> ## Documentation Index > Fetch the complete documentation index at: https://docs.parallel.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Response > Create a response. Generates an answer to the given input, grounded in live web research and annotated with URL citations. Set `model` to `parallel`; `reasoning.effort` (`low`/`medium`/`high`) controls how much research is performed, trading response time for answer quality. Returns an OpenAI-format `Response` as `application/json`, or a `text/event-stream` of OpenAI Responses SSE events when `stream=true`. ## OpenAPI ````yaml /public-openapi.json post /v1/responses openapi: 3.1.0 info: title: Parallel API description: Parallel API contact: name: Parallel Support url: https://parallel.ai email: support@parallel.ai version: 0.1.2 servers: - url: https://api.parallel.ai description: Parallel API security: - ApiKeyAuth: [] tags: - name: Search description: >- Search returns ranked URLs with extended excerpts suitable for LLM consumption. Inputs are a natural-language objective and optional keyword queries. Source policies allow including or excluding specific domains and have configurable output sizes. The returned extended snippets contain dense, relevant information from relevant pages. - Result: ranked list with URL, title, and long text excerpts - name: Extract description: >- Extract returns excerpts or full content from one or more URLs. Inputs are a list of URLs and an optional search objective and keyword queries. The returned excerpts or full content is formatted as markdown and suitable for LLM consumption. - Result: excerpts or full content from the URL formatted as markdown - name: Tasks description: >- The Task API executes web research and extraction tasks. Clients submit a natural-language objective with an optional input schema; the service plans retrieval, fetches relevant URLs, and returns outputs that conform to a provided or inferred JSON schema. Supports deep research style queries and can return rich structured JSON outputs. Processors trade-off between cost, latency, and quality. Each processor supports calibrated confidences. - Output metadata: citations, excerpts, reasoning, and confidence per field Task Groups enable batch execution of many independent Task runs with group-level monitoring and failure handling. - Submit hundreds or thousands of Tasks as a single group - Observe group progress and receive results as they complete - Real-time updates via Server-Sent Events (SSE) - Add tasks to an existing group while it is running - Group-level retry and error aggregation - name: FindAll description: >- The FindAll API discovers and evaluates entities that match complex criteria from natural language objectives. Submit a high-level goal and the service automatically generates structured match conditions, discovers relevant candidates, and evaluates each against the criteria. Returns comprehensive results with detailed reasoning, citations, and confidence scores for each match decision. Streaming events and webhooks are supported. - name: Monitor description: >- The Monitor API watches the web for material changes on a fixed frequency. Each monitor runs once on creation and then on its configured schedule, emitting events when meaningful changes are detected. - `event_stream` monitors track a search query and emit an event for each new material change. - `snapshot` monitors track a specific task run's output and emit an event when the output changes. Results can be polled via the events endpoint or delivered via webhooks. - name: Chat API (Beta) description: >- The Chat API provides a programmatic chat-style text generation interface. It accepts a sequence of messages and returns model responses. Intended for assistant-like interactions and evaluation. Streaming responses are supported. - name: Responses API description: >- An OpenAI-Responses-compatible interface for answers grounded in live web research, with URL citations. Point any Responses-API client — the OpenAI Python SDK, OpenAI TypeScript SDK, the Agents SDK, or raw HTTP — at `https://api.parallel.ai` with your Parallel API key, set `model` to `parallel`, and call `/v1/responses`. - `input` accepts a plain string or an array of role/content messages (canonical OpenAI shape; text content only). - `reasoning.effort` (`low`/`medium`/`high`) controls how much research is performed, trading response time for answer quality. - Multi-turn via `previous_response_id`. - Structured outputs via `text.format = {"type": "json_schema", "name": ..., "schema": {...