> ## Documentation Index > Fetch the complete documentation index at: https://docs.corti.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create response > Creates a model response for the given input. This is the OpenAI Responses API. Supports `instructions` (system message equivalent), streaming, tool calling, JSON mode, and multi-turn conversations. When present, reasoning is returned as a structured output item with `type: "reasoning"`, separate from the message output. ## OpenAPI ````yaml /api-reference/corti-models/corti-models-openapi.yml post /responses openapi: 3.0.3 info: title: Corti S1 API description: > OpenAI-compatible and Anthropic-compatible API for Corti's LLM models. ## Available Models | Model | Description | |------|-------------| | `corti-s1` | Full-capability model | | `corti-s1-instant` | Fast variant of corti-s1 | | `corti-s1-mini` | Smaller model | | `corti-s1-mini-instant` | Fast variant of corti-s1-mini | | `corti-s1-embedding` | Embedding model | `-instant` variants are optimized for speed and lower token usage. ## Reasoning Some models return chain-of-thought reasoning in a `reasoning` field (chat completions) or as structured output items with `type: "reasoning"` (responses API). The `-instant` variants do not produce reasoning. | Model | Chat Completions | Anthropic Messages | |-------|:---:|:---:| | `corti-s1` | `reasoning` field present | Text content only | | `corti-s1-instant` | `reasoning: null` | Text content only | | `corti-s1-mini` | `reasoning` field present | Text content only | | `corti-s1-mini-instant` | `reasoning: null` | Text content only | ## Authentication All endpoints require a bearer token issued by Corti. Pass it in the `Authorization` header as `Bearer `. version: 1.0.0 contact: name: Corti AI url: https://corti.app servers: - url: https://ai.eu.corti.app/v1 description: Production (EU) security: - bearerAuth: [] paths: /responses: post: tags: - Responses summary: Create response description: > Creates a model response for the given input. This is the OpenAI Responses API. Supports `instructions` (system message equivalent), streaming, tool calling, JSON mode, and multi-turn conversations. When present, reasoning is returned as a structured output item with `type: "reasoning"`, separate from the message output. operationId: createResponse requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ResponseRequest' examples: Basic: summary: Basic response value: model: corti-s1 input: - role: user content: - type: input_text text: Count from 1 to 5 With Instructions: summary: With system instructions value: model: corti-s1 input: - role: user content: - type: input_text text: Count from 1 to 5 instructions: You are a helpful assistant. Streaming: summary: Streaming response value: model: corti-s1 input: - role: user content: - type: input_text text: Count from 1 to 5 stream: true JSON Mode: summary: Structured JSON output value: model: corti-s1 input: - role: user content: - type: input_text text: >- Return a JSON object with fields name and age for John who is 30. response_format: type: json_object Tool Calling: summary: Function calling value: model: corti-s1 input: - role: user content: - type: input_text text: What is the weather in Copenhagen? tools: - type: function name: get_weather description: Get weather for a city parameters: type: object properties: city: type: string required: - city Multi-turn: summary: Multi-turn via input array value: model: corti-s1 input: - role: user content: - type: input_text text: Count from 1 to 5 - role: assistant content: - type: output_text text: 1, 2, 3, 4, 5 - role: user content: - type: input_text text: Now count from 10 to 15 responses: '200': description: > Successful response. For non-streaming requests, returns a complete response object. For streaming requests, returns Server-Sent Events (SSE) with typed events. content: application/json: schema: $ref: '#/components/schemas/ResponseObject' text/event-stream: schema: $ref: '#/components/schemas/ResponseStreamEvent' '401': description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Response ID not found content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ResponseRequest: type: object required: - model - input properties: model: type: string enum: - corti-s1 - corti-s1-instant - corti-s1-mini - corti-s1-mini-instant default: corti-s1 input: type: array description: > Input messages as an array of message objects. Each message has a `role` and a `content` array of typed parts. items: type: object required: - role - content properties: role: type: string enum: - user - assistant content: type: array items: type: object required: - type - text properties: type: type: string enum: - input_text - output_text description: > `input_text` for user messages, `output_text` for assistant messages in multi-turn conversations. text: type: string description: The text content. instructions: type: string nullable: true description: > System-level instructions. Equivalent to a system message in chat completions. stream: type: boolean default: false description: > If true, returns Server-Sent Events (SSE) with typed events (`response.created`, `response.in_progress`, `response.output_item.added`, `response.output_text.delta`, `response.completed`). temperature: type: number format: float minimum: 0 maximum: 1 default: 1 top_p: type: number format: float default: 0.95 max_output_tokens: type: integer minimum: 1 description: > Maximum output tokens. If exceeded, the response status is `incomplete` with `incomplete_details.reason: "max_output_tokens"`. response_format: type: object properties: type: type: string enum: - json_object required: - type tools: type: array description: Tools the model may call. items: $ref: '#/components/schemas/ResponseFunctionTool' tool_choice: type: string enum: - auto - none default: auto presence_penalty: type: number format: float default: 0 frequency_penalty: type: number format: float default: 0 ResponseObject: type: object properties: id: type: string description: Unique response ID (e.g. `resp_88d5b93fd2e7b7b1`). object: type: string enum: - response created_at: type: integer description: Unix timestamp (seconds). model: type: string description: The model name used for this response. status: type: string enum: - completed - incomplete description: > `incomplete` when max_output_tokens is hit before generation finishes. incomplete_details: type: object nullable: true properties: reason: type: string enum: - max_output_tokens instructions: type: string nullable: true output: type: array description: > Array of output items. May include reasoning items with `type: "reasoning"`, message items with `type: "message"`, and function call items with `type: "function_call"`. items: $ref: '#/components/schemas/ResponseOutputItem' temperature: type: number top_p: type: number tool_choice: type: string tools: type: array max_output_tokens: type: integer previous_response_id: type: string nullable: true usage: $ref: '#/components/schemas/ResponseUsage' service_tier: type: string nullable: true truncation: type: string background: type: boolean parallel_tool_calls: type: boolean max_tool_calls: type: integer nullable: true text: type: string nullable: true top_logprobs: type: integer nullable: true reasoning: type: string nullable: true description: Reasoning is returned in `output[]` items. prompt: type: string nullable: true metadata: type: object nullable: true user: type: string nullable: true presence_penalty: type: number frequency_penalty: type: number kv_transfer_params: type: object nullable: true input_messages: type: array nullable: true output_messages: type: array nullable: true ResponseStreamEvent: type: object description: > SSE events from the Responses API. Each event has a type and sequence number. Event types include: `response.created`, `response.in_progress`, `response.output_item.added`, `response.output_text.delta`, `response.output_item.done`, `response.completed`. properties: type: type: string enum: - response.created - response.in_progress - response.output_item.added - response.output_text.delta - response.output_item.done - response.completed sequence_number: type: integer response: type: object description: The current state of the response object. item: type: object description: The output item (for item events). part: type: object description: The content part (for part events). delta: type: string description: Incremental text (for delta events). Error: type: object required: - error properties: error: type: string description: Error message or object with message. detail: type: string ResponseFunctionTool: type: object required: - type - name - parameters properties: type: type: string enum: - function name: type: string pattern: ^[a-zA-Z0-9_-]+$ maxLength: 64 description: type: string parameters: type: object description: JSON Schema object defining accepted parameters. ResponseOutputItem: oneOf: - title: Message type: object properties: id: type: string type: type: string enum: - message role: type: string enum: - assistant status: type: string enum: - completed phase: type: string nullable: true content: type: array items: type: object properties: text: type: string description: The model's text response. type: type: string enum: - output_text annotations: type: array items: {} logprobs: type: object nullable: true - title: Function Call type: object properties: id: type: string type: type: string enum: - function_call name: type: string description: Function name to call. arguments: type: string description: JSON-encoded function arguments. call_id: type: string description: ID to reference when providing the tool result. namespace: type: string nullable: true status: type: string enum: - completed ResponseUsage: type: object properties: input_tokens: type: integer output_tokens: type: integer total_tokens: type: integer input_tokens_details: type: object properties: cached_tokens: type: integer input_tokens_per_turn: type: array items: {} cached_tokens_per_turn: type: array items: {} output_tokens_details: type: object properties: reasoning_tokens: type: integer tool_output_tokens: type: integer output_tokens_per_turn: type: array items: {} tool_output_tokens_per_turn: type: array items: {} securitySchemes: bearerAuth: type: http scheme: bearer description: | Use a Corti-issued bearer token. ````