> ## Documentation Index > Fetch the complete documentation index at: https://docs.dedaluslabs.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Chat Completion > Create a chat completion. Generates a model response for the given conversation and configuration. Supports OpenAI-compatible parameters and provider-specific extensions. Headers: - Authorization: bearer key for the calling account. - X-Provider / X-Provider-Key: optional headers for using your own provider API key. Behavior: - If multiple models are supplied, the first one is used, and the agent may hand off to another model. - Tools may be invoked on the server or signaled for the client to run. - Streaming responses emit incremental deltas; non-streaming returns a single object. - Usage metrics are computed when available and returned in the response. Responses: - 200 OK: JSON completion object with choices, message content, and usage. - 400 Bad Request: validation error. - 401 Unauthorized: authentication failed. - 402 Payment Required or 429 Too Many Requests: quota, balance, or rate limit issue. - 500 Internal Server Error: unexpected failure. Billing: - Token usage metered by the selected model(s). - Tool calls and MCP sessions may be billed separately. - Streaming is settled after the stream ends via an async task. Example (non-streaming HTTP): POST /v1/chat/completions Content-Type: application/json Authorization: Bearer { "model": "provider/model-name", "messages": [{"role": "user", "content": "Hello"}] } 200 OK { "id": "cmpl_123", "object": "chat.completion", "choices": [ {"index": 0, "message": {"role": "assistant", "content": "Hi there!"}, "finish_reason": "stop"} ], "usage": {"prompt_tokens": 3, "completion_tokens": 4, "total_tokens": 7} } Example (streaming over SSE): POST /v1/chat/completions Accept: text/event-stream data: {"id":"cmpl_123","choices":[{"index":0,"delta":{"content":"Hi"}}]} data: {"id":"cmpl_123","choices":[{"index":0,"delta":{"content":" there!"}}]} data: [DONE] ## OpenAPI ````yaml /openapi.json post /v1/chat/completions openapi: 3.1.0 info: title: Dedalus API description: >- MCP gateway for AI agents. Mix-and-match any model with any tool from our marketplace. ## Authentication Use Bearer token or X-API-Key header authentication: ``` Authorization: Bearer your-api-key-here ``` ``` x-api-key: your-api-key-here ``` ## Available Endpoints - **GET /v1/models**: list available models - **POST /v1/chat/completions**: Chat completions with MCP tools - **GET /health**: Service health check version: 0.0.1 servers: - url: https://api.dedaluslabs.ai description: Official Dedalus API security: [] paths: /v1/chat/completions: post: tags: - V1 - Chat summary: Create Chat Completion description: |- Create a chat completion. Generates a model response for the given conversation and configuration. Supports OpenAI-compatible parameters and provider-specific extensions. Headers: - Authorization: bearer key for the calling account. - X-Provider / X-Provider-Key: optional headers for using your own provider API key. Behavior: - If multiple models are supplied, the first one is used, and the agent may hand off to another model. - Tools may be invoked on the server or signaled for the client to run. - Streaming responses emit incremental deltas; non-streaming returns a single object. - Usage metrics are computed when available and returned in the response. Responses: - 200 OK: JSON completion object with choices, message content, and usage. - 400 Bad Request: validation error. - 401 Unauthorized: authentication failed. - 402 Payment Required or 429 Too Many Requests: quota, balance, or rate limit issue. - 500 Internal Server Error: unexpected failure. Billing: - Token usage metered by the selected model(s). - Tool calls and MCP sessions may be billed separately. - Streaming is settled after the stream ends via an async task. Example (non-streaming HTTP): POST /v1/chat/completions Content-Type: application/json Authorization: Bearer { "model": "provider/model-name", "messages": [{"role": "user", "content": "Hello"}] } 200 OK { "id": "cmpl_123", "object": "chat.completion", "choices": [ {"index": 0, "message": {"role": "assistant", "content": "Hi there!"}, "finish_reason": "stop"} ], "usage": {"prompt_tokens": 3, "completion_tokens": 4, "total_tokens": 7} } Example (streaming over SSE): POST /v1/chat/completions Accept: text/event-stream data: {"id":"cmpl_123","choices":[{"index":0,"delta":{"content":"Hi"}}]} data: {"id":"cmpl_123","choices":[{"index":0,"delta":{"content":" there!"}}]} data: [DONE] operationId: create_chat_completion_v1_chat_completions_post requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' required: true responses: '200': description: JSON or SSE stream of ChatCompletionChunk events content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' text/event-stream: schema: $ref: '#/components/schemas/ChatCompletionStreamResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Bearer: [] x-codeSamples: - lang: typescript label: Typescript source: |- const client = new Dedalus(); const result = await client.chat.completions.create({ ...params }); - lang: python label: Python source: |- client = Dedalus() result = client.chat.completions.create(**params) - lang: go label: Go source: >- client := dedalus.NewClient() result, err := client.Chat.Completions.New(ctx, body githubcomdedaluslabsdedalussdkgo.ChatCompletionNewParams) components: schemas: ChatCompletionRequest: properties: audio: anyOf: - $ref: '#/components/schemas/ChatCompletionRequestAudio' - type: 'null' description: >- Parameters for audio output. Required when requesting audio responses with `modalities: ['audio']`. See: https://platform.openai.com/docs/guides/audio examples: - format: mp3 voice: alloy frequency_penalty: anyOf: - type: number maximum: 2 minimum: -2 - type: 'null' title: Frequency Penalty description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. default: 0 function_call: anyOf: - type: string - type: 'null' title: Function Call description: >- Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. functions: anyOf: - items: $ref: '#/components/schemas/ChatCompletionFunctions' type: array - type: 'null' title: Functions description: >- Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. logit_bias: anyOf: - additionalProperties: type: integer type: object - type: 'null' title: Logit Bias description: >- Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. logprobs: anyOf: - type: boolean - type: 'null' title: Logprobs description: >- Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. default: false max_completion_tokens: anyOf: - type: integer - type: 'null' title: Max Completion Tokens description: Maximum tokens in completion (newer parameter name) max_tokens: anyOf: - type: integer minimum: 1 - type: 'null' title: Max Tokens description: Maximum tokens in completion messages: anyOf: - items: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessage' - $ref: '#/components/schemas/ChatCompletionRequestSystemMessage' - $ref: '#/components/schemas/ChatCompletionRequestUserMessage' - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage' - $ref: '#/components/schemas/ChatCompletionRequestToolMessage' - $ref: '#/components/schemas/ChatCompletionRequestFunctionMessage' discriminator: propertyName: role mapping: assistant: $ref: >- #/components/schemas/ChatCompletionRequestAssistantMessage developer: $ref: >- #/components/schemas/ChatCompletionRequestDeveloperMessage function: $ref: >- #/components/schemas/ChatCompletionRequestFunctionMessage system: $ref: '#/components/schemas/ChatCompletionRequestSystemMessage' tool: $ref: '#/components/schemas/ChatCompletionRequestToolMessage' user: $ref: '#/components/schemas/ChatCompletionRequestUserMessage' type: array - type: 'null' title: Messages description: >- Conversation history (OpenAI: messages, Google: contents, Responses: input) metadata: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' 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. modalities: anyOf: - items: type: string type: array - type: 'null' title: Modalities description: >- Output types that you would like the model to generate. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]` model: anyOf: - $ref: '#/components/schemas/DedalusModelChoice' - items: $ref: '#/components/schemas/DedalusModelChoice' type: array title: Model description: >- Model identifier. Accepts model ID strings, lists for routing, or DedalusModel objects with per-model settings. examples: - openai/gpt-5 - - openai/gpt-5 - anthropic/claude-3-sonnet 'n': anyOf: - type: integer maximum: 128 minimum: 1 - type: 'null' title: 'N' description: >- How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. default: 1 parallel_tool_calls: anyOf: - type: boolean - type: 'null' title: Parallel Tool Calls description: >- Whether to enable parallel tool calls (Anthropic uses inverted polarity). default: true prediction: anyOf: - $ref: '#/components/schemas/PredictionContent' - type: 'null' description: >- Configuration for a [Predicted Output](/docs/guides/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. presence_penalty: anyOf: - type: number maximum: 2 minimum: -2 - type: 'null' title: Presence Penalty description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. default: 0 prompt_cache_key: anyOf: - type: string - type: 'null' title: Prompt Cache Key description: >- Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](/docs/guides/prompt-caching). prompt_cache_retention: anyOf: - type: string - type: 'null' title: Prompt Cache Retention description: >- The retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](/docs/guides/prompt-caching#prompt-cache-retention). reasoning_effort: anyOf: - type: string - type: 'null' title: Reasoning Effort description: >- Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool calls are supported for all reasoning values in gpt-5.1. - All models before `gpt-5.1` default to `medium` reasoning effort, and do not support `none`. - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort. - `xhigh` is supported for all models after `gpt-5.1-codex-max`. default: medium response_format: anyOf: - oneOf: - $ref: '#/components/schemas/ResponseFormatText' - $ref: '#/components/schemas/ResponseFormatJsonSchema' - $ref: '#/components/schemas/ResponseFormatJsonObject' discriminator: propertyName: type mapping: json_object: $ref: '#/components/schemas/ResponseFormatJsonObject' json_schema: $ref: '#/components/schemas/ResponseFormatJsonSchema' text: $ref: '#/components/schemas/ResponseFormatText' - type: 'null' title: Response Format description: >- An object specifying the format that the model must output. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON. Using `json_schema` is preferred for models that support it. safety_identifier: anyOf: - type: string maxLength: 64 - type: 'null' title: Safety Identifier description: >- A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). seed: anyOf: - type: integer maximum: 9223372036854776000 minimum: 0 - type: 'null' title: Seed description: Random seed for deterministic output service_tier: anyOf: - type: string - type: 'null' title: Service Tier description: Service tier for request processing default: auto stop: anyOf: - items: type: string type: array - type: string - type: 'null' title: Stop description: Sequences that stop generation store: anyOf: - type: boolean - type: 'null' title: Store description: >- Whether or not to store the output of this chat completion request for use in our [model distillation](/docs/guides/distillation) or [evals](/docs/guides/evals) products. Supports text and image inputs. Note: image inputs over 8MB will be dropped. default: false stream: anyOf: - type: boolean - type: 'null' title: Stream description: Enable streaming response default: false stream_options: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' description: >- Options for streaming response. Only set this when you set `stream: true`. system_instruction: anyOf: - $ref: '#/components/schemas/JSONObject' - type: string - type: 'null' title: System Instruction description: System instruction/prompt temperature: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Temperature description: Sampling temperature (0-2 for most providers) default: 1 tool_choice: anyOf: - type: string - oneOf: - $ref: '#/components/schemas/ToolChoiceAuto' - $ref: '#/components/schemas/ToolChoiceAny' - $ref: '#/components/schemas/ToolChoiceTool' - $ref: '#/components/schemas/ToolChoiceNone' discriminator: propertyName: type mapping: any: $ref: '#/components/schemas/ToolChoiceAny' auto: $ref: '#/components/schemas/ToolChoiceAuto' none: $ref: '#/components/schemas/ToolChoiceNone' tool: $ref: '#/components/schemas/ToolChoiceTool' - type: 'null' title: Tool Choice description: >- Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present. default: auto tools: anyOf: - items: $ref: '#/components/schemas/Tool' type: array - type: 'null' title: Tools description: Available tools/functions for the model top_k: anyOf: - type: integer minimum: 0 - type: 'null' title: Top K description: Top-k sampling parameter top_logprobs: anyOf: - type: integer maximum: 8 minimum: 0 - type: 'null' title: Top Logprobs description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. top_p: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Top P description: Nucleus sampling threshold default: 1 user: anyOf: - type: string - type: 'null' title: User description: >- This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](/docs/guides/safety-best-practices#safety-identifiers). verbosity: anyOf: - type: string - type: 'null' title: Verbosity description: >- Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are `low`, `medium`, and `high`. default: medium web_search_options: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' description: >- This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](/docs/guides/tools-web-search?api-mode=chat). cache_control: anyOf: - $ref: '#/components/schemas/CacheControlEphemeral' - type: 'null' description: >- Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. cached_content: anyOf: - type: string - type: 'null' title: Cached Content description: >- Optional. The name of the content [cached](https://ai.google.dev/gemini-api/docs/caching) to use as context to serve the prediction. Format: `cachedContents/{cachedContent}` container: anyOf: - type: string - type: 'null' title: Container description: Container identifier for reuse across requests. deferred: anyOf: - type: boolean - type: 'null' title: Deferred description: >- If set to `true`, the request returns a `request_id`. You can then get the deferred response by GET `/v1/chat/deferred-completion/{request_id}`. default: false generation_config: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' description: Generation parameters wrapper (Google-specific) inference_geo: anyOf: - type: string - type: 'null' title: Inference Geo description: >- Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. output_config: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' prompt_mode: anyOf: - type: string const: reasoning - type: 'null' title: Prompt Mode description: >- Allows toggling between the reasoning mode and no system prompt. When set to `reasoning` the system prompt for reasoning models will be used. safe_prompt: anyOf: - type: boolean - type: 'null' title: Safe Prompt description: Whether to inject a safety prompt before all conversations. default: false safety_settings: anyOf: - items: $ref: '#/components/schemas/SafetySetting' type: array - type: 'null' title: Safety Settings description: Safety/content filtering settings (Google-specific) search_parameters: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' description: >- Set the parameters to be used for searched data. If not set, no data will be acquired by the model. thinking: anyOf: - oneOf: - $ref: '#/components/schemas/ThinkingConfigEnabled' - $ref: '#/components/schemas/ThinkingConfigDisabled' - $ref: '#/components/schemas/ThinkingConfigAdaptive' discriminator: propertyName: type mapping: adaptive: $ref: '#/components/schemas/ThinkingConfigAdaptive' disabled: $ref: '#/components/schemas/ThinkingConfigDisabled' enabled: $ref: '#/components/schemas/ThinkingConfigEnabled' - type: 'null' title: Thinking description: Extended thinking configuration (Anthropic-specific) tool_config: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' description: Tool calling configuration (Google-specific) mcp_servers: anyOf: - type: string - $ref: '#/components/schemas/MCPServerSpec' - $ref: '#/components/schemas/MCPServers' - type: 'null' title: Mcp Servers description: >- MCP server identifiers. Accepts marketplace slugs, URLs, or MCPServerSpec objects. MCP tools are executed server-side and billed separately. examples: - dedalus-labs/example-server - - dedalus-labs/example-server-1 - dedalus-labs/example-server-2 - slug: dedalus-labs/example-server-1 version: v1.0.0 - url: https://mcp.dedaluslabs.ai/dedalus-labs/example-server-1 - url: https://mcp.dedaluslabs.ai/dedalus-labs/example-server-2/mcp credentials: anyOf: - $ref: '#/components/schemas/Credential' - $ref: '#/components/schemas/MCPCredentials' - type: 'null' title: Credentials description: >- Credentials for MCP server authentication. Each credential is matched to servers by connection name. examples: - connection_name: external-service values: api_key: sk-... - - connection_name: service-a values: api_key: sk-... - connection_name: service-b values: token: tok_... guardrails: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' title: Guardrails description: Content filtering and safety policy configuration. handoff_config: anyOf: - additionalProperties: true type: object - type: 'null' title: Handoff Config description: Configuration for multi-model handoffs. model_attributes: anyOf: - additionalProperties: additionalProperties: type: number type: object type: object - type: 'null' title: Model Attributes description: >- Model attributes for routing. Maps model IDs to attribute dictionaries with values in [0.0, 1.0]. examples: - gpt-5: accuracy: 0.95 speed: 0.6 agent_attributes: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Agent Attributes description: Agent