}}`. - Streaming (`stream=true`) emits the standard OpenAI Responses SSE lifecycle: `response.created` and `response.in_progress`, then output item / content part / text delta events with URL-citation annotations, the matching `*.done` events, and a terminal `response.completed` — or `response.failed` if the request fails mid-stream. paths: /v1/responses: post: tags: - Responses API summary: Create Response description: >- Create a response. Generates an answer to the given input, grounded in live web research and annotated with URL citations. Set `model` to `parallel`; `reasoning.effort` (`low`/`medium`/`high`) controls how much research is performed, trading response time for answer quality. Returns an OpenAI-format `Response` as `application/json`, or a `text/event-stream` of OpenAI Responses SSE events when `stream=true`. operationId: create_response_v1_responses_post requestBody: content: application/json: schema: $ref: '#/components/schemas/ResponseCreateRequest' required: true responses: '200': description: >- Returns a Response object for non-streaming requests (application/json), or a stream of OpenAI Responses streaming events (text/event-stream) when `stream=true` is set in the request. content: application/json: schema: $ref: '#/components/schemas/Response' text/event-stream: schema: $ref: '#/components/schemas/ResponseStreamEvent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ResponseCreateRequest: properties: model: type: string title: Model description: >- The model to run. `parallel` is the only supported value (matched case-insensitively); any other value is rejected. To trade response time for answer quality, set `reasoning.effort` (low/medium/high) rather than changing the model name. examples: - parallel input: anyOf: - type: string - items: $ref: '#/components/schemas/ResponseInputMessage' type: array title: Input description: >- The input to generate a response for: a plain string, or a list of role/content messages that includes at least one `user` message. Must be non-empty, and only text content is supported. `input` and `instructions` together may total at most 20,000 characters. examples: - What are the latest developments in fusion energy? instructions: anyOf: - type: string - type: 'null' title: Instructions description: System instructions for the model. previous_response_id: anyOf: - type: string - type: 'null' title: Previous Response Id description: ID of a previous response to use as conversation context. stream: anyOf: - type: boolean - type: 'null' title: Stream description: Whether to stream the response. text: anyOf: - $ref: '#/components/schemas/ResponseTextConfig' - type: 'null' description: Configuration for text output, including structured output. metadata: anyOf: - additionalProperties: type: string type: object maxProperties: 16 - type: 'null' title: Metadata description: >- Arbitrary key-value pairs, echoed back on the Response object. Useful for tagging requests. At most 16 keys; keys up to 64 characters, values up to 512 characters. reasoning: anyOf: - $ref: '#/components/schemas/ResponseReasoningConfig' - type: 'null' description: >- Reasoning configuration. `effort` (low/medium/high) controls how much research is performed; defaults to `medium`. background: anyOf: - type: boolean - type: 'null' title: Background description: >- Background mode is not supported: requests with `background=true` are rejected with a 422 validation error. Use the Task API (POST /v1/tasks/runs) for long-running work. type: object required: - model - input title: ResponseCreateRequest description: >- Request body for the Responses API (`POST /v1/responses`). OpenAI-Responses-compatible: point a standard OpenAI client at `https://api.parallel.ai/v1` with your Parallel API key and set `model` to `parallel`. The fields below are the ones Parallel acts on; other OpenAI request fields (`tools`, `tool_choice`, `temperature`, `top_p`, `max_output_tokens`, `parallel_tool_calls`, `truncation`, `store`, `user`, `include`) are accepted for compatibility but have no effect. Response: additionalProperties: true description: |- A response from the `parallel` model. A completed response contains a single assistant message whose text is annotated with URL citations grounding the answer. properties: id: title: Id type: string created_at: title: Created At type: number error: anyOf: - $ref: '#/components/schemas/ResponseError' - type: 'null' default: null incomplete_details: anyOf: - $ref: '#/components/schemas/IncompleteDetails' - type: 'null' default: null instructions: anyOf: - type: string - type: 'null' default: null title: Instructions metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' default: null title: Metadata model: const: parallel default: parallel title: Model type: string object: const: response title: Object type: string output: items: $ref: '#/components/schemas/ResponseOutputMessage' title: Output type: array parallel_tool_calls: title: Parallel Tool Calls type: boolean temperature: anyOf: - type: number - type: 'null' default: null title: Temperature tool_choice: default: auto title: Tool Choice type: string tools: default: [] items: {} title: Tools type: array top_p: anyOf: - type: number - type: 'null' default: null title: Top P background: anyOf: - type: boolean - type: 'null' default: null title: Background completed_at: anyOf: - type: number - type: 'null' default: null title: Completed At conversation: default: null title: Conversation type: 'null' max_output_tokens: anyOf: - type: integer - type: 'null' default: null title: Max Output Tokens max_tool_calls: anyOf: - type: integer - type: 'null' default: null title: Max Tool Calls moderation: anyOf: - $ref: '#/components/schemas/Moderation' - type: 'null' default: null previous_response_id: anyOf: - type: string - type: 'null' default: null title: Previous Response Id prompt: default: null title: Prompt type: 'null' prompt_cache_key: anyOf: - type: string - type: 'null' default: null title: Prompt Cache Key prompt_cache_retention: anyOf: - enum: - in_memory - 24h type: string - type: 'null' default: null title: Prompt Cache Retention reasoning: anyOf: - $ref: '#/components/schemas/ResponseReasoningConfig' - type: 'null' default: null safety_identifier: anyOf: - type: string - type: 'null' default: null title: Safety Identifier service_tier: anyOf: - type: string enum: - auto - default - flex - scale - priority - type: 'null' default: null title: Service Tier status: anyOf: - enum: - completed - failed - in_progress - cancelled - queued - incomplete type: string - type: 'null' default: null title: Status text: anyOf: - $ref: '#/components/schemas/ResponseTextConfig' - type: 'null' default: null top_logprobs: anyOf: - type: integer - type: 'null' default: null title: Top Logprobs truncation: anyOf: - enum: - auto - disabled type: string - type: 'null' default: null title: Truncation usage: anyOf: - $ref: '#/components/schemas/ResponseUsage' - type: 'null' default: null user: anyOf: - type: string - type: 'null' default: null title: User required: - id - created_at - object - output - parallel_tool_calls title: Response type: object ResponseStreamEvent: anyOf: - $ref: '#/components/schemas/ResponseCreatedEvent' - $ref: '#/components/schemas/ResponseInProgressEvent' - $ref: '#/components/schemas/ResponseOutputItemAddedEvent' - $ref: '#/components/schemas/ResponseContentPartAddedEvent' - $ref: '#/components/schemas/ResponseTextDeltaEvent' - $ref: '#/components/schemas/ResponseTextDoneEvent' - $ref: '#/components/schemas/ResponseOutputTextAnnotationAddedEvent' - $ref: '#/components/schemas/ResponseContentPartDoneEvent' - $ref: '#/components/schemas/ResponseOutputItemDoneEvent' - $ref: '#/components/schemas/ResponseCompletedEvent' - $ref: '#/components/schemas/ResponseFailedEvent' - $ref: '#/components/schemas/ResponseIncompleteEvent' description: An event in the Responses API SSE stream; `type` identifies the event. title: ResponseStreamEvent HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ResponseInputMessage: properties: role: type: string enum: - user - assistant - system - developer title: Role description: The role of the message author. content: anyOf: - type: string - items: $ref: '#/components/schemas/ResponseInputContentPart' type: array title: Content description: >- Text content of the message. Either a string or a list of content parts (`{text, type}` objects) for OpenAI SDK clients. type: object required: - role - content title: ResponseInputMessage description: |- A single input message for the Responses API. `content` accepts either a bare string (`"hi"`) or the canonical OpenAI list-of-parts (`[{"text": "hi", "type": "input_text"}]`). ResponseTextConfig: additionalProperties: true description: >- Text output configuration. By default the response is plain text; for structured output set `format` to `{"type": "json_schema", "name": ..., "schema": {...}}`. The `json_object` format is accepted for compatibility but produces plain text. properties: format: anyOf: - $ref: '#/components/schemas/ResponseFormatText' - $ref: '#/components/schemas/ResponseFormatTextJSONSchemaConfig' - $ref: '#/components/schemas/ResponseFormatJSONObject' - type: 'null' default: null title: Format verbosity: anyOf: - enum: - low - medium - high type: string - type: 'null' default: null title: Verbosity title: ResponseTextConfig type: object ResponseReasoningConfig: description: Reasoning configuration (OpenAI-compatible subset). properties: effort: anyOf: - enum: - low - medium - high type: string - type: 'null' default: null description: >- Controls how much research is performed, trading response time for answer quality. Defaults to `medium` when omitted. examples: - high title: Effort title: ResponseReasoningConfig type: object ResponseError: additionalProperties: true description: Details of a failed response. properties: code: const: server_error description: Error code; currently always "server_error". title: Code type: string message: title: Message type: string required: - code - message title: ResponseError type: object IncompleteDetails: additionalProperties: true description: Details about why the response is incomplete. properties: reason: anyOf: - enum: - max_output_tokens - content_filter type: string - type: 'null' default: null title: Reason title: IncompleteDetails type: object ResponseOutputMessage: additionalProperties: true description: An assistant message produced by the model. properties: id: title: Id type: string content: items: $ref: '#/components/schemas/ResponseOutputText' title: Content type: array role: const: assistant title: Role type: string status: enum: - in_progress - completed - incomplete title: Status type: string type: const: message title: Type type: string phase: anyOf: - enum: - commentary - final_answer type: string - type: 'null' default: null title: Phase required: - id - content - role - status - type title: ResponseOutputMessage type: object Moderation: additionalProperties: true description: >- Moderation results for the response input and output, if moderated completions were requested. properties: input: anyOf: - $ref: '#/components/schemas/ModerationInputModerationResult' - $ref: '#/components/schemas/ModerationInputError' title: Input output: anyOf: - $ref: '#/components/schemas/ModerationOutputModerationResult' - $ref: '#/components/schemas/ModerationOutputError' title: Output required: - input - output title: Moderation type: object ResponseUsage: additionalProperties: true description: |- Estimated token usage, populated for OpenAI SDK compatibility. Counts are approximate; Parallel bills per request, not per token. properties: input_tokens: title: Input Tokens type: integer input_tokens_details: $ref: '#/components/schemas/InputTokensDetails' output_tokens: title: Output Tokens type: integer output_tokens_details: $ref: '#/components/schemas/OutputTokensDetails' total_tokens: title: Total Tokens type: integer required: - input_tokens - input_tokens_details - output_tokens - output_tokens_details - total_tokens title: ResponseUsage type: object ResponseCreatedEvent: additionalProperties: true properties: response: $ref: '#/components/schemas/Response' sequence_number: title: Sequence Number type: integer type: const: response.created title: Type type: string required: - response - sequence_number - type title: ResponseCreatedEvent type: object ResponseInProgressEvent: additionalProperties: true properties: response: $ref: '#/components/schemas/Response' sequence_number: title: Sequence Number type: integer type: const: response.in_progress title: Type type: string required: - response - sequence_number - type title: ResponseInProgressEvent type: object ResponseOutputItemAddedEvent: additionalProperties: true properties: item: $ref: '#/components/schemas/ResponseOutputMessage' output_index: title: Output Index type: integer sequence_number: title: Sequence Number type: integer type: const: response.output_item.added title: Type type: string required: - item - output_index - sequence_number - type title: ResponseOutputItemAddedEvent type: object ResponseContentPartAddedEvent: additionalProperties: true properties: content_index: title: Content Index type: integer item_id: title: Item Id type: string output_index: title: Output Index type: integer part: $ref: '#/components/schemas/ResponseOutputText' sequence_number: title: Sequence Number type: integer type: const: response.content_part.added title: Type type: string required: - content_index - item_id - output_index - part - sequence_number - type title: ResponseContentPartAddedEvent type: object ResponseTextDeltaEvent: additionalProperties: true description: Emitted when there is an additional text delta. properties: content_index: title: Content Index type: integer delta: title: Delta type: string item_id: title: Item Id type: string logprobs: items: $ref: >- #/components/schemas/openai__types__responses__response_text_delta_event__Logprob title: Logprobs type: array output_index: title: Output Index type: integer sequence_number: title: Sequence Number type: integer type: const: response.output_text.delta title: Type type: string required: - content_index - delta - item_id - logprobs - output_index - sequence_number - type title: ResponseTextDeltaEvent type: object ResponseTextDoneEvent: additionalProperties: true description: Emitted when text content is finalized. properties: content_index: title: Content Index type: integer item_id: title: Item Id type: string logprobs: items: $ref: >- #/components/schemas/openai__types__responses__response_text_done_event__Logprob title: Logprobs type: array output_index: title: Output Index type: integer sequence_number: title: Sequence Number type: integer text: title: Text type: string type: const: response.output_text.done title: Type type: string required: - content_index - item_id - logprobs - output_index - sequence_number - text - type title: ResponseTextDoneEvent type: object ResponseOutputTextAnnotationAddedEvent: additionalProperties: true properties: annotation: $ref: '#/components/schemas/AnnotationURLCitation' annotation_index: title: Annotation Index type: integer content_index: title: Content Index type: integer item_id: title: Item Id type: string output_index: title: Output Index type: integer sequence_number: title: Sequence Number type: integer type: const: response.output_text.annotation.added title: Type type: string required: - annotation - annotation_index - content_index - item_id - output_index - sequence_number - type title: ResponseOutputTextAnnotationAddedEvent type: object ResponseContentPartDoneEvent: additionalProperties: true properties: content_index: title: Content Index type: integer item_id: title: Item Id type: string output_index: title: Output Index type: integer part: $ref: '#/components/schemas/ResponseOutputText' sequence_number: title: Sequence Number type: integer type: const: response.content_part.done title: Type type: string required: - content_index - item_id - output_index - part - sequence_number - type title: ResponseContentPartDoneEvent type: object ResponseOutputItemDoneEvent: additionalProperties: true properties: item: $ref: '#/components/schemas/ResponseOutputMessage' output_index: title: Output Index type: integer sequence_number: title: Sequence Number type: integer type: const: response.output_item.done title: Type type: string required: - item - output_index - sequence_number - type title: ResponseOutputItemDoneEvent type: object ResponseCompletedEvent: additionalProperties: true properties: response: $ref: '#/components/schemas/Response' sequence_number: title: Sequence Number type: integer type: const: response.completed title: Type type: string required: - response - sequence_number - type title: ResponseCompletedEvent type: object ResponseFailedEvent: additionalProperties: true properties: response: $ref: '#/components/schemas/Response' sequence_number: title: Sequence Number type: integer type: const: response.failed title: Type type: string required: - response - sequence_number - type title: ResponseFailedEvent type: object ResponseIncompleteEvent: additionalProperties: true properties: response: $ref: '#/components/schemas/Response' sequence_number: title: Sequence Number type: integer type: const: response.incomplete title: Type type: string required: - response - sequence_number - type title: ResponseIncompleteEvent type: object ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: title: Message type: string type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError ResponseInputContentPart: properties: type: anyOf: - type: string - type: 'null' title: Type description: >- The content part type. Supported: `input_text`, `output_text`, and `text`. Multimodal types (`input_image`, `input_audio`, `input_file`) are rejected with a 422 error. text: anyOf: - type: string - type: 'null' title: Text description: The text payload, when the part carries one. type: object title: ResponseInputContentPart description: |- A single content part of a message, e.g. `{"text": "hi", "type": "input_text"}`. Only text parts are supported; requests containing image, audio, or file parts fail with a 422 error. ResponseFormatText: additionalProperties: true description: Default response format. Used to generate text responses. properties: type: const: text title: Type type: string required: - type title: ResponseFormatText type: object ResponseFormatTextJSONSchemaConfig: additionalProperties: true description: >- JSON Schema output format: the response's output text conforms to `schema`. properties: name: type: string title: Name schema: additionalProperties: true title: Schema type: object type: type: string const: json_schema title: Type description: anyOf: - type: string - type: 'null' default: null title: Description strict: anyOf: - type: boolean - type: 'null' default: null title: Strict required: - name - schema - type title: ResponseFormatTextJSONSchemaConfig type: object ResponseFormatJSONObject: additionalProperties: true description: >- JSON object response format. An older method of generating JSON responses. Using `json_schema` is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so. properties: type: const: json_object title: Type type: string required: - type title: ResponseFormatJSONObject type: object ResponseOutputText: additionalProperties: true description: |- A text content part of an output message. `annotations` carries the URL citations grounding the answer. properties: annotations: items: $ref: '#/components/schemas/AnnotationURLCitation' title: Annotations type: array text: title: Text type: string type: const: output_text title: Type type: string logprobs: anyOf: - items: $ref: >- #/components/schemas/openai__types__responses__response_output_text__Logprob type: array - type: 'null' default: null title: Logprobs required: - annotations - text - type title: ResponseOutputText type: object ModerationInputModerationResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationInputModerationResult type: object ModerationInputError: additionalProperties: true description: >- An error produced while attempting moderation for the response input or output. properties: code: type: string title: Code message: title: Message type: string type: type: string const: error title: Type required: - code - message - type title: ModerationInputError type: object ModerationOutputModerationResult: additionalProperties: true description: A moderation result produced for the response input or output. properties: categories: additionalProperties: type: boolean title: Categories type: object category_applied_input_types: additionalProperties: items: enum: - text - image type: string type: array title: Category Applied Input Types type: object category_scores: additionalProperties: type: number title: Category Scores type: object flagged: title: Flagged type: boolean model: type: string title: Model type: const: moderation_result title: Type type: string required: - categories - category_applied_input_types - category_scores - flagged - model - type title: ModerationOutputModerationResult type: object ModerationOutputError: additionalProperties: true description: >- An error produced while attempting moderation for the response input or output. properties: code: type: string title: Code message: title: Message type: string type: type: string const: error title: Type required: - code - message - type title: ModerationOutputError type: object InputTokensDetails: additionalProperties: true description: A detailed breakdown of the input tokens. properties: cached_tokens: title: Cached Tokens type: integer required: - cached_tokens title: InputTokensDetails type: object OutputTokensDetails: additionalProperties: true description: A detailed breakdown of the output tokens. properties: reasoning_tokens: title: Reasoning Tokens type: integer required: - reasoning_tokens title: OutputTokensDetails type: object openai__types__responses__response_text_delta_event__Logprob: additionalProperties: true description: >- A logprob is the logarithmic probability that the model assigns to producing a particular token at a given position in the sequence. Less-negative (higher) logprob values indicate greater model confidence in that token choice. properties: token: title: Token type: string logprob: title: Logprob type: number top_logprobs: anyOf: - items: $ref: >- #/components/schemas/openai__types__responses__response_text_delta_event__LogprobTopLogprob type: array - type: 'null' default: null title: Top Logprobs required: - token - logprob title: Logprob type: object openai__types__responses__response_text_done_event__Logprob: additionalProperties: true description: >- A logprob is the logarithmic probability that the model assigns to producing a particular token at a given position in the sequence. Less-negative (higher) logprob values indicate greater model confidence in that token choice. properties: token: title: Token type: string logprob: title: Logprob type: number top_logprobs: anyOf: - items: $ref: >- #/components/schemas/openai__types__responses__response_text_done_event__LogprobTopLogprob type: array - type: 'null' default: null title: Top Logprobs required: - token - logprob title: Logprob type: object AnnotationURLCitation: additionalProperties: true description: A citation for a web resource used to generate a model response. properties: end_index: title: End Index type: integer start_index: title: Start Index type: integer title: title: Title type: string type: const: url_citation title: Type type: string url: type: string title: Url required: - end_index - start_index - title - type - url title: AnnotationURLCitation type: object openai__types__responses__response_output_text__Logprob: additionalProperties: true description: The log probability of a token. properties: token: title: Token type: string bytes: items: type: integer title: Bytes type: array logprob: title: Logprob type: number top_logprobs: items: $ref: >- #/components/schemas/openai__types__responses__response_output_text__LogprobTopLogprob title: Top Logprobs type: array required: - token - bytes - logprob - top_logprobs title: Logprob type: object openai__types__responses__response_text_delta_event__LogprobTopLogprob: additionalProperties: true properties: token: anyOf: - type: string - type: 'null' default: null title: Token logprob: anyOf: - type: number - type: 'null' default: null title: Logprob title: LogprobTopLogprob type: object openai__types__responses__response_text_done_event__LogprobTopLogprob: additionalProperties: true properties: token: anyOf: - type: string - type: 'null' default: null title: Token logprob: anyOf: - type: number - type: 'null' default: null title: Logprob title: LogprobTopLogprob type: object openai__types__responses__response_output_text__LogprobTopLogprob: additionalProperties: true description: The top log probability of a token. properties: token: title: Token type: string bytes: items: type: integer title: Bytes type: array logprob: title: Logprob type: number required: - token - bytes - logprob title: LogprobTopLogprob type: object securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-key ````