> ## Documentation Index > Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Response > Generate a model response using the OpenAI Responses schema. Set `stream: true` to receive typed server-sent events followed by `data: [DONE]`. The Router API accepts the OpenAI Responses schema with a defined subset of parameters. This endpoint is stateless: send the full conversation in `input` on each request. **Honored:** `model`, `input`, `instructions`, `include` (`reasoning.encrypted_content`), `tools`, `tool_choice`, `text`, `temperature`, `top_p`, `parallel_tool_calls`, `stream`, `max_output_tokens`, `reasoning`, `prompt_cache_key`, `truncation` (`disabled`), and `service_tier` (`auto`, `default`, `flex`, `priority`). **Accepted but not forwarded to the model:** `metadata` and `safety_identifier`. Both fields are echoed in the response. **Accepted only at their default values:** `store` (`false`), `background` (`false`), `presence_penalty` (0), and `frequency_penalty` (0). **Rejected with a 400:** non-null `previous_response_id`, `store: true`, `background: true`, `max_tool_calls`, `top_logprobs`, `truncation: "auto"`, `include: ["message.output_text.logprobs"]`, file or video input, item references, `tool_choice` with `allowed_tools`, `text.format` with `json_object`, `text.format.strict: false`, `stream_options.include_obfuscation: true`, plus any unrecognized top-level field. **Notes:** Function tools require a `description`. JSON Schema output always runs in strict mode. `stream_options` requires `stream: true`. Set `stream: true` to receive typed server-sent events such as `response.created`, `response.output_text.delta`, and `response.completed`. A successful stream ends with `data: [DONE]`. If an error occurs after streaming begins, the stream emits an `error` event followed by `response.failed` and closes without a `[DONE]` trailer. Errors use the Responses envelope: ```json theme={null} { "error": { "type": "invalid_request", "code": null, "message": "model is required", "param": "model" } } ``` `type` is `invalid_request` for invalid requests, `not_found` when a resource is unavailable, `too_many_requests` for `429`, and `server_error` for server failures. Retry rate-limit and overload errors after the `Retry-After` interval. Requests that fail before producing output are not billed. ## OpenAPI ````yaml post /router/v1/responses openapi: 3.0.3 info: title: Perplexity Router API (OpenAI Responses-compatible) description: >- OpenAI Responses-compatible access to models across providers. Schema structure is derived from the Apache-2.0-licensed OpenResponses specification and documents the Router's supported request and response shapes. version: '2026-04-24' servers: - url: https://api.perplexity.ai security: [] paths: /router/v1/responses: post: summary: Create Response description: >- Generate a model response using the OpenAI Responses schema. Set `stream: true` to receive typed server-sent events followed by `data: [DONE]`. operationId: gateway_create_response requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateResponseBody' responses: '200': description: >- Successful response. JSON for non-streaming requests; a `text/event-stream` of typed response events when `stream` is true. content: application/json: schema: $ref: '#/components/schemas/ResponseResource' text/event-stream: schema: $ref: '#/components/schemas/ResponseStreamEvent' '400': description: >- Invalid request — malformed body, unsupported parameter, or a model that is not available on the Router. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: >- Rate limit exceeded or the selected model is overloaded. Retry after the `Retry-After` interval. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: The request could not be completed because of a server error. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - HTTPBearer: [] components: schemas: CreateResponseBody: properties: model: type: string description: >- The model that will process the request, as a `creator/model-name` id from the Router catalog. input: oneOf: - type: string maxLength: 10485760 - items: $ref: '#/components/schemas/ItemParam' type: array description: >- Context to provide to the model for the scope of this request. May either be a string or an array of input items. If a string is provided, it is interpreted as a user message. include: items: $ref: '#/components/schemas/IncludeEnum' type: array tools: nullable: true items: $ref: '#/components/schemas/ResponsesToolParam' type: array description: >- A list of tools that the model may call while generating the response. tool_choice: $ref: '#/components/schemas/ToolChoiceParam' metadata: $ref: '#/components/schemas/MetadataParam' text: $ref: '#/components/schemas/TextParam' temperature: nullable: true type: number description: >- Sampling temperature to use, between 0 and 2. Higher values make the output more random. top_p: nullable: true type: number description: >- Nucleus sampling parameter, between 0 and 1. The model considers only the tokens with the top cumulative probability. parallel_tool_calls: nullable: true type: boolean description: Whether the model may call multiple tools in parallel. stream: type: boolean description: Whether to stream response events as server-sent events. max_output_tokens: nullable: true type: integer minimum: 16 description: >- The maximum number of tokens the model may generate for this response. reasoning: $ref: '#/components/schemas/ReasoningParam' safety_identifier: nullable: true type: string maxLength: 64 description: A stable identifier used for safety monitoring and abuse detection. prompt_cache_key: nullable: true type: string maxLength: 64 description: A key to use when reading from or writing to the prompt cache. truncation: $ref: '#/components/schemas/TruncationEnum' instructions: nullable: true type: string description: Additional instructions to guide the model for this request. service_tier: $ref: '#/components/schemas/ServiceTierEnum' type: object required: - model - input ResponseResource: properties: id: type: string description: The unique ID of the response that was created. object: type: string enum: - response description: The object type, which was always `response`. default: response created_at: type: integer description: The Unix timestamp (in seconds) for when the response was created. completed_at: nullable: true type: integer description: >- The Unix timestamp (in seconds) for when the response was completed, if it was completed. status: type: string description: The status that was set for the response. incomplete_details: nullable: true description: Details about why the response was incomplete, if applicable. allOf: - $ref: '#/components/schemas/IncompleteDetails' model: type: string description: The model that generated this response. previous_response_id: nullable: true type: string description: >- The ID of the previous response in the chain that was referenced, if any. instructions: nullable: true oneOf: - type: string description: >- Additional instructions that were used to guide the model for this response. output: items: $ref: '#/components/schemas/ItemField' type: array description: The output items that were generated by the model. error: nullable: true description: The error that occurred, if the response failed. allOf: - $ref: '#/components/schemas/Error' tools: items: $ref: '#/components/schemas/Tool' type: array description: >- The tools that were available to the model during response generation. tool_choice: oneOf: - $ref: '#/components/schemas/FunctionToolChoice' - $ref: '#/components/schemas/ToolChoiceValueEnum' - $ref: '#/components/schemas/AllowedToolChoice' truncation: $ref: '#/components/schemas/TruncationEnum' parallel_tool_calls: type: boolean description: Whether the model was allowed to call multiple tools in parallel. text: type: object additionalProperties: true description: The text output configuration used for this response. top_p: type: number description: The nucleus sampling parameter that was used for this response. presence_penalty: type: number description: >- The presence penalty that was used to penalize new tokens based on whether they appear in the text so far. frequency_penalty: type: number description: >- The frequency penalty that was used to penalize new tokens based on their frequency in the text so far. top_logprobs: type: integer description: >- The number of most likely tokens that were returned at each position, along with their log probabilities. temperature: type: number description: The sampling temperature that was used for this response. reasoning: nullable: true type: object additionalProperties: true description: The reasoning configuration used for this response. usage: nullable: true description: >- Token usage statistics that were recorded for the response, if available. allOf: - $ref: '#/components/schemas/Usage' max_output_tokens: nullable: true type: integer description: >- The maximum number of tokens the model was allowed to generate for this response. max_tool_calls: nullable: true type: integer description: >- The maximum number of tool calls the model was allowed to make while generating the response. store: type: boolean description: Whether this response was stored so it can be retrieved later. background: type: boolean description: Whether this request was run in the background. service_tier: type: string description: The service tier that was used for this response. metadata: description: Developer-defined metadata associated with the response. safety_identifier: nullable: true type: string description: >- A stable identifier that was used for safety monitoring and abuse detection. prompt_cache_key: nullable: true type: string description: A key that was used to read from or write to the prompt cache. type: object required: - id - object - created_at - completed_at - status - incomplete_details - model - previous_response_id - instructions - output - error - tools - tool_choice - truncation - parallel_tool_calls - text - top_p - presence_penalty - frequency_penalty - top_logprobs - temperature - reasoning - usage - max_output_tokens - max_tool_calls - store - background - service_tier - metadata - safety_identifier - prompt_cache_key title: The response object description: The complete response object that was returned by the Responses API. ResponseStreamEvent: title: Response stream event description: One event in a streamed response. oneOf: - $ref: '#/components/schemas/ResponseCreatedStreamingEvent' - $ref: '#/components/schemas/ResponseQueuedStreamingEvent' - $ref: '#/components/schemas/ResponseInProgressStreamingEvent' - $ref: '#/components/schemas/ResponseCompletedStreamingEvent' - $ref: '#/components/schemas/ResponseFailedStreamingEvent' - $ref: '#/components/schemas/ResponseIncompleteStreamingEvent' - $ref: '#/components/schemas/ResponseOutputItemAddedStreamingEvent' - $ref: '#/components/schemas/ResponseOutputItemDoneStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryPartAddedStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryPartDoneStreamingEvent' - $ref: '#/components/schemas/ResponseContentPartAddedStreamingEvent' - $ref: '#/components/schemas/ResponseContentPartDoneStreamingEvent' - $ref: '#/components/schemas/ResponseOutputTextDeltaStreamingEvent' - $ref: '#/components/schemas/ResponseOutputTextDoneStreamingEvent' - $ref: '#/components/schemas/ResponseRefusalDeltaStreamingEvent' - $ref: '#/components/schemas/ResponseRefusalDoneStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningDeltaStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningDoneStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryDeltaStreamingEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryDoneStreamingEvent' - $ref: '#/components/schemas/ResponseOutputTextAnnotationAddedStreamingEvent' - $ref: >- #/components/schemas/ResponseFunctionCallArgumentsDeltaStreamingEvent - $ref: '#/components/schemas/ResponseFunctionCallArgumentsDoneStreamingEvent' - $ref: '#/components/schemas/ResponseCustomToolCallInputDeltaStreamingEvent' - $ref: '#/components/schemas/ResponseCustomToolCallInputDoneStreamingEvent' - $ref: '#/components/schemas/ErrorStreamingEvent' ErrorResponse: properties: error: $ref: '#/components/schemas/ErrorPayload' type: object required: - error title: Error response description: An error returned before streaming begins. ItemParam: oneOf: - $ref: '#/components/schemas/AdditionalToolsItemParam' - $ref: '#/components/schemas/ReasoningItemParam' - $ref: '#/components/schemas/UserMessageItemParam' - $ref: '#/components/schemas/SystemMessageItemParam' - $ref: '#/components/schemas/DeveloperMessageItemParam' - $ref: '#/components/schemas/AssistantMessageItemParam' - $ref: '#/components/schemas/FunctionCallItemParam' - $ref: '#/components/schemas/FunctionCallOutputItemParam' - $ref: '#/components/schemas/CustomToolCallItemParam' - $ref: '#/components/schemas/CustomToolCallOutputItemParam' discriminator: propertyName: type x-unionDisplay: section x-unionTitle: Input Item Types IncludeEnum: type: string enum: - reasoning.encrypted_content description: '' x-enumDescriptions: reasoning.encrypted_content: >- includes encrypted reasoning content so that it may be rehydrated on a subsequent request. ResponsesToolParam: oneOf: - $ref: '#/components/schemas/FunctionToolParam' - $ref: '#/components/schemas/CustomToolParam' - $ref: '#/components/schemas/NamespaceToolParam' discriminator: propertyName: type x-unionDisplay: section x-unionTitle: Tool Types ToolChoiceParam: oneOf: - $ref: '#/components/schemas/SpecificToolChoiceParam' - $ref: '#/components/schemas/ToolChoiceValueEnum' description: Controls which tool the model should use, if any. MetadataParam: additionalProperties: type: string maxLength: 512 type: object maxProperties: 16 description: >- 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. TextParam: properties: format: $ref: '#/components/schemas/TextFormatParam' verbosity: $ref: '#/components/schemas/VerbosityEnum' type: object ReasoningParam: properties: effort: nullable: true oneOf: - $ref: '#/components/schemas/ReasoningEffortEnum' description: >- Controls the level of reasoning effort the model should apply. Higher effort may increase latency and cost. summary: $ref: '#/components/schemas/ReasoningSummaryEnum' type: object description: >- **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). TruncationEnum: type: string enum: - disabled x-enumDescriptions: auto: Let the service decide how to truncate. disabled: >- Disable service truncation. Context over the model's context limit will result in a 400 error. ServiceTierEnum: type: string enum: - auto - default - flex - priority x-enumDescriptions: auto: Choose a service tier automatically based on current account state. default: Choose the default service tier. flex: Choose the flex service tier. priority: Choose the priority service tier. IncompleteDetails: properties: reason: type: string description: The reason the response could not be completed. type: object required: - reason title: Incomplete details description: Details about why the response was incomplete. ItemField: oneOf: - $ref: '#/components/schemas/Message' - $ref: '#/components/schemas/FunctionCall' - $ref: '#/components/schemas/FunctionCallOutput' - $ref: '#/components/schemas/CustomToolCall' - $ref: '#/components/schemas/ReasoningBody' description: >- An item representing a message, tool call, tool output, reasoning, or other response element. discriminator: propertyName: type Error: properties: code: type: string description: A machine-readable error code that was returned. message: type: string description: A human-readable description of the error that was returned. type: object required: - code - message title: Error description: An error that occurred while generating the response. Tool: oneOf: - $ref: '#/components/schemas/FunctionTool' description: A tool that can be used to generate a response. discriminator: propertyName: type FunctionToolChoice: properties: type: type: string enum: - function default: function name: type: string type: object required: - type ToolChoiceValueEnum: type: string enum: - none - auto - required x-enumDescriptions: auto: Let the model choose the tools from among the provided set. none: Restrict the model from calling any tools. required: Require the model to call a tool. AllowedToolChoice: properties: type: type: string enum: - allowed_tools default: allowed_tools tools: items: oneOf: - $ref: '#/components/schemas/FunctionToolChoice' type: array mode: $ref: '#/components/schemas/ToolChoiceValueEnum' type: object required: - type - tools - mode Usage: properties: input_tokens: type: integer description: The number of input tokens that were used to generate the response. output_tokens: type: integer description: The number of output tokens that were generated by the model. total_tokens: type: integer description: The total number of tokens that were used. input_tokens_details: $ref: '#/components/schemas/InputTokensDetails' output_tokens_details: $ref: '#/components/schemas/OutputTokensDetails' type: object required: - input_tokens - output_tokens - total_tokens - input_tokens_details - output_tokens_details title: Usage description: Token usage statistics that were recorded for the response. ResponseCreatedStreamingEvent: properties: type: type: string enum: - response.created description: The type of the event, always `response.created`. default: response.created sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response created event description: A streaming event that indicated the response was created. ResponseQueuedStreamingEvent: properties: type: type: string enum: - response.queued description: The type of the event, always `response.queued`. default: response.queued sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response queued event description: A streaming event that indicated the response was queued. ResponseInProgressStreamingEvent: properties: type: type: string enum: - response.in_progress description: The type of the event, always `response.in_progress`. default: response.in_progress sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response in progress event description: A streaming event that indicated the response was in progress. ResponseCompletedStreamingEvent: properties: type: type: string enum: - response.completed description: The type of the event, always `response.completed`. default: response.completed sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response completed event description: A streaming event that indicated the response was completed. ResponseFailedStreamingEvent: properties: type: type: string enum: - response.failed description: The type of the event, always `response.failed`. default: response.failed sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response failed event description: A streaming event that indicated the response had failed. ResponseIncompleteStreamingEvent: properties: type: type: string enum: - response.incomplete description: The type of the event, always `response.incomplete`. default: response.incomplete sequence_number: type: integer description: The sequence number of the event that was emitted. response: $ref: '#/components/schemas/ResponseResource' type: object required: - type - sequence_number - response title: Response incomplete event description: A streaming event that indicated the response was incomplete. ResponseOutputItemAddedStreamingEvent: properties: type: type: string enum: - response.output_item.added description: The type of the event, always `response.output_item.added`. default: response.output_item.added sequence_number: type: integer description: The sequence number of the event that was emitted. output_index: type: integer description: The index of the output item that was added. item: $ref: '#/components/schemas/ItemField' type: object required: - type - sequence_number - output_index - item title: Response output item added event description: >- A streaming event that indicated an output item was added to the response. ResponseOutputItemDoneStreamingEvent: properties: type: type: string enum: - response.output_item.done description: The type of the event, always `response.output_item.done`. default: response.output_item.done sequence_number: type: integer description: The sequence number of the event that was emitted. output_index: type: integer description: The index of the output item that was completed. item: $ref: '#/components/schemas/ItemField' type: object required: - type - sequence_number - output_index - item title: Response output item done event description: A streaming event that indicated an output item was completed. ResponseReasoningSummaryPartAddedStreamingEvent: properties: type: type: string enum: - response.reasoning_summary_part.added description: >- The type of the event, always `response.reasoning_summary_part.added`. default: response.reasoning_summary_part.added sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. summary_index: type: integer description: The index of the summary part that was added. part: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: object required: - type - sequence_number - item_id - output_index - summary_index - part title: Response reasoning summary part added event description: A streaming event that indicated a reasoning summary part was added. ResponseReasoningSummaryPartDoneStreamingEvent: properties: type: type: string enum: - response.reasoning_summary_part.done description: >- The type of the event, always `response.reasoning_summary_part.done`. default: response.reasoning_summary_part.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. summary_index: type: integer description: The index of the summary part that was completed. part: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: object required: - type - sequence_number - item_id - output_index - summary_index - part title: Response reasoning summary part done event description: A streaming event that indicated a reasoning summary part was completed. ResponseContentPartAddedStreamingEvent: properties: type: type: string enum: - response.content_part.added description: The type of the event, always `response.content_part.added`. default: response.content_part.added sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the content part that was added. part: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: object required: - type - sequence_number - item_id - output_index - content_index - part title: Response content part added event description: A streaming event that indicated a content part was added. ResponseContentPartDoneStreamingEvent: properties: type: type: string enum: - response.content_part.done description: The type of the event, always `response.content_part.done`. default: response.content_part.