> ## Documentation Index > Fetch the complete documentation index at: https://docs.llmrouter.app/llms.txt > Use this file to discover all available pages before exploring further. # Create Response (OpenAI Responses API) > Creates a response using the new OpenAI Responses API format. Often used by agentic tools (like OpenAI Codex or O-series models) for multi-step reasoning and structured outputs. Passes through all native parameters. ## OpenAPI ````yaml /api-reference/openapi.json post /responses openapi: 3.1.0 info: title: LLM Router API description: >- Intelligent AI Gateway with smart routing, Skills, Zero Data Retention, and cost optimization. Fully compatible with the OpenAI API. version: 1.0.0 contact: name: LLM Router Support url: https://docs.llmrouter.app servers: - url: https://api.llmrouter.app/v1 description: Production Server security: - bearerAuth: [] paths: /responses: post: tags: - Responses summary: Create Response (OpenAI Responses API) description: >- Creates a response using the new OpenAI Responses API format. Often used by agentic tools (like OpenAI Codex or O-series models) for multi-step reasoning and structured outputs. Passes through all native parameters. requestBody: description: Responses API request parameters required: true content: application/json: schema: $ref: '#/components/schemas/ResponseAPIRequest' responses: '200': description: Successful Response generation content: application/json: schema: $ref: '#/components/schemas/ResponseAPIResult' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ResponseAPIRequest: type: object required: - model - input properties: model: type: string description: ID of the model to use (e.g., openai/o3) input: type: array description: The input conversation sequence. items: $ref: '#/components/schemas/Message' gateway: $ref: '#/components/schemas/GatewayConfig' additionalProperties: true description: >- Accepts any additional properties supported by the upstream Responses API (e.g., reasoning_effort, tools, instructions). ResponseAPIResult: type: object properties: id: type: string description: Unique identifier for the response example: gen_8f90f62a-b4c1-4482-94b8-0132c42a6afb object: type: string example: response created_at: type: integer description: Unix timestamp when the response was created status: type: string enum: - completed - in_progress - failed - incomplete example: completed completed_at: type: - integer - 'null' nullable: true incomplete_details: type: - object - 'null' nullable: true error: type: - object - 'null' nullable: true output: type: array items: type: object properties: type: type: string example: message id: type: string status: type: string role: type: string example: assistant content: type: array items: type: object properties: type: type: string example: output_text text: type: string annotations: type: array items: type: object logprobs: type: array items: type: object usage: type: object properties: input_tokens: type: integer output_tokens: type: integer total_tokens: type: integer planning_usage_details: allOf: - $ref: '#/components/schemas/Usage' nullable: true description: >- The cost breakdown for the planning/reasoning phase of the request (if applicable). Can be null. model: type: string temperature: type: number top_p: type: number max_output_tokens: type: - integer - 'null' nullable: true presence_penalty: type: number frequency_penalty: type: number tools: type: array items: type: object tool_choice: type: string example: auto text: type: object properties: format: type: object properties: type: type: string example: text output_text: type: string description: Concatenated output text for convenience required: - id - object - created_at - status - model - output - usage additionalProperties: true Error: type: object required: - error properties: error: type: object properties: message: type: string code: type: string nullable: true enum: - UNAUTHORIZED - FORBIDDEN - INTERNAL_SERVER_ERROR - BAD_REQUEST - USER_NOT_FOUND - MODEL_NOT_FOUND - EXCEEDS_MONTHLY_LIMIT - INVALID_GATEWAY_SETTINGS - TOO_MANY_REQUESTS description: Error code (can be null or undefined) additionalProperties: true additionalProperties: true Message: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool - function content: type: - string - array description: >- The contents of the message. Can be a string or an array of multimodal content parts. name: type: string additionalProperties: true GatewayConfig: type: object description: Custom LLM Router configurations injected into the request. properties: zdr: type: boolean description: >- If true, enforces Zero Data Retention by only routing to non-logging providers. order: type: array items: type: string description: Priority list of provider slugs for fallbacks. only: type: array items: type: string description: Strict whitelist of allowed provider slugs. planningTriggerScore: type: number minimum: 0 maximum: 1 description: Threshold to trigger the Chain-of-Thought planning model. imageGenerationModel: type: string description: Fallback model used if the request requires an image output. tags: type: array description: Intent-based routing rules. items: type: object required: - name - description - models properties: name: type: string description: type: string models: type: array items: type: string skills: type: object required: - skillIds properties: skillIds: type: array items: type: string enableAutoSearch: type: boolean default: false chatHistoryCompression: type: object properties: enabled: type: boolean default: false score: type: number minimum: 0 maximum: 1 default: 0.6 mediaOptimization: type: boolean default: false toolOptimization: type: object properties: enabled: type: boolean default: false acceptScore: type: number minimum: 0 maximum: 1 default: 0.5 alwaysInclude: type: array items: type: string redact: type: object description: PII redaction configuration properties: email: type: boolean phone: type: boolean ip: type: boolean uuid: type: boolean token: type: boolean credit_card: type: boolean iban: type: boolean ssn: type: boolean mac: type: boolean custom: type: array items: type: string Usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer cost: type: integer description: Total model usage cost (excluding routing fees) securitySchemes: bearerAuth: type: http scheme: bearer description: LLM Router API Key (e.g., sk-llmr-...) ````