attributes. Values in [0.0, 1.0]. examples: - accuracy: 0.9 complexity: 0.8 max_turns: anyOf: - type: integer maximum: 100 minimum: 1 - type: 'null' title: Max Turns description: Maximum conversation turns. examples: - 5 - 10 automatic_tool_execution: type: boolean title: Automatic Tool Execution description: >- Execute tools server-side. If false, returns raw tool calls for manual handling. default: true correlation_id: anyOf: - type: string - type: 'null' title: Correlation Id description: >- Stable session ID for resuming a previous handoff. Returned by the server on handoff; echo it on the next request to resume. deferred_calls: anyOf: - items: $ref: '#/components/schemas/DeferredCallResponse' type: array - type: 'null' title: Deferred Calls description: >- Tier 2 stateless resumption. Deferred tool specs from a previous handoff response, sent back verbatim so the server can resume without Redis. handoff_mode: anyOf: - type: boolean - type: 'null' title: Handoff Mode description: >- Handoff control. None or omitted: auto-detect. true: structured handoff (SDK). false: drop-in (LLM re-run for mixed turns). additionalProperties: true type: object required: - model title: ChatCompletionRequest description: |- ChatCompletion request schema. Supports OpenAI-compatible parameters, provider-specific extensions, server-side execution, and agent orchestration features. ChatCompletion: properties: id: type: string title: Id description: A unique identifier for the chat completion. x-order: 0 choices: items: $ref: '#/components/schemas/Choice' type: array title: Choices description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. x-order: 1 created: type: integer title: Created description: >- The Unix timestamp (in seconds) of when the chat completion was created. x-order: 2 model: type: string title: Model description: The model used for the chat completion. x-order: 3 service_tier: anyOf: - type: string enum: - auto - default - flex - scale - priority - type: 'null' title: Service Tier description: |- Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. x-order: 4 system_fingerprint: type: string title: System Fingerprint description: >- This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. x-order: 5 object: type: string const: chat.completion title: Object description: The object type, which is always `chat.completion`. x-order: 6 usage: $ref: '#/components/schemas/CompletionUsage' description: Usage statistics for the completion request. x-order: 7 tools_executed: anyOf: - items: type: string type: array - type: 'null' title: Tools Executed description: >- List of tool names that were executed server-side (e.g., MCP tools). Only present when tools were executed on the server rather than returned for client-side execution. mcp_server_errors: anyOf: - additionalProperties: $ref: '#/components/schemas/MCPServerError' type: object - type: 'null' title: Mcp Server Errors description: MCP server failures keyed by server name. mcp_tool_results: anyOf: - items: $ref: '#/components/schemas/MCPToolResult' type: array - type: 'null' title: Mcp Tool Results description: >- Detailed results of MCP tool executions including inputs, outputs, and timing. Provides full visibility into server-side tool execution for debugging and audit purposes. correlation_id: anyOf: - type: string - type: 'null' title: Correlation Id description: >- Stable session ID for cross-turn handoff state. Echo this on the next request to resume server-side execution. server_results: anyOf: - additionalProperties: $ref: '#/components/schemas/JSONValue' type: object - type: 'null' title: Server Results description: Completed server tool outputs keyed by call ID. deferred: anyOf: - items: $ref: '#/components/schemas/DeferredCallResponse' type: array - type: 'null' title: Deferred description: Server tools blocked on client results. pending_tools: anyOf: - items: $ref: '#/components/schemas/PendingCallResponse' type: array - type: 'null' title: Pending Tools description: Client tools to execute, with dependency ordering. turns_consumed: anyOf: - type: integer - type: 'null' title: Turns Consumed description: >- Number of internal LLM calls made during this request. SDKs can sum this across their outer loop to track total LLM calls. type: object required: - id - choices - created - model - object title: ChatCompletion description: >- Chat completion response for Dedalus API. OpenAI-compatible chat completion response with Dedalus extensions. Maintains full compatibility with OpenAI API while providing additional features like server-side tool execution tracking and MCP error reporting. example: choices: - finish_reason: stop index: 0 message: content: The next Warriors game is tomorrow at 7:30 PM. role: assistant created: 1677652288 id: chatcmpl-123 model: gpt-4o-mini object: chat.completion tools_executed: - search_events - get_event_details usage: completion_tokens: 12 prompt_tokens: 9 total_tokens: 21 ChatCompletionStreamResponse: description: |- Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. [Learn more](/docs/guides/streaming-responses). Fields: - id (required): str - choices (required): list[ChatCompletionStreamResponseChoicesItem] - created (required): int - model (required): str - service_tier (optional): ServiceTier - system_fingerprint (optional): str - object (required): Literal["chat.completion.chunk"] - usage (optional): CompletionUsage properties: id: description: >- A unique identifier for the chat completion. Each chunk has the same ID. title: Id type: string x-order: 0 choices: description: >- A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the last chunk if you set `stream_options: {"include_usage": true}`. items: $ref: '#/components/schemas/ChatCompletionStreamResponseChoicesItem' title: Choices type: array x-order: 1 created: description: >- The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. title: Created type: integer x-order: 2 model: description: The model to generate the completion. title: Model type: string x-order: 3 service_tier: anyOf: - type: string enum: - auto - default - flex - scale - priority - type: 'null' default: null description: |- Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](/docs/guides/flex-processing)' or '[priority](https://openai.com/api-priority-processing/)', then the request will be processed with the corresponding service tier. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. title: Service Tier x-order: 4 system_fingerprint: default: null description: >- This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. title: System Fingerprint type: string x-order: 5 object: const: chat.completion.chunk description: The object type, which is always `chat.completion.chunk`. title: Object type: string x-order: 6 usage: anyOf: - $ref: '#/components/schemas/CompletionUsage' - type: 'null' default: null description: >- An optional field that will only be present when you set `stream_options: {"include_usage": true}` in your request. When present, it contains a null value **except for the last chunk** which contains the token usage statistics for the entire request. **NOTE:** If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request. x-order: 7 required: - id - choices - created - model - object title: ChatCompletionStreamResponse type: object HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ChatCompletionRequestAudio: properties: voice: anyOf: - type: string - type: string enum: - alloy - ash - ballad - coral - echo - sage - shimmer - verse - marin - cedar - $ref: '#/components/schemas/VoiceIdsOrCustomVoiceInline' title: Voice description: >- The voice the model uses to respond. Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`, `onyx`, `sage`, `shimmer`, `marin`, and `cedar`. You may also provide a custom voice object with an `id`, for example `{ "id": "voice_1234" }`. x-order: 0 format: type: string enum: - wav - aac - mp3 - flac - opus - pcm16 title: Format description: >- Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`. x-order: 1 type: object required: - voice - format title: ChatCompletionRequestAudio description: >- Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. [Learn more](/docs/guides/audio). Fields: - voice (required): VoiceIdsOrCustomVoice - format (required): Literal["wav", "aac", "mp3", "flac", "opus", "pcm16"] x-ddls-inline: true ChatCompletionFunctions: properties: description: type: string title: Description description: >- A description of what the function does, used by the model to choose when and how to call the function. x-order: 0 name: type: string title: Name description: >- The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. x-order: 1 parameters: $ref: '#/components/schemas/FunctionParameters' description: >- The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list. x-order: 2 type: object required: - name title: ChatCompletionFunctions description: |- Schema for ChatCompletionFunctions. Fields: - description (optional): str - name (required): str - parameters (optional): FunctionParameters ChatCompletionRequestDeveloperMessage: properties: content: anyOf: - type: string - items: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: ChatCompletionRequestDeveloperMessageContentArray title: Content description: The contents of the developer message. x-order: 0 role: type: string const: developer title: Role description: The role of the messages author, in this case `developer`. x-order: 1 name: type: string title: Name description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. x-order: 2 type: object required: - content - role title: ChatCompletionRequestDeveloperMessage description: >- Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, `developer` messages replace the previous `system` messages. Fields: - content (required): str | Annotated[list[ChatCompletionRequestMessageContentPartText], MinLen(1), ArrayTitle("ChatCompletionRequestDeveloperMessageContentArray")] - role (required): Literal["developer"] - name (optional): str ChatCompletionRequestSystemMessage: properties: content: anyOf: - type: string - items: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: ChatCompletionRequestSystemMessageContentArray title: Content description: The contents of the system message. x-order: 0 role: type: string const: system title: Role description: The role of the messages author, in this case `system`. x-order: 1 name: type: string title: Name description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. x-order: 2 type: object required: - content - role title: ChatCompletionRequestSystemMessage description: >- Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use `developer` messages for this purpose instead. Fields: - content (required): str | Annotated[list[ChatCompletionRequestSystemMessageContentPart], MinLen(1), ArrayTitle("ChatCompletionRequestSystemMessageContentArray")] - role (required): Literal["system"] - name (optional): str ChatCompletionRequestUserMessage: properties: content: anyOf: - type: string - items: oneOf: - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartImage - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartAudio - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartFile discriminator: propertyName: type mapping: file: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartFile image_url: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartImage input_audio: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartAudio text: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: ChatCompletionRequestUserMessageContentArray title: Content description: The contents of the user message. x-order: 0 role: type: string const: user title: Role description: The role of the messages author, in this case `user`. x-order: 1 name: type: string title: Name description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. x-order: 2 type: object required: - content - role title: ChatCompletionRequestUserMessage description: >- Messages sent by an end user, containing prompts or additional context information. Fields: - content (required): str | Annotated[list[ChatCompletionRequestUserMessageContentPart], MinLen(1), ArrayTitle("ChatCompletionRequestUserMessageContentArray")] - role (required): Literal["user"] - name (optional): str ChatCompletionRequestAssistantMessage: properties: content: anyOf: - type: string - items: oneOf: - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartRefusal discriminator: propertyName: type mapping: refusal: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartRefusal text: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: ChatCompletionRequestAssistantMessageContentArray - type: 'null' title: Content description: >- The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. x-order: 0 refusal: anyOf: - type: string - type: 'null' title: Refusal description: The refusal message by the assistant. x-order: 1 role: type: string const: assistant title: Role description: The role of the messages author, in this case `assistant`. x-order: 2 name: type: string title: Name description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. x-order: 3 audio: anyOf: - $ref: '#/components/schemas/Audio' - type: 'null' description: |- Data about a previous audio response from the model. [Learn more](/docs/guides/audio). x-order: 4 tool_calls: items: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageToolCall' - $ref: '#/components/schemas/ChatCompletionMessageCustomToolCall' discriminator: propertyName: type mapping: custom: $ref: '#/components/schemas/ChatCompletionMessageCustomToolCall' function: $ref: '#/components/schemas/ChatCompletionMessageToolCall' type: array title: Tool Calls description: The tool calls generated by the model, such as function calls. x-order: 5 function_call: anyOf: - $ref: '#/components/schemas/FunctionCall' - type: 'null' description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. x-order: 6 type: object required: - role title: ChatCompletionRequestAssistantMessage description: >- Messages sent by the model in response to user messages. Fields: - content (optional): str | Annotated[list[ChatCompletionRequestAssistantMessageContentPart], MinLen(1), ArrayTitle("ChatCompletionRequestAssistantMessageContentArray")] | None - refusal (optional): str | None - role (required): Literal["assistant"] - name (optional): str - audio (optional): Audio | None - tool_calls (optional): ChatCompletionMessageToolCalls - function_call (optional): FunctionCall | None ChatCompletionRequestToolMessage: properties: role: type: string const: tool title: Role description: The role of the messages author, in this case `tool`. x-order: 0 content: anyOf: - type: string - items: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: ChatCompletionRequestToolMessageContentArray title: Content description: The contents of the tool message. x-order: 1 tool_call_id: type: string title: Tool Call Id description: Tool call that this message is responding to. x-order: 2 type: object required: - role - content - tool_call_id title: ChatCompletionRequestToolMessage description: >- Schema for ChatCompletionRequestToolMessage. Fields: - role (required): Literal["tool"] - content (required): str | Annotated[list[ChatCompletionRequestToolMessageContentPart], MinLen(1), ArrayTitle("ChatCompletionRequestToolMessageContentArray")] - tool_call_id (required): str ChatCompletionRequestFunctionMessage: properties: role: type: string const: function title: Role description: The role of the messages author, in this case `function`. x-order: 0 content: anyOf: - type: string - type: 'null' title: Content description: The contents of the function message. x-order: 1 name: type: string title: Name description: The name of the function to call. x-order: 2 type: object required: - role - content - name title: ChatCompletionRequestFunctionMessage description: |- Schema for ChatCompletionRequestFunctionMessage. Fields: - role (required): Literal["function"] - content (required): str | None - name (required): str JSONObject: additionalProperties: $ref: '#/components/schemas/JSONValue' type: object DedalusModelChoice: anyOf: - $ref: '#/components/schemas/ModelId' - $ref: '#/components/schemas/DedalusModel' title: DedalusModelChoice description: >- Dedalus model choice - either a string ID or DedalusModel configuration object. PredictionContent: properties: type: type: string const: content title: Type description: |- The type of the predicted content you want to provide. This type is currently always `content`. x-order: 0 content: anyOf: - type: string - items: $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartText type: array minItems: 1 title: PredictionContentArray title: Content description: >- The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly. x-order: 1 type: object required: - type - content title: PredictionContent description: >- Static predicted output content, such as the content of a text file that is being regenerated. Fields: - type (required): Literal["content"] - content (required): str | Annotated[list[ChatCompletionRequestMessageContentPartText], MinLen(1), ArrayTitle("PredictionContentArray")] ResponseFormatText: properties: type: type: string const: text title: Type description: The type of response format being defined. Always `text`. x-order: 0 type: object required: - type title: ResponseFormatText description: |- Default response format. Used to generate text responses. Fields: - type (required): Literal["text"] ResponseFormatJsonSchema: properties: type: type: string const: json_schema title: Type description: The type of response format being defined. Always `json_schema`. x-order: 0 json_schema: $ref: '#/components/schemas/JSONSchema' description: Structured Outputs configuration options, including a JSON Schema. x-order: 1 type: object required: - type - json_schema title: ResponseFormatJsonSchema description: |- JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](/docs/guides/structured-outputs). Fields: - type (required): Literal["json_schema"] - json_schema (required): JSONSchema ResponseFormatJsonObject: properties: type: type: string const: json_object title: Type description: The type of response format being defined. Always `json_object`. x-order: 0 type: object required: - type title: ResponseFormatJsonObject 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. Fields: - type (required): Literal["json_object"] ToolChoiceAuto: properties: disable_parallel_tool_use: type: boolean title: Disable Parallel Tool Use description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. x-order: 0 type: type: string const: auto title: Type x-order: 1 type: object required: - type title: ToolChoiceAuto description: |- The model will automatically decide whether to use tools. Fields: - disable_parallel_tool_use (optional): bool - type (required): Literal["auto"] ToolChoiceAny: properties: disable_parallel_tool_use: type: boolean title: Disable Parallel Tool Use description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. x-order: 0 type: type: string const: any title: Type x-order: 1 type: object required: - type title: ToolChoiceAny description: |- The model will use any available tools. Fields: - disable_parallel_tool_use (optional): bool - type (required): Literal["any"] ToolChoiceTool: properties: disable_parallel_tool_use: type: boolean title: Disable Parallel Tool Use description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. x-order: 0 name: type: string title: Name description: The name of the tool to use. x-order: 1 type: type: string const: tool title: Type x-order: 2 type: object required: - name - type title: ToolChoiceTool description: |- The model will use the specified tool with `tool_choice.name`. Fields: - disable_parallel_tool_use (optional): bool - name (required): str - type (required): Literal["tool"] ToolChoiceNone: properties: type: type: string const: none title: Type x-order: 0 type: object required: - type title: ToolChoiceNone description: |- The model will not be allowed to use tools. Fields: - type (required): Literal["none"] Tool: properties: type: type: string const: function title: Type default: function x-order: 0 function: $ref: '#/components/schemas/Function' x-order: 1 type: object required: - function title: Tool description: |- Schema for Tool. Fields: - type (optional): ToolTypes - function (required): Function CacheControlEphemeral: properties: ttl: type: string enum: - 5m - 1h title: Ttl description: |- The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. x-order: 0 type: type: string const: ephemeral title: Type x-order: 1 type: object required: - type title: CacheControlEphemeral description: |- Schema for CacheControlEphemeral. Fields: - ttl (optional): Literal["5m", "1h"] - type (required): Literal["ephemeral"] SafetySetting: properties: category: type: string enum: - SEXUALLY_EXPLICIT - DANGEROUS_CONTENT title: Category description: The category this setting applies to. x-order: 0 threshold: type: string enum: - BLOCK_UNSET - BLOCK_LOW_THRESHOLD - BLOCK_HIGH_THRESHOLD title: Threshold description: The blocking threshold for the category. x-order: 1 type: object required: - category - threshold title: SafetySetting description: >- Per-category safety setting that pairs a content category with a blocking threshold. Fields: - category (required): SafetyCategory - threshold (required): SafetyThreshold ThinkingConfigEnabled: properties: budget_tokens: type: integer minimum: 1024 title: Budget Tokens description: >- Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://docs.claude.com/en/docs/build-with-claude/extended-thinking) for details. x-order: 0 type: type: string const: enabled title: Type x-order: 1 type: object required: - budget_tokens - type title: ThinkingConfigEnabled description: |- Schema for ThinkingConfigEnabled. Fields: - budget_tokens (required): int - type (required): Literal["enabled"] ThinkingConfigDisabled: properties: type: type: string const: disabled title: Type x-order: 0 type: object required: - type title: ThinkingConfigDisabled description: |- Schema for ThinkingConfigDisabled. Fields: - type (required): Literal["disabled"] ThinkingConfigAdaptive: properties: type: type: string const: adaptive title: Type x-order: 0 type: object required: - type title: ThinkingConfigAdaptive description: |- Schema for ThinkingConfigAdaptive. Fields: - type (required): Literal["adaptive"] MCPServerSpec: properties: slug: anyOf: - type: string pattern: ^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$ - type: 'null' title: Slug description: Marketplace identifier. url: anyOf: - type: string - type: 'null' title: Url description: Direct URL to MCP server endpoint (Pro users). name: type: string title: Name description: Server instance name for credential matching. version: anyOf: - type: string - type: 'null' title: Version description: Version constraint for slug-based servers. credentials: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Credentials description: >- Encrypted credential blobs keyed by connection name. Values are base64url ciphertext produced by the SDK (client-side encryption with the AS public key). additionalProperties: false type: object required: - name title: MCPServerSpec description: >- Structured MCP server specification. Slug-based: {"slug": "dedalus-labs/brave-search", "name": "github-integration", "version": "v1.0.0"} URL-based: {"url": "https://mcp.dedaluslabs.ai/acme/my-server/mcp", "name": "custom-server"} MCPServers: items: anyOf: - type: string - $ref: '#/components/schemas/MCPServerSpec' type: array title: MCPServers description: List of MCP server inputs (slugs or structured specs). x-stainless-variantName: MCPServers Credential: properties: connection_name: type: string title: Connection Name description: Connection name. Must match a connection in MCPServer.connections. values: additionalProperties: anyOf: - type: string - type: integer - type: boolean type: object title: Values description: >- Credential values. Keys are credential field names, values are the secrets. additionalProperties: false type: object required: - connection_name - values title: Credential description: >- Credential for MCP server authentication. Passed at endpoint level (e.g., chat.completions.create) and matched to MCP servers by connection name. Wire format matches dedalus_mcp.Credential.to_dict(). MCPCredentials: items: $ref: '#/components/schemas/Credential' type: array title: MCPCredentials description: List of credentials for MCP server authentication. x-stainless-variantName: MCPCredentials DeferredCallResponse: properties: id: type: string title: Id description: Unique identifier for this deferred call. name: type: string title: Name description: Name of the tool. arguments: $ref: '#/components/schemas/JSONObject' description: Input arguments for the tool call. venue: type: string title: Venue description: Execution venue (server or client). default: server dependencies: items: type: string type: array title: Dependencies description: IDs of calls this depends on. blocked_by: items: type: string type: array title: Blocked By description: IDs of pending client calls blocking this call. type: object required: - id - name title: DeferredCallResponse description: |- Server-side call blocked until pending client calls complete. Carries full spec for stateless resumption on subsequent turns. Choice: properties: finish_reason: anyOf: - type: string enum: - stop - length - tool_calls - content_filter - function_call - type: 'null' title: Finish Reason description: >- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. x-order: 0 index: type: integer title: Index description: The index of the choice in the list of choices. x-order: 1 message: $ref: '#/components/schemas/ChatCompletionResponseMessage' description: A chat completion message generated by the model. x-order: 2 logprobs: anyOf: - $ref: '#/components/schemas/ChoiceLogprobs' - type: 'null' description: Log probability information for the choice. x-order: 3 type: object required: - index - message title: Choice description: |- A chat completion choice. OpenAI-compatible choice object for non-streaming responses. Part of the ChatCompletion response. x-ddls-inline: true CompletionUsage: properties: completion_tokens: type: integer title: Completion Tokens description: Number of tokens in the generated completion. x-order: 0 prompt_tokens: type: integer title: Prompt Tokens description: Number of tokens in the prompt. x-order: 1 total_tokens: type: integer title: Total Tokens description: Total number of tokens used in the request (prompt + completion). x-order: 2 completion_tokens_details: $ref: '#/components/schemas/CompletionTokensDetails' description: Breakdown of tokens used in a completion. x-order: 3 prompt_tokens_details: $ref: '#/components/schemas/PromptTokensDetails' description: Breakdown of tokens used in the prompt. x-order: 4 type: object required: - completion_tokens - prompt_tokens - total_tokens title: CompletionUsage description: |- Usage statistics for the completion request. Fields: - completion_tokens (required): int - prompt_tokens (required): int - total_tokens (required): int - completion_tokens_details (optional): CompletionTokensDetails - prompt_tokens_details (optional): PromptTokensDetails MCPServerError: properties: message: type: string title: Message description: Human-readable error message. code: anyOf: - type: string - type: 'null' title: Code description: Machine-readable error code. recommendation: anyOf: - type: string - type: 'null' title: Recommendation description: Suggested action for the user. type: object required: - message title: MCPServerError description: Error details for a single MCP server failure. MCPToolResult: properties: tool_name: type: string title: Tool Name description: Name of the MCP tool that was executed. server_name: type: string title: Server Name description: Name of the MCP server that handled the tool. arguments: $ref: '#/components/schemas/JSONObject' description: Input arguments passed to the tool. result: anyOf: - $ref: '#/components/schemas/JSONValue' - type: 'null' description: >- Structured result from the tool (parsed from structuredContent or content). is_error: type: boolean title: Is Error description: Whether the tool execution resulted in an error. duration_ms: anyOf: - type: integer - type: 'null' title: Duration (ms) description: Execution time in milliseconds. type: object required: - tool_name - server_name - arguments - is_error title: MCPToolResult description: >- Result of a single MCP tool execution. Provides visibility into MCP tool calls including the full input arguments and structured output, enabling debugging and audit trails. JSONValue: anyOf: - type: string - type: integer - type: number - type: boolean - additionalProperties: $ref: '#/components/schemas/JSONValue' type: object - items: $ref: '#/components/schemas/JSONValue' type: array - type: 'null' PendingCallResponse: properties: id: type: string title: Id description: Unique identifier for this tool call. name: type: string title: Name description: Name of the tool to execute. arguments: $ref: '#/components/schemas/JSONObject' description: Input arguments for the tool call. dependencies: items: type: string type: array title: Dependencies description: IDs of other pending calls that must complete first. type: object required: - id - name - arguments title: PendingCallResponse description: Client-side tool call the SDK must execute. ChatCompletionStreamResponseChoicesItem: description: >- Schema for ChatCompletionStreamResponseChoicesItem. Fields: - delta (required): ChatCompletionStreamResponseDelta - logprobs (optional): ChatCompletionStreamResponseChoicesItemLogprobs - finish_reason (required): Literal["stop", "length", "tool_calls", "content_filter", "function_call"] - index (required): int properties: delta: $ref: '#/components/schemas/ChatCompletionStreamResponseDelta' description: A chat completion delta generated by streamed model responses. x-order: 0 logprobs: anyOf: - $ref: >- #/components/schemas/ChatCompletionStreamResponseChoicesItemLogprobs - type: 'null' default: null description: Log probability information for the choice. x-order: 1 finish_reason: anyOf: - type: string enum: - stop - length - tool_calls - content_filter - function_call - type: 'null' description: >- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. title: Finish Reason x-order: 2 index: description: The index of the choice in the list of choices. title: Index type: integer x-order: 3 required: - delta - finish_reason - index title: ChatCompletionStreamResponseChoicesItem type: object x-ddls-inline: true ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError VoiceIdsOrCustomVoiceInline: properties: id: type: string title: Id description: The custom voice ID, e.g. `voice_1234`. x-order: 0 type: object required: - id title: VoiceIdsOrCustomVoiceInline description: |- Custom voice reference. Fields: - id (required): str x-ddls-inline: true FunctionParameters: additionalProperties: true type: object title: FunctionParameters description: >- The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list. ChatCompletionRequestMessageContentPartText: properties: type: type: string const: text title: Type description: The type of the content part. x-order: 0 text: type: string title: Text description: The text content. x-order: 1 type: object required: - type - text title: ChatCompletionRequestMessageContentPartText description: |- Learn about [text inputs](/docs/guides/text-generation). Fields: - type (required): Literal["text"] - text (required): str ChatCompletionRequestMessageContentPartImage: properties: type: type: string const: image_url title: Type description: The type of the content part. x-order: 0 image_url: properties: url: type: string minLength: 1 format: uri title: Url description: Either a URL of the image or the base64 encoded image data. x-order: 0 detail: type: string enum: - auto - low - high title: Detail description: >- Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision#low-or-high-fidelity-image-understanding). default: auto x-order: 1 type: object required: - url description: |- Schema for ImageUrl. Fields: - url (required): AnyUrl - detail (optional): Literal["auto", "low", "high"] type: object required: - type - image_url title: ChatCompletionRequestMessageContentPartImage description: |- Learn about [image inputs](/docs/guides/vision). Fields: - type (required): Literal["image_url"] - image_url (required): ImageUrl ChatCompletionRequestMessageContentPartAudio: properties: type: type: string const: input_audio title: Type description: The type of the content part. Always `input_audio`. x-order: 0 input_audio: properties: data: type: string title: Data description: Base64 encoded audio data. x-order: 0 format: type: string enum: - wav - mp3 title: Format description: >- The format of the encoded audio data. Currently supports "wav" and "mp3". x-order: 1 type: object required: - data - format description: |- Schema for InputAudio. Fields: - data (required): str - format (required): Literal["wav", "mp3"] type: object required: - type - input_audio title: ChatCompletionRequestMessageContentPartAudio description: |- Learn about [audio inputs](/docs/guides/audio). Fields: - type (required): Literal["input_audio"] - input_audio (required): InputAudio ChatCompletionRequestMessageContentPartFile: properties: type: type: string const: file title: Type description: The type of the content part. Always `file`. x-order: 0 file: properties: filename: type: string title: Filename description: >- The name of the file, used when passing the file to the model as a string. x-order: 0 file_data: type: string title: File Data description: >- The base64 encoded file data, used when passing the file to the model as a string. x-order: 1 file_id: type: string title: File Id description: The ID of an uploaded file to use as input. x-order: 2 type: object description: |- Schema for File. Fields: - filename (optional): str - file_data (optional): str - file_id (optional): str type: object required: - type - file title: ChatCompletionRequestMessageContentPartFile description: |- Learn about [file inputs](/docs/guides/text) for text generation. Fields: - type (required): Literal["file"] - file (required): File ChatCompletionRequestMessageContentPartRefusal: properties: type: type: string const: refusal title: Type description: The type of the content part. x-order: 0 refusal: type: string title: Refusal description: The refusal message generated by the model. x-order: 1 type: object required: - type - refusal title: ChatCompletionRequestMessageContentPartRefusal description: |- Schema for ChatCompletionRequestMessageContentPartRefusal. Fields: - type (required): Literal["refusal"] - refusal (required): str Audio: properties: id: type: string title: Id description: Unique identifier for a previous audio response from the model. x-order: 0 type: object required: - id title: Audio description: |- Data about a previous audio response from the model. [Learn more](/docs/guides/audio). Fields: - id (required): str x-ddls-inline: true ChatCompletionMessageToolCall: properties: id: type: string title: Id description: The ID of the tool call. x-order: 0 type: type: string const: function title: Type description: The type of the tool. Currently, only `function` is supported. x-order: 1 function: properties: name: type: string title: Name description: The name of the function to call. x-order: 0 arguments: type: string title: Arguments description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. x-order: 1 type: object required: - name - arguments description: |- The function that the model called. Fields: - name (required): str - arguments (required): str thought_signature: anyOf: - type: string - type: 'null' title: Thought Signature description: >- Opaque signature for thought continuity in multi-turn tool use (Google-specific, base64 encoded) type: object required: - id - type - function title: ChatCompletionMessageToolCall description: |- A call to a function tool created by the model. Fields: - id (required): str - type (required): Literal["function"] - function (required): ChatCompletionMessageToolCallFunction - thought_signature (optional): str ChatCompletionMessageCustomToolCall: properties: id: type: string title: Id description: The ID of the tool call. x-order: 0 type: type: string const: custom title: Type description: The type of the tool. Always `custom`. x-order: 1 custom: properties: name: type: string title: Name description: The name of the custom tool to call. x-order: 0 input: type: string title: Input description: The input for the custom tool call generated by the model. x-order: 1 type: object required: - name - input description: |- The custom tool that the model called. Fields: - name (required): str - input (required): str type: object required: - id - type - custom title: ChatCompletionMessageCustomToolCall description: |- A call to a custom tool created by the model. Fields: - id (required): str - type (required): Literal["custom"] - custom (required): ChatCompletionMessageCustomToolCallCustom FunctionCall: properties: arguments: type: string title: Arguments description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. x-order: 0 name: type: string title: Name description: The name of the function to call. x-order: 1 type: object required: - arguments - name title: FunctionCall description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. Fields: - arguments (required): str - name (required): str x-ddls-inline: true ModelId: type: string title: ModelId description: >- Model identifier string (e.g., 'openai/gpt-5', 'anthropic/claude-3-5-sonnet'). x-stainless-variantName: ModelId DedalusModel: properties: model: type: string title: Model description: >- Model identifier with provider prefix (e.g., 'openai/gpt-5', 'anthropic/claude-3-5-sonnet'). settings: anyOf: - $ref: '#/components/schemas/ModelSettings' - type: 'null' description: >- Optional default generation settings (e.g., temperature, max_tokens) applied when this model is selected. additionalProperties: false type: object required: - model title: DedalusModel description: |- Structured model selection entry used in request payloads. Supports OpenAI-style semantics (string model id) while enabling optional per-model default settings for Dedalus multi-model routing. JSONSchema: properties: description: type: string title: Description description: >- A description of what the response format is for, used by the model to determine how to respond in the format. x-order: 0 name: type: string title: Name 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. x-order: 1 schema: $ref: '#/components/schemas/ResponseFormatJsonSchemaSchema' x-order: 2 strict: anyOf: - type: boolean - type: 'null' title: Strict 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`. To learn more, read the [Structured Outputs guide](/docs/guides/structured-outputs). default: false x-order: 3 type: object required: - name title: JSONSchema description: |- Structured Outputs configuration options, including a JSON Schema. Fields: - description (optional): str - name (required): str - schema (optional): ResponseFormatJsonSchemaSchema - strict (optional): bool | None x-ddls-inline: true Function: properties: name: type: string title: Name description: The name of the function to call. x-order: 0 type: object required: - name title: Function description: |- Schema for Function. Fields: - name (required): str x-ddls-inline: true ChatCompletionResponseMessage: properties: content: anyOf: - type: string - type: 'null' title: Content description: The contents of the message. x-order: 0 refusal: anyOf: - type: string - type: 'null' title: Refusal description: The refusal message generated by the model. x-order: 1 tool_calls: items: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageToolCall' - $ref: '#/components/schemas/ChatCompletionMessageCustomToolCall' discriminator: propertyName: type mapping: custom: $ref: '#/components/schemas/ChatCompletionMessageCustomToolCall' function: $ref: '#/components/schemas/ChatCompletionMessageToolCall' type: array title: Tool Calls description: The tool calls generated by the model, such as function calls. x-order: 2 annotations: items: properties: type: type: string const: url_citation title: Type description: The type of the URL citation. Always `url_citation`. x-order: 0 url_citation: properties: end_index: type: integer title: End Index description: >- The index of the last character of the URL citation in the message. x-order: 0 start_index: type: integer title: Start Index description: >- The index of the first character of the URL citation in the message. x-order: 1 url: type: string title: Url description: The URL of the web resource. x-order: 2 title: type: string title: Title description: The title of the web resource. x-order: 3 type: object required: - end_index - start_index - url - title description: |- A URL citation when using web search. Fields: - end_index (required): int - start_index (required): int - url (required): str - title (required): str type: object required: - type - url_citation description: |- A URL citation when using web search. Fields: - type (required): Literal["url_citation"] - url_citation (required): UrlCitation type: array title: Annotations description: |- Annotations for the message, when applicable, as when using the [web search tool](/docs/guides/tools-web-search?api-mode=chat). x-order: 3 role: type: string const: assistant title: Role description: The role of the author of this message. x-order: 4 function_call: properties: arguments: type: string title: Arguments description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. x-order: 0 name: type: string title: Name description: The name of the function to call. x-order: 1 type: object required: - arguments - name description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. Fields: - arguments (required): str - name (required): str audio: anyOf: - properties: id: type: string title: Id description: Unique identifier for this audio response. x-order: 0 expires_at: type: integer title: Expires At description: >- The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations. x-order: 1 data: type: string title: Data description: >- Base64 encoded audio bytes generated by the model, in the format specified in the request. x-order: 2 transcript: type: string title: Transcript description: Transcript of the audio generated by the model. x-order: 3 type: object required: - id - expires_at - data - transcript description: >- If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](/docs/guides/audio). Fields: - id (required): str - expires_at (required): int - data (required): str - transcript (required): str - type: 'null' description: >- If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](/docs/guides/audio). x-order: 6 type: object required: - content - refusal - role title: ChatCompletionResponseMessage description: |- A chat completion message generated by the model. Fields: - content (required): str | None - refusal (required): str | None - tool_calls (optional): ChatCompletionMessageToolCalls - annotations (optional): list[AnnotationsItem] - role (required): Literal["assistant"] - function_call (optional): ChatCompletionResponseMessageFunctionCall - audio (optional): ChatCompletionResponseMessageAudio | None ChoiceLogprobs: properties: content: anyOf: - items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' type: array - type: 'null' title: Content description: A list of message content tokens with log probability information. x-order: 0 refusal: anyOf: - items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' type: array - type: 'null' title: Refusal description: A list of message refusal tokens with log probability information. x-order: 1 type: object title: ChoiceLogprobs description: Log probability information for the choice. x-ddls-inline: true CompletionTokensDetails: properties: accepted_prediction_tokens: type: integer title: Accepted Prediction Tokens description: |- When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion. default: 0 x-order: 0 audio_tokens: type: integer title: Audio Tokens description: Audio input tokens generated by the model. default: 0 x-order: 1 reasoning_tokens: type: integer title: Reasoning Tokens description: Tokens generated by the model for reasoning. default: 0 x-order: 2 rejected_prediction_tokens: type: integer title: Rejected Prediction Tokens description: >- When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits. default: 0 x-order: 3 type: object title: CompletionTokensDetails description: |- Breakdown of tokens used in a completion. Fields: - accepted_prediction_tokens (optional): int - audio_tokens (optional): int - reasoning_tokens (optional): int - rejected_prediction_tokens (optional): int x-ddls-inline: true PromptTokensDetails: properties: audio_tokens: type: integer title: Audio Tokens description: Audio input tokens present in the prompt. default: 0 x-order: 0 cached_tokens: type: integer title: Cached Tokens description: Cached tokens present in the prompt. default: 0 x-order: 1 type: object title: PromptTokensDetails description: |- Breakdown of tokens used in the prompt. Fields: - audio_tokens (optional): int - cached_tokens (optional): int x-ddls-inline: true ChatCompletionStreamResponseDelta: description: >- A chat completion delta generated by streamed model responses. Fields: - content (optional): str | None - function_call (optional): ChatCompletionStreamResponseDeltaFunctionCall - tool_calls (optional): list[ChatCompletionMessageToolCallChunk] - role (optional): Literal["developer", "system", "user", "assistant", "tool"] - refusal (optional): str | None properties: content: anyOf: - type: string - type: 'null' default: null description: The contents of the chunk message. title: Content x-order: 0 function_call: description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. Fields: - arguments (optional): str - name (optional): str properties: arguments: default: null description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. title: Arguments type: string x-order: 0 name: default: null description: The name of the function to call. title: Name type: string x-order: 1 type: object tool_calls: default: null items: $ref: '#/components/schemas/ChatCompletionMessageToolCallChunk' title: Tool Calls type: array x-order: 2 role: default: null description: The role of the author of this message. enum: - developer - system - user - assistant - tool title: Role type: string x-order: 3 refusal: anyOf: - type: string - type: 'null' default: null description: The refusal message generated by the model. title: Refusal x-order: 4 title: ChatCompletionStreamResponseDelta type: object ChatCompletionStreamResponseChoicesItemLogprobs: description: |- Log probability information for the choice. Fields: - content (required): list[ChatCompletionTokenLogprob] - refusal (required): list[ChatCompletionTokenLogprob] properties: content: anyOf: - items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' type: array - type: 'null' title: Content description: A list of message content tokens with log probability information. x-order: 0 refusal: anyOf: - items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' type: array - type: 'null' title: Refusal description: A list of message refusal tokens with log probability information. x-order: 1 required: - content - refusal title: ChatCompletionStreamResponseChoicesItemLogprobs type: object x-ddls-inline: true ModelSettings: properties: temperature: anyOf: - type: number - type: 'null' title: Temperature top_p: anyOf: - type: number - type: 'null' title: Top P frequency_penalty: anyOf: - type: number - type: 'null' title: Frequency Penalty presence_penalty: anyOf: - type: number - type: 'null' title: Presence Penalty stop: anyOf: - type: string - items: type: string type: array - type: 'null' title: Stop seed: anyOf: - type: integer - type: 'null' title: Seed logit_bias: anyOf: - additionalProperties: type: integer type: object - type: 'null' title: Logit Bias logprobs: anyOf: - type: boolean - type: 'null' title: Logprobs top_logprobs: anyOf: - type: integer - type: 'null' title: Top Logprobs 'n': anyOf: - type: integer - type: 'null' title: 'N' user: anyOf: - type: string - type: 'null' title: User response_format: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' stream: anyOf: - type: boolean - type: 'null' title: Stream stream_options: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' audio: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' service_tier: anyOf: - type: string - type: 'null' title: Service Tier prediction: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' tool_choice: anyOf: - $ref: '#/components/schemas/ToolChoice' - type: 'null' parallel_tool_calls: anyOf: - type: boolean - type: 'null' title: Parallel Tool Calls truncation: anyOf: - type: string enum: - auto - disabled - type: 'null' title: Truncation max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens max_completion_tokens: anyOf: - type: integer - type: 'null' title: Max Completion Tokens reasoning: anyOf: - $ref: '#/components/schemas/Reasoning' - type: 'null' reasoning_effort: anyOf: - type: string - type: 'null' title: Reasoning Effort metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata store: anyOf: - type: boolean - type: 'null' title: Store include_usage: anyOf: - type: boolean - type: 'null' title: Include Usage timeout: anyOf: - type: number - type: 'null' title: Timeout prompt_cache_key: anyOf: - type: string - type: 'null' title: Prompt Cache Key safety_identifier: anyOf: - type: string - type: 'null' title: Safety Identifier verbosity: anyOf: - type: string - type: 'null' title: Verbosity web_search_options: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' extra_query: anyOf: - $ref: '#/components/schemas/QueryParams' - type: 'null' extra_headers: anyOf: - $ref: '#/components/schemas/HeaderParams' - type: 'null' extra_args: anyOf: - additionalProperties: true type: object - type: 'null' title: Extra Args attributes: additionalProperties: true type: object title: Attributes voice: anyOf: - type: string - type: 'null' title: Voice modalities: anyOf: - items: type: string type: array - type: 'null' title: Modalities input_audio_format: anyOf: - type: string - type: 'null' title: Input Audio Format output_audio_format: anyOf: - type: string - type: 'null' title: Output Audio Format input_audio_transcription: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' turn_detection: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' thinking: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' top_k: anyOf: - type: integer - type: 'null' title: Top K generation_config: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' system_instruction: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' safety_settings: anyOf: - items: $ref: '#/components/schemas/JSONObject' type: array - type: 'null' title: Safety Settings tool_config: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' search_parameters: anyOf: - $ref: '#/components/schemas/JSONObject' - type: 'null' deferred: anyOf: - type: boolean - type: 'null' title: Deferred structured_output: anyOf: - {} - type: 'null' title: Structured Output x-stainless-any: true type: object title: ModelSettings ResponseFormatJsonSchemaSchema: additionalProperties: true type: object title: ResponseFormatJsonSchemaSchema description: |- The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). ChatCompletionTokenLogprob: properties: token: type: string title: Token description: The token. x-order: 0 logprob: type: number title: Logprob description: >- The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. x-order: 1 bytes: anyOf: - items: type: integer type: array - type: 'null' title: Bytes description: >- A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. x-order: 2 top_logprobs: items: properties: token: type: string title: Token description: The token. x-order: 0 logprob: type: number title: Logprob description: >- The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. x-order: 1 bytes: anyOf: - items: type: integer type: array - type: 'null' title: Bytes description: >- A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. x-order: 2 type: object required: - token - logprob - bytes description: Token and its log probability. type: array title: Top Logprobs description: >- List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. x-order: 3 type: object required: - token - logprob - bytes - top_logprobs title: ChatCompletionTokenLogprob description: Token log probability information. ChatCompletionMessageToolCallChunk: description: |- Schema for ChatCompletionMessageToolCallChunk. Fields: - index (required): int - id (optional): str - type (optional): Literal["function"] - function (optional): ChatCompletionMessageToolCallChunkFunction properties: index: title: Index type: integer x-order: 0 id: default: null description: The ID of the tool call. title: Id type: string x-order: 1 type: const: function default: function description: The type of the tool. Currently, only `function` is supported. title: Type type: string x-order: 2 function: description: |- Schema for ChatCompletionMessageToolCallChunkFunction. Fields: - name (optional): str - arguments (optional): str properties: name: default: null description: The name of the function to call. title: Name type: string x-order: 0 arguments: default: null description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. title: Arguments type: string x-order: 1 type: object required: - index title: ChatCompletionMessageToolCallChunk type: object ToolChoice: anyOf: - type: string enum: - auto - required - none - type: string - additionalProperties: true type: object - $ref: '#/components/schemas/MCPToolChoice' - type: 'null' Reasoning: properties: effort: anyOf: - type: string enum: - none - minimal - low - medium - high - xhigh - type: 'null' title: Effort generate_summary: anyOf: - type: string enum: - auto - concise - detailed - type: 'null' title: Generate Summary summary: anyOf: - type: string enum: - auto - concise - detailed - type: 'null' title: Summary additionalProperties: true type: object title: Reasoning description: |- **gpt-5 and o-series models only** Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning). QueryParams: additionalProperties: true type: object HeaderParams: additionalProperties: type: string type: object MCPToolChoice: properties: server_label: type: string title: Server Label name: type: string title: Name type: object required: - server_label - name title: MCPToolChoice securitySchemes: Bearer: type: http scheme: bearer ````