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the content part that was completed. part: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: object required: - type - sequence_number - item_id - output_index - content_index - part title: Response content part done event description: A streaming event that indicated a content part was completed. ResponseOutputTextDeltaStreamingEvent: properties: type: type: string enum: - response.output_text.delta description: The type of the event, always `response.output_text.delta`. default: response.output_text.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the content part that was updated. delta: type: string description: The text delta that was appended. logprobs: items: $ref: '#/components/schemas/LogProb' type: array description: >- The token log probabilities that were emitted with the delta, if any. obfuscation: type: string description: An obfuscation string that was added to pad the event payload. type: object required: - type - sequence_number - item_id - output_index - content_index - delta title: Response output text delta event description: A streaming event that indicated output text was incrementally added. ResponseOutputTextDoneStreamingEvent: properties: type: type: string enum: - response.output_text.done description: The type of the event, always `response.output_text.done`. default: response.output_text.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the content part that was completed. text: type: string description: The final text that was emitted. logprobs: items: $ref: '#/components/schemas/LogProb' type: array description: >- The token log probabilities that were emitted with the final text, if any. type: object required: - type - sequence_number - item_id - output_index - content_index - text title: Response output text done event description: A streaming event that indicated output text was completed. ResponseRefusalDeltaStreamingEvent: properties: type: type: string enum: - response.refusal.delta description: The type of the event, always `response.refusal.delta`. default: response.refusal.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the refusal content that was updated. delta: type: string description: The refusal text delta that was appended. type: object required: - type - sequence_number - item_id - output_index - content_index - delta title: Response refusal delta event description: A streaming event that indicated refusal text was incrementally added. ResponseRefusalDoneStreamingEvent: properties: type: type: string enum: - response.refusal.done description: The type of the event, always `response.refusal.done`. default: response.refusal.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the refusal content that was completed. refusal: type: string description: The final refusal text that was emitted. type: object required: - type - sequence_number - item_id - output_index - content_index - refusal title: Response refusal done event description: A streaming event that indicated refusal text was completed. ResponseReasoningDeltaStreamingEvent: properties: type: type: string enum: - response.reasoning.delta description: The type of the event, always `response.reasoning.delta`. default: response.reasoning.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the reasoning content that was updated. delta: type: string description: The reasoning text delta that was appended. obfuscation: type: string description: An obfuscation string that was added to pad the event payload. type: object required: - type - sequence_number - item_id - output_index - content_index - delta title: Response reasoning delta event description: A streaming event that indicated reasoning text was incrementally added. ResponseReasoningDoneStreamingEvent: properties: type: type: string enum: - response.reasoning.done description: The type of the event, always `response.reasoning.done`. default: response.reasoning.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the reasoning content that was completed. text: type: string description: The final reasoning text that was emitted. type: object required: - type - sequence_number - item_id - output_index - content_index - text title: Response reasoning done event description: A streaming event that indicated reasoning text was completed. ResponseReasoningSummaryDeltaStreamingEvent: properties: type: type: string enum: - response.reasoning_summary_text.delta description: The type of the event, always `response.reasoning_summary.delta`. default: response.reasoning_summary_text.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. summary_index: type: integer description: The index of the summary content that was updated. delta: type: string description: The summary text delta that was appended. obfuscation: type: string description: An obfuscation string that was added to pad the event payload. type: object required: - type - sequence_number - item_id - output_index - summary_index - delta title: Response reasoning summary delta event description: >- A streaming event that indicated a reasoning summary was incrementally added. ResponseReasoningSummaryDoneStreamingEvent: properties: type: type: string enum: - response.reasoning_summary_text.done description: The type of the event, always `response.reasoning_summary.done`. default: response.reasoning_summary_text.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. summary_index: type: integer description: The index of the summary content that was completed. text: type: string description: The final summary text that was emitted. type: object required: - type - sequence_number - item_id - output_index - summary_index - text title: Response reasoning summary done event description: A streaming event that indicated a reasoning summary was completed. ResponseOutputTextAnnotationAddedStreamingEvent: properties: type: type: string enum: - response.output_text.annotation.added description: >- The type of the event, always `response.output_text.annotation.added`. default: response.output_text.annotation.added sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the item that was updated. output_index: type: integer description: The index of the output item that was updated. content_index: type: integer description: The index of the output text content that was updated. annotation_index: type: integer description: The index of the annotation that was added. annotation: $ref: '#/components/schemas/Annotation' type: object required: - type - sequence_number - item_id - output_index - content_index - annotation_index - annotation title: Response output text annotation added event description: A streaming event that indicated an output text annotation was added. ResponseFunctionCallArgumentsDeltaStreamingEvent: properties: type: type: string enum: - response.function_call_arguments.delta description: >- The type of the event, always `response.function_call_arguments.delta`. default: response.function_call_arguments.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the tool call item that was updated. output_index: type: integer description: The index of the output item that was updated. delta: type: string description: The arguments delta that was appended. obfuscation: type: string description: An obfuscation string that was added to pad the event payload. type: object required: - type - sequence_number - item_id - output_index - delta title: Response function call arguments delta event description: >- A streaming event that indicated function call arguments were incrementally added. ResponseFunctionCallArgumentsDoneStreamingEvent: properties: type: type: string enum: - response.function_call_arguments.done description: >- The type of the event, always `response.function_call_arguments.done`. default: response.function_call_arguments.