions: String | Array[DecisionQuestionInputPart]` - `String = String` - `Parts = Array[DecisionQuestionInputPart]` - `class DecisionQuestionInputText` - `class DecisionQuestionInputImage` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `class DecisionInputJSON` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `levels: Array[Level{ label, description}]` `minItems: 2`, `maxItems: 10` - `label: String` - `description: String` - `type: :score` - `:score` - `name: String` - `type: :decisions` - `:decisions` - `acknowledgement_delay_ms: Integer` Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400. Updates apply to subsequent delegations. `minimum: 0`, `maximum: 800` - `input: Array[InitialItem]` Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and a configured rendered-token limit (8,192 by default). `maxItems: 128` - `class Developer` A developer message included in the initial text history of a Live session. - `content: Array[Content{ text, type}]` The message content. Supply exactly one text part for the initial Live conversation history. `minItems: 1`, `maxItems: 1` - `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` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status: :incomplete | :completed` 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` - `class User` A user message included in the initial text history of a Live session. - `content: Array[Content{ text, type}]` The message content. Supply exactly one text part for the initial Live conversation history. `minItems: 1`, `maxItems: 1` - `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` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status: :incomplete | :completed` 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` - `class Assistant` An assistant message included in the initial text history of a Live session. - `content: Array[Text{ text, type} | OutputText{ text, type}]` The message content. Supply exactly one text part for the initial Live conversation history. `minItems: 1`, `maxItems: 1` - `class 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` - `class 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` An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation. - `status: :incomplete | :completed` 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` Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](https://developers.openai.com/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: bool` Whether to store the session for later forking and recording download. Defaults to false for new sessions. - `triggers: Array[DecisionTrigger]` At most one Decisions trigger per transcript event type. Triggers run independently of delegation. On update, omit triggers to keep the current configuration, send a list to replace it, or send an empty list to disable triggers. `maxItems: 2` - `decisions: Decisions{ questions}` Questions evaluated using the current transcript and the session's shared Decision items. - `questions: Array[DecisionQuestion]` Native Decision API questions evaluated together, in order. `minItems: 1`, `maxItems: 64` - `class Choice` - `class Predicate` - `class Score` - `event_type: :"session.input_transcript.delta" | :"session.output_transcript.delta"` - `:"session.input_transcript.delta"` - `:"session.output_transcript.delta"` - `type: :decisions` - `:decisions` - `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. - `class 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. - `class InputAudioMutedEvent` Acknowledges a session.input_audio.mute command. An independent input mute sends silence to the model and preserves sideband audio reflection. Fixture playback does not emit this event. - `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. - `class InputAudioUnmutedEvent` Acknowledges a session.input_audio.unmute command, removing the independent input mute. An active audio fixture still pauses inference until playback finishes. Fixture playback does not emit this event. - `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. - `class OutputAudioFixturePlayingEvent` The existing playback path has accepted the validated audio fixture. This acknowledgment does not identify when the listener receives the first sample. The optional client_event_id echoes the play command. - `event_id: String` The unique ID of the Live server event. - `type: :"session.output_audio.fixture.playing"` - `:"session.output_audio.fixture.playing"` - `client_event_id: String` The event_id of the client command associated with this server event, when supplied. - `class OutputAudioFixturePlayedEvent` The complete audio fixture has drained from the server mixer and normal inference has resumed. Transport buffers may still contain audio; this event does not prove listener-side completion. The optional client_event_id echoes the play command. This event is not emitted for canceled or failed playback. - `event_id: String` The unique ID of the Live server event. - `type: :"session.output_audio.fixture.played"` - `:"session.output_audio.fixture.played"` - `client_event_id: String` The event_id of the client command associated with this server event, when supplied. - `class 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: Integer` 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: Integer` 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. - `class 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: Integer` 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: Integer` 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. - `class 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: Integer` 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: Integer` 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. - `class 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: Integer` 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: Integer` 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. - `class 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: Integer` 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: Integer` 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. - `class DelegationCreatedEvent` Returned when the Live model delegates work to your application, Responses, or Decisions. Contains delegation metadata and the position on the session timeline where the work was delegated. - `delegation: Delegation{ id, target, type, response_id}` 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 backend events. - `target: :client | :responses | :decisions` Where the Live model delegated the work: `client`, `responses`, or `decisions`. - `Target = :client | :responses | :decisions` Where the Live model delegated the work: `client`, `responses`, or `decisions`. - `:client` - `:responses` - `:decisions` - `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: Integer` 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. - `class DecisionEvent` A Decision API event for a Live delegation or transcript trigger. For a trigger, source_event_id identifies the transcript delta that caused this evaluation. - `delegation_id: String` The Live delegation ID, or null for a transcript trigger. - `event: Event{ decision, type}` - `decision: Decision` The native Decision API response, including its model, ordered answers, and token usage. - `answers: Array[Predicate{ name, probability, type} | Choice{ choice, confidence, name, 2 more} | Score{ confidence, name, probabilities, 2 more} | Refusal{ name, type}]` Answers in question order. Any question can return a refusal instead of an answer; other questions can still receive answers. A refusal has `type: "refusal"` and the question's `name`, or `null` if it was unnamed. `minItems: 0`, `maxItems: 2000` - `class Predicate` - `name: String` `minLength: 0` - `probability: Float` - `type: :predicate` The type of the object. Always `predicate`. - `:predicate` - `class Choice` - `choice: String | bool` Choice values are typed: a string and a boolean with the same text are distinct. - `String = String` - `UnionMember1 = bool` - `confidence: Float` - `name: String` `minLength: 0` - `probabilities: Array[Probability{ probability, value}]` `minItems: 0`, `maxItems: 2000` - `probability: Float` - `value: String | bool` Choice values are typed: a string and a boolean with the same text are distinct. - `String = String` - `UnionMember1 = bool` - `type: :choice` The type of the object. Always `choice`. - `:choice` - `class Score` - `confidence: Float` - `name: String` `minLength: 0` - `probabilities: Array[Probability{ label, probability, value}]` `minItems: 0`, `maxItems: 2000` - `label: String` `minLength: 0` - `probability: Float` - `value: Integer` `format: int64` - `score: Float` - `type: :score` The type of the object. Always `score`. - `:score` - `class Refusal` The model declined to answer this question. Other questions in the same request can still receive answers. - `name: String` `minLength: 0` - `type: :refusal` The type of the object. Always `refusal`. - `:refusal` - `model: String` The model used. `minLength: 0` - `usage: Usage{ input_tokens, input_tokens_details, output_tokens, 2 more}` Token usage for the request. - `input_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `input_tokens_details: InputTokensDetails{ cache_write_tokens, cached_tokens}` - `cache_write_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `cached_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `output_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `output_tokens_details: OutputTokensDetails{ reasoning_tokens}` - `reasoning_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `total_tokens: Integer` `format: int64`, `minimum: -2147483648`, `maximum: 2147483647` - `type: :"decision.completed"` - `:"decision.completed"` - `event_id: String` The unique ID of this Live server event. - `source_event_id: String` The event_id of the transcript delta that fired this trigger, or null for a delegation. - `source_event_type: :"session.input_transcript.delta" | :"session.output_transcript.delta"` - `SourceEventType = :"session.input_transcript.delta" | :"session.output_transcript.delta"` - `:"session.input_transcript.delta"` - `:"session.output_transcript.delta"` - `trigger_id: String` The Live-assigned ID of this trigger firing, or null for a delegation. - `type: :"decision.event"` - `:"decision.event"` - `class DecisionItemCreatedEvent` An input item was appended for future decisions. - `event_id: String` The unique ID of the Live server event. - `item: DecisionStoredUserMessage | DecisionStoredDeveloperMessage | DecisionStoredSystemMessage | 5 more` - `class DecisionStoredUserMessage` - `id: String` - `content: String | Array[InputText{ text, type} | InputImage{ image_url, type, detail} | InputJSON{ data, type}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[InputText{ text, type} | InputImage{ image_url, type, detail} | InputJSON{ data, type}]` - `class InputText` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `:input_text` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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` - `class InputJSON` - `data: DecisionJSONObject | Array[DecisionJSONObject]` - `DecisionJSONObject = Hash[Symbol, untyped]` - `UnionMember1 = Array[DecisionJSONObject]` - `type: :input_json` - `:input_json` - `role: :user` The message role. Always `user`. - `:user` - `type: :message` - `:message` - `class DecisionStoredDeveloperMessage` - `id: String` - `content: String | Array[DecisionInputText]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText]` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `:input_text` - `role: :developer` - `:developer` - `type: :message` - `:message` - `class DecisionStoredSystemMessage` - `id: String` - `content: String | Array[DecisionInputText]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText]` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `role: :system` - `:system` - `type: :message` - `:message` - `class DecisionStoredAssistantMessage` - `id: String` - `content: String | Array[OutputText{ text, type} | Refusal{ refusal, type}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[OutputText{ text, type} | Refusal{ refusal, type}]` - `class OutputText` - `text: String` The text content. `maxLength: 10485760` - `type: :output_text` - `:output_text` - `class Refusal` - `refusal: String` The refusal text. `maxLength: 10485760` - `type: :refusal` - `:refusal` - `role: :assistant` - `:assistant` - `phase: :commentary | :final_answer` Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages. - `:commentary` - `:final_answer` - `type: :message` - `:message` - `class FunctionCall` - `id: String` - `arguments: String` The function arguments as a JSON string. - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `name: String` `minLength: 1`, `maxLength: 128` - `type: :function_call` The item type. Always `function_call`. - `:function_call` - `namespace: String` The namespace of the function to call. `minLength: 1`, `maxLength: 64` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class FunctionCallOutput` - `id: String` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `output: String | Array[DecisionInputText | InputImage{ image_url, type, detail}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText | InputImage{ image_url, type, detail}]` - `class DecisionInputText` - `text: String` The text input to the model. `maxLength: 10485760` - `type: :input_text` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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: :function_call_output` The type of the function tool call output. Always `function_call_output`. - `:function_call_output` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class CustomToolCall` - `id: String` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `input: String` The input to the custom tool call. - `name: String` The name of the custom tool to call. `minLength: 1`, `maxLength: 64` - `type: :custom_tool_call` The item type. Always `custom_tool_call`. - `:custom_tool_call` - `namespace: String` The namespace of the function to call. `minLength: 1`, `maxLength: 64` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `class CustomToolCallOutput` - `id: String` - `call_id: String` The unique ID of the function tool call generated by the model. `minLength: 1`, `maxLength: 64` - `output: String | Array[DecisionInputText | InputImage{ image_url, type, detail}]` The text input to the model. - `String = String` The text input to the model. - `Parts = Array[DecisionInputText | InputImage{ image_url, type, detail}]` - `class DecisionInputText` - `class InputImage` - `image_url: String` A base64-encoded image data URL or a publicly accessible HTTP(S) image URL. `maxLength: 20971520` - `type: :input_image` - `:input_image` - `detail: :low | :high | :auto | :original` 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: :custom_tool_call_output` - `:custom_tool_call_output` - `status: :in_progress | :completed | :incomplete` - `:in_progress` - `:completed` - `:incomplete` - `type: :"decision.item.created"` - `:"decision.item.created"` - `client_event_id: String` The event_id of the client command associated with this server event, when supplied. - `class DecisionItemDeletedEvent` An input item was removed from future decisions. - `event_id: String` The unique ID of the Live server event. - `item_id: String` - `type: :"decision.item.deleted"` - `:"decision.item.deleted"` - `client_event_id: String` The event_id of the client command associated with this server event, when supplied. - `class 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: Hash[Symbol, untyped]` 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` The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation. - `class 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: Float` 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{ usage_ratio}` The latest measured Live context-window usage. Omitted when the context limit is unknown. - `usage_ratio: Float` The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames. - `class 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. - `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` - `: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. - `class 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. - `class 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. - `class 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"` - `class 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: Integer` 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: Integer` Inclusive session-relative start in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. - `class TransportDtmfReceived` A SIP DTMF keypress received from the caller. Delivered only to sideband observers. - `event: String` `minLength: 1`, `maxLength: 1` - `event_id: String` - `type: :"transport.dtmf.received"` - `:"transport.dtmf.received"` - `class TransportDtmfSend` Legacy SIP DTMF delivery notification retained for SDK compatibility and saved events. Current servers confirm delivery with transport.dtmf.sent; transport.dtmf.send is now the client command. - `event: String` `minLength: 1`, `maxLength: 1` - `event_id: String` - `type: :"transport.dtmf.send"` - `:"transport.dtmf.send"` - `client_event_id: String` The event_id of the client command, when supplied. - `class TransportDtmfSent` A SIP DTMF keypress successfully sent to the SIP trunk. Delivered only to sideband observers; this is not a client command. - `event: String` `minLength: 1`, `maxLength: 1` - `event_id: String` - `type: :"transport.dtmf.sent"` - `:"transport.dtmf.sent"` - `client_event_id: String` The event_id of the client command, when supplied. - `class 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"` - `class 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"` - `class TransportFailed` An asynchronous outbound SIP setup failure. Delivered only to sideband observers. - `error: Error{ code, message, type, param}` - `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"`