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the tool call item that was updated. output_index: type: integer description: The index of the output item that was updated. arguments: type: string description: The final arguments string that was emitted. type: object required: - type - sequence_number - item_id - output_index - arguments title: Response function call arguments done event description: A streaming event that indicated function call arguments were completed. ResponseCustomToolCallInputDeltaStreamingEvent: properties: type: type: string enum: - response.custom_tool_call_input.delta description: >- The type of the event, always `response.custom_tool_call_input.delta`. default: response.custom_tool_call_input.delta sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the custom tool call item that was updated. output_index: type: integer description: The index of the output item that was updated. delta: type: string description: The input delta that was appended. type: object required: - type - sequence_number - item_id - output_index - delta title: Response custom tool call input delta event description: >- A streaming event that indicated custom tool call input was incrementally added. ResponseCustomToolCallInputDoneStreamingEvent: properties: type: type: string enum: - response.custom_tool_call_input.done description: >- The type of the event, always `response.custom_tool_call_input.done`. default: response.custom_tool_call_input.done sequence_number: type: integer description: The sequence number of the event that was emitted. item_id: type: string description: The ID of the custom tool call item that was updated. output_index: type: integer description: The index of the output item that was updated. input: type: string description: The final input string that was emitted. type: object required: - type - sequence_number - item_id - output_index - input title: Response custom tool call input done event description: A streaming event that indicated custom tool call input was completed. ErrorStreamingEvent: properties: type: type: string enum: - error description: The type of the event, always `error`. default: error sequence_number: type: integer description: The sequence number of the event that was emitted. error: $ref: '#/components/schemas/ErrorPayload' type: object required: - type - sequence_number - error title: Error event description: A streaming event that indicated an error was emitted. ErrorPayload: properties: type: type: string description: The error type that was emitted. code: nullable: true type: string description: The error code that was emitted, if any. message: type: string description: The human-readable error message that was emitted. param: nullable: true type: string description: The parameter name that was associated with the error, if any. headers: additionalProperties: type: string description: The header value that was emitted. type: object description: The response headers that were emitted with the error, if any. type: object required: - type - code - message - param title: Error payload description: An error payload that was emitted for a streaming error event. AdditionalToolsItemParam: properties: type: type: string enum: - additional_tools description: The item type. Always `additional_tools`. default: additional_tools role: type: string description: The role codex attributes the tool prefix to (always `developer`). tools: items: $ref: '#/components/schemas/ResponsesToolParam' type: array description: The tools to merge after the top-level tools param. type: object required: - type - tools title: Additional tools item description: >- A Codex-compatible input item that supplies additional tools for the request. ReasoningItemParam: properties: id: nullable: true type: string description: The unique ID of this reasoning item. example: rs_123 type: type: string enum: - reasoning description: The item type. Always `reasoning`. default: reasoning summary: items: $ref: '#/components/schemas/ReasoningSummaryContentParam' type: array description: Reasoning summary content associated with this item. content: nullable: true encrypted_content: nullable: true type: string description: An encrypted representation of the reasoning content. type: object required: - type - summary UserMessageItemParam: properties: id: nullable: true type: string description: The unique ID of this message item. example: msg_123 type: type: string enum: - message description: The item type. Always `message`. default: message role: type: string enum: - user description: The message role. Always `user`. default: user content: oneOf: - items: oneOf: - $ref: '#/components/schemas/InputTextContentParam' - $ref: '#/components/schemas/InputImageContentParamAutoParam' description: A piece of message content, such as text, an image, or a file. discriminator: propertyName: type type: array - type: string maxLength: 10485760 description: The message content, as a single string. description: The message content, as an array of content parts. status: nullable: true type: string description: The status of the message item. type: object required: - type - role - content SystemMessageItemParam: properties: id: nullable: true type: string description: The unique ID of this message item. example: msg_123 type: type: string enum: - message description: The item type. Always `message`. default: message role: type: string enum: - system description: The message role. Always `system`. default: system content: oneOf: - items: oneOf: - $ref: '#/components/schemas/InputTextContentParam' discriminator: propertyName: type type: array - type: string maxLength: 10485760 description: The message content, as a single string. description: The message content, as an array of content parts. status: nullable: true type: string description: The status of the message item. type: object required: - type - role - content DeveloperMessageItemParam: properties: id: nullable: true type: string description: The unique ID of this message item. example: msg_123 type: type: string enum: - message description: The item type. Always `message`. default: message role: type: string enum: - developer description: The message role. Always `developer`. default: developer content: oneOf: - items: oneOf: - $ref: '#/components/schemas/InputTextContentParam' discriminator: propertyName: type type: array - type: string maxLength: 10485760 description: The message content, as a single string. description: The message content, as an array of content parts. status: nullable: true type: string description: The status of the message item. type: object required: - type - role - content AssistantMessageItemParam: properties: id: nullable: true type: string description: The unique ID of this message item. example: msg_123 type: type: string enum: - message description: The item type. Always `message`. default: message role: type: string enum: - assistant description: The role of the message author. Always `assistant`. default: assistant content: oneOf: - items: oneOf: - $ref: '#/components/schemas/OutputTextContentParam' - $ref: '#/components/schemas/RefusalContentParam' description: >- A piece of assistant message content, such as text or a refusal. discriminator: propertyName: type type: array - type: string maxLength: 10485760 description: The message content, as a single string. description: The message content, as an array of content parts. phase: type: string enum: - commentary - final_answer description: >- Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages. Omitting it can degrade performance. Not used for user messages. x-openresponses-added-in: '2026-04-24' status: nullable: true type: string description: The status of the message item. type: object required: - type - role - content FunctionCallItemParam: properties: id: nullable: true type: string description: The unique ID of this function tool call. example: fc_123 call_id: type: string maxLength: 64 minLength: 1 description: The unique ID of the function tool call generated by the model. type: type: string enum: - function_call description: The item type. Always `function_call`. default: function_call name: type: string maxLength: 64 minLength: 1 pattern: ^[a-zA-Z0-9_-]+$ description: The name of the function to call. arguments: type: string description: The function arguments as a JSON string. namespace: type: string description: The namespace associated with the function tool, if any. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - call_id - type - name - arguments FunctionCallOutputItemParam: properties: id: nullable: true type: string description: >- The unique ID of the function tool call output. Populated when this item is returned via API. example: fc_123 call_id: type: string maxLength: 64 minLength: 1 description: The unique ID of the function tool call generated by the model. type: type: string enum: - function_call_output description: >- The type of the function tool call output. Always `function_call_output`. default: function_call_output output: oneOf: - type: string maxLength: 10485760 description: A JSON string of the output of the function tool call. - items: oneOf: - $ref: '#/components/schemas/InputTextContentParam' - $ref: '#/components/schemas/InputImageContentParamAutoParam' description: A piece of message content, such as text, an image, or a file. discriminator: propertyName: type type: array description: >- An array of content outputs (text, image, file) for the function tool call. description: Text, image, or file output of the function tool call. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - call_id - type - output title: Function tool call output description: The output of a function tool call. CustomToolCallItemParam: properties: id: nullable: true type: string description: The unique ID of this custom tool call. example: ctc_123 call_id: type: string maxLength: 64 minLength: 1 description: The unique ID of the custom tool call generated by the model. type: type: string enum: - custom_tool_call description: The item type. Always `custom_tool_call`. default: custom_tool_call name: type: string maxLength: 64 minLength: 1 pattern: ^[a-zA-Z0-9_-]+$ description: The name of the custom tool to call. input: type: string description: The raw freeform tool input string, forwarded verbatim. namespace: type: string description: The namespace associated with the custom tool, if any. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - call_id - type - name - input title: Custom tool call description: A custom (freeform) tool call replayed from a prior response. CustomToolCallOutputItemParam: properties: id: nullable: true type: string description: The unique ID of the custom tool call output. example: ctco_123 call_id: type: string maxLength: 64 minLength: 1 description: The unique ID of the custom tool call generated by the model. type: type: string enum: - custom_tool_call_output description: The item type. Always `custom_tool_call_output`. default: custom_tool_call_output output: oneOf: - type: string maxLength: 10485760 description: A string output of the custom tool call. - items: oneOf: - $ref: '#/components/schemas/InputTextContentParam' - $ref: '#/components/schemas/InputImageContentParamAutoParam' description: A piece of message content, such as text or an image. discriminator: propertyName: type type: array description: >- An array of content outputs (text, image) for the custom tool call. description: Text or image output of the custom tool call. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - call_id - type - output title: Custom tool call output description: The output of a custom tool call. FunctionToolParam: properties: name: type: string maxLength: 64 minLength: 1 pattern: ^[a-zA-Z0-9_-]+$ description: type: string parameters: type: object additionalProperties: true nullable: true description: >- JSON Schema for the function parameters, kept as raw JSON and forwarded verbatim. strict: type: boolean type: type: string enum: - function default: function type: object required: - name - type - description CustomToolParam: properties: name: type: string maxLength: 64 minLength: 1 pattern: ^[a-zA-Z0-9_-]+$ description: nullable: true type: string format: type: object additionalProperties: true nullable: true description: >- The freeform input format constraint ({"type":"text"} or {"type":"grammar","syntax":...,"definition":...}), kept as raw JSON and forwarded verbatim. type: type: string enum: - custom default: custom type: object required: - name - type title: Custom tool description: >- A freeform custom tool whose input is a raw string, optionally constrained by a grammar. NamespaceToolParam: properties: name: type: string maxLength: 64 minLength: 1 description: nullable: true type: string tools: items: $ref: '#/components/schemas/FunctionToolParam' type: array description: The function tools grouped under this namespace. type: type: string enum: - namespace default: namespace type: object required: - name - tools - type title: Namespace tool description: A namespace that groups related function tools. SpecificToolChoiceParam: oneOf: - $ref: '#/components/schemas/SpecificFunctionParam' TextFormatParam: oneOf: - $ref: '#/components/schemas/TextResponseFormat' - $ref: '#/components/schemas/JsonSchemaResponseFormatParam' VerbosityEnum: type: string enum: - low - medium - high x-enumDescriptions: high: Instruct the model to emit more verbose final responses. low: Instruct the model to emit less verbose final responses. medium: Use the model's default verbosity setting. ReasoningEffortEnum: type: string enum: - none - low - medium - high - xhigh x-enumDescriptions: high: Use a higher reasoning effort to improve answer quality. medium: Use a balanced reasoning effort. low: Use a lower reasoning effort for faster responses. minimal: Use the lowest non-zero reasoning effort. none: >- Restrict the model from performing any reasoning before emitting a final answer. xhigh: Use the maximum reasoning effort available. ReasoningSummaryEnum: type: string enum: - concise - detailed - auto x-enumDescriptions: auto: Allow the model to decide when to summarize. concise: Emit concise summaries of reasoning content. detailed: Emit details summaries of reasoning content. Message: properties: type: type: string enum: - message description: The type of the message. Always set to `message`. default: message id: type: string description: The unique ID of the message. status: $ref: '#/components/schemas/MessageStatus' role: $ref: '#/components/schemas/MessageRole' content: items: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' - $ref: '#/components/schemas/InputVideoContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: array description: The content of the message phase: type: string enum: - commentary - final_answer description: >- 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. Omitting it can degrade performance. Not used for user messages. x-openresponses-added-in: '2026-04-24' type: object required: - type - id - status - role - content title: Message description: A message to or from the model. FunctionCall: properties: type: type: string enum: - function_call description: The type of the item. Always `function_call`. default: function_call id: type: string description: The unique ID of the function call item. call_id: type: string description: The unique ID of the function tool call that was generated. name: type: string description: The name of the function that was called. arguments: type: string description: The arguments JSON string that was generated. namespace: type: string description: The namespace associated with the function tool, if any. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - type - id - call_id - name - arguments - status title: Function call description: A function tool call that was generated by the model. FunctionCallOutput: properties: type: type: string enum: - function_call_output description: >- The type of the function tool call output. Always `function_call_output`. default: function_call_output id: type: string description: >- The unique ID of the function tool call output. Populated when this item is returned via API. call_id: type: string description: The unique ID of the function tool call generated by the model. output: oneOf: - type: string description: A JSON string of the output of the function tool call. - items: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: array description: >- An array of output contents (images, files, text) for the function tool call. status: $ref: '#/components/schemas/FunctionCallOutputStatusEnum' type: object required: - type - id - call_id - output - status title: Function call output description: A function tool call output that was returned by the tool. CustomToolCall: properties: type: type: string enum: - custom_tool_call description: The type of the item. Always `custom_tool_call`. default: custom_tool_call id: type: string description: The unique ID of the custom tool call item. call_id: type: string description: The unique ID of the custom tool call that was generated. name: type: string description: The name of the custom tool that was called. input: type: string description: >- The raw freeform input string that was generated, never forced through JSON. namespace: type: string description: The namespace associated with the custom tool, if any. status: $ref: '#/components/schemas/FunctionCallStatus' type: object required: - type - id - call_id - name - input - status title: Custom tool call description: A custom (freeform) tool call that was generated by the model. ReasoningBody: properties: type: type: string enum: - reasoning description: The type of the item. Always `reasoning`. default: reasoning id: type: string description: The unique ID of the reasoning item. content: items: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: array description: The reasoning content that was generated. summary: items: oneOf: - $ref: '#/components/schemas/InputTextContent' - $ref: '#/components/schemas/OutputTextContent' - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/SummaryTextContent' - $ref: '#/components/schemas/ReasoningTextContent' - $ref: '#/components/schemas/RefusalContent' - $ref: '#/components/schemas/InputImageContent' - $ref: '#/components/schemas/InputFileContent' description: A content part that makes up an input or output item. discriminator: propertyName: type type: array description: The reasoning summary content that was generated. encrypted_content: type: string description: The encrypted reasoning content that was generated. status: $ref: '#/components/schemas/MessageStatus' type: object required: - type - id - summary title: Reasoning item description: A reasoning item that was generated by the model. FunctionTool: properties: type: type: string enum: - function description: The type of the function tool. Always `function`. default: function name: type: string description: The name of the function to call. description: nullable: true type: string description: >- A description of the function. Used by the model to determine whether or not to call the function. parameters: nullable: true additionalProperties: {} type: object description: A JSON schema object describing the parameters of the function. strict: nullable: true type: boolean description: Whether to enforce strict parameter validation. Default `true`. type: object required: - type - name - description - parameters - strict title: Function description: >- Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). InputTokensDetails: properties: cached_tokens: type: integer description: The number of input tokens that were served from cache. cache_write_tokens: type: integer description: >- The number of input tokens written to the prompt cache. Present only when cache writes occur. type: object required: - cached_tokens title: Input tokens details description: A breakdown of input token usage that was recorded. OutputTokensDetails: properties: reasoning_tokens: type: integer description: The number of output tokens that were attributed to reasoning. type: object required: - reasoning_tokens title: Output tokens details description: A breakdown of output token usage that was recorded. InputTextContent: properties: type: type: string enum: - input_text description: The type of the input item. Always `input_text`. default: input_text text: type: string description: The text input to the model. type: object required: - type - text title: Input text description: A text input to the model. OutputTextContent: properties: type: type: string enum: - output_text description: The type of the output text. Always `output_text`. default: output_text text: type: string description: The text output from the model. annotations: items: $ref: '#/components/schemas/Annotation' type: array description: The annotations of the text output. logprobs: items: $ref: '#/components/schemas/LogProb' type: array type: object required: - type - text - annotations title: Output text description: A text output from the model. TextContent: properties: type: type: string enum: - text default: text text: type: string type: object required: - type - text title: Text Content description: A text content. SummaryTextContent: properties: type: type: string enum: - summary_text description: The type of the object. Always `summary_text`. default: summary_text text: type: string description: A summary of the reasoning output from the model so far. type: object required: - type - text title: Summary text description: A summary text from the model. ReasoningTextContent: properties: type: type: string enum: - reasoning_text description: The type of the reasoning text. Always `reasoning_text`. default: reasoning_text text: type: string description: The reasoning text from the model. type: object required: - type - text title: Reasoning text description: Reasoning text from the model. RefusalContent: properties: type: type: string enum: - refusal description: The type of the refusal. Always `refusal`. default: refusal refusal: type: string description: The refusal explanation from the model. type: object required: - type - refusal title: Refusal description: A refusal from the model. InputImageContent: properties: type: type: string enum: - input_image description: The type of the input item. Always `input_image`. default: input_image image_url: nullable: true type: string description: >- The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. detail: $ref: '#/components/schemas/ImageDetail' type: object required: - type - image_url - detail title: Input image description: >- An image input to the model. Learn about [image inputs](/docs/guides/vision). InputFileContent: properties: type: type: string enum: - input_file description: The type of the input item. Always `input_file`. default: input_file filename: type: string description: The name of the file to be sent to the model. file_url: type: string description: The URL of the file to be sent to the model. type: object required: - type title: Input file description: A file input to the model. LogProb: properties: token: type: string logprob: type: number bytes: items: type: integer type: array top_logprobs: items: $ref: '#/components/schemas/TopLogProb' type: array type: object required: - token - logprob - bytes - top_logprobs title: Log probability description: The log probability of a token. Annotation: oneOf: - $ref: '#/components/schemas/UrlCitationBody' description: An annotation that applies to a span of output text. discriminator: propertyName: type ReasoningSummaryContentParam: properties: type: type: string enum: - summary_text description: The content type. Always `summary_text`. default: summary_text text: type: string maxLength: 10485760 description: The reasoning summary text. type: object required: - type - text InputTextContentParam: properties: type: type: string enum: - input_text description: The type of the input item. Always `input_text`. default: input_text text: type: string maxLength: 10485760 description: The text input to the model. type: object required: - type - text title: Input text description: A text input to the model. x-unionDisplay: section x-unionTitle: Content Type InputImageContentParamAutoParam: properties: type: type: string enum: - input_image description: The type of the input item. Always `input_image`. default: input_image image_url: nullable: true type: string maxLength: 20971520 description: >- The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. detail: $ref: '#/components/schemas/ImageDetail' type: object required: - type title: Input image description: >- An image input to the model. Learn about [image inputs](/docs/guides/vision) OutputTextContentParam: properties: type: type: string enum: - output_text description: The content type. Always `output_text`. default: output_text text: type: string maxLength: 10485760 description: The text content. annotations: oneOf: - items: $ref: '#/components/schemas/UrlCitationParam' type: array description: Citations associated with the text content. type: object required: - type - text RefusalContentParam: properties: type: type: string enum: - refusal description: The content type. Always `refusal`. default: refusal refusal: type: string maxLength: 10485760 description: The refusal text. type: object required: - type - refusal FunctionCallStatus: type: string enum: - in_progress - completed - incomplete x-enumDescriptions: completed: Model has finished sampling this item. in_progress: Model is currently sampling this item. incomplete: >- Model was interrupted from sampling this item partway through. This can occur, for example, if the model encounters a stop token or exhausts its output_token budget. SpecificFunctionParam: properties: type: type: string enum: - function description: The tool to call. Always `function`. default: function name: type: string description: The name of the function tool to call. type: object required: - type - name TextResponseFormat: properties: type: type: string enum: - text default: text type: object required: - type JsonSchemaResponseFormatParam: type: object properties: type: type: string description: The type of response format being defined. Always `json_schema`. enum: - json_schema description: type: string description: >- A description of what the response format is for, used by the model to determine how to respond in the format. name: type: string description: |- 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: type: object title: JSON schema description: >- The schema for the response format, described as a JSON Schema object. additionalProperties: true strict: nullable: true type: boolean default: true description: >- 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`. enum: - true required: - type - name - schema MessageStatus: type: string enum: - in_progress - completed - incomplete x-enumDescriptions: completed: Model has finished sampling this item. in_progress: Model is currently sampling this item. incomplete: >- Model was interrupted from sampling this item partway through. This can occur, for example, if the model encounters a stop token or exhausts its output_token budget. MessageRole: type: string enum: - user - assistant - system - developer x-enumDescriptions: assistant: Model-generated content in the conversation. developer: Developer-supplied guidance that shapes the assistant’s behavior. system: System-level instructions that set global behavior. user: End‑user input in the conversation. InputVideoContent: type: object description: A content block representing a video input to the model. properties: type: type: string enum: - input_video description: The type of the input content. Always `input_video`. video_url: type: string description: A base64 or remote url that resolves to a video file. required: - type - video_url FunctionCallOutputStatusEnum: type: string enum: - in_progress - completed - incomplete description: >- Similar to `FunctionCallStatus`. All three options are allowed here for compatibility, but because in practice these items will be provided by developers, only `completed` should be used. ImageDetail: type: string enum: - low - high - auto x-enumDescriptions: auto: Choose the detail level automatically. high: >- Allows the model to "see" a higher-resolution version of the image, usually increasing input token costs. low: Restricts the model to a lower-resolution version of the image. TopLogProb: properties: token: type: string logprob: type: number bytes: items: type: integer type: array type: object required: - token - logprob - bytes title: Top log probability description: The top log probability of a token. UrlCitationBody: properties: type: type: string enum: - url_citation description: The type of the URL citation. Always `url_citation`. default: url_citation url: type: string description: The URL of the web resource. start_index: type: integer description: The index of the first character of the URL citation in the message. end_index: type: integer description: The index of the last character of the URL citation in the message. title: type: string description: The title of the web resource. type: object required: - type - url - start_index - end_index - title title: URL citation description: A citation for a web resource used to generate a model response. UrlCitationParam: properties: type: type: string enum: - url_citation description: The citation type. Always `url_citation`. default: url_citation start_index: type: integer minimum: 0 description: The index of the first character of the citation in the message. end_index: type: integer minimum: 0 description: The index of the last character of the citation in the message. url: type: string description: The URL of the cited resource. title: type: string description: The title of the cited resource. type: object required: - type - start_index - end_index - url - title securitySchemes: HTTPBearer: type: http scheme: bearer description: Your Perplexity API key. ````