> ## Documentation Index
> Fetch the complete documentation index at: https://docs.linkmodel.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Responses

> Use this endpoint when your client requires OpenAI's Responses API wire
protocol, such as Codex with `wire_api = "responses"`.

This endpoint is intended for GPT-series LinkModel chat models. The
request body, supported `model` values, streaming flag, and optional tool
fields are defined in the schema below.
Official protocol reference: [OpenAI Responses API](https://platform.openai.com/docs/api-reference/responses/create).




## OpenAPI

````yaml /openapi/chat/_openai-responses.yaml post /responses
openapi: 3.0.3
info:
  title: OpenAI Responses
  version: 1.0.0
  description: OpenAI-compatible Responses endpoint for LinkModel GPT-series chat models.
servers:
  - url: https://api.linkmodel.ai/v1
    description: Production
security:
  - bearerAuth: []
tags:
  - name: chat
paths:
  /responses:
    post:
      tags:
        - chat
      summary: OpenAI Responses
      description: >
        Use this endpoint when your client requires OpenAI's Responses API wire

        protocol, such as Codex with `wire_api = "responses"`.


        This endpoint is intended for GPT-series LinkModel chat models. The

        request body, supported `model` values, streaming flag, and optional
        tool

        fields are defined in the schema below.

        Official protocol reference: [OpenAI Responses
        API](https://platform.openai.com/docs/api-reference/responses/create).
      operationId: openai-responses
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              properties:
                model:
                  type: string
                  description: >-
                    ID of the GPT-series chat model to use. See
                    [Models](/models) for the current model list, pricing, and
                    endpoint support.
                  example: gpt-5.3-codex
                input:
                  description: Text input or Responses API input items.
                  oneOf:
                    - type: string
                      example: 'Reply with exactly one word: pong'
                    - type: array
                      items:
                        type: object
                        additionalProperties: true
                instructions:
                  type: string
                  description: Optional system or developer instructions.
                max_output_tokens:
                  type: integer
                  description: Maximum number of output tokens to generate.
                  example: 1024
                stream:
                  type: boolean
                  description: If true, stream typed Responses API events over SSE.
                  default: false
                reasoning:
                  type: object
                  description: >-
                    Optional reasoning controls, such as `{ "effort": "none" }`.
                    Support can vary by selected model and provider.
                  additionalProperties: true
                text:
                  type: object
                  description: Optional text output controls.
                  additionalProperties: true
                temperature:
                  type: number
                  description: Sampling temperature.
                  minimum: 0
                  maximum: 2
                  example: 1
                top_p:
                  type: number
                  description: Nucleus sampling parameter.
                  minimum: 0
                  maximum: 1
                  example: 1
                previous_response_id:
                  type: string
                  description: >-
                    Optional previous response ID for multi-turn clients that
                    use response chaining. Support can vary by selected model
                    and provider.
                store:
                  type: boolean
                  description: >-
                    Whether the response should be stored when supported by the
                    provider. Support can vary by selected model and provider.
                metadata:
                  type: object
                  description: >-
                    Optional metadata attached to the response. Support can vary
                    by selected model and provider.
                  additionalProperties: true
                tools:
                  type: array
                  description: >-
                    Optional Responses API tools. Support can vary by selected
                    model and provider.
                  items:
                    type: object
                    additionalProperties: true
                tool_choice:
                  description: >-
                    Tool selection strategy. Support can vary by selected model
                    and provider.
                  oneOf:
                    - type: string
                      enum:
                        - auto
                        - none
                    - type: object
                      additionalProperties: true
      responses:
        '200':
          description: Responses API result.
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                    example: resp_abc123
                  object:
                    type: string
                    example: response
                  status:
                    type: string
                    example: completed
                  model:
                    type: string
                    example: gpt-5.3-codex
                  output:
                    type: array
                    items:
                      type: object
                      additionalProperties: true
                  output_text:
                    type: string
                    description: Flattened text output when available.
                    example: pong
                  usage:
                    type: object
                    additionalProperties: true
            text/event-stream:
              schema:
                type: string
                description: >
                  SSE stream of typed Responses API events. Typical events
                  include

                  `response.created`, `response.in_progress`,
                  `response.output_text.delta`,

                  `response.output_item.done`, and `response.completed`.
        '400':
          description: Bad request -- invalid or missing parameter.
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                    example: 400
                  msg:
                    type: string
                    example: model is required
                  request_id:
                    type: string
        '401':
          description: Unauthorized -- missing or invalid API key.
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                    example: 401
                  msg:
                    type: string
                    example: unauthorized
                  request_id:
                    type: string
        '500':
          description: Internal server error.
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                    example: 500
                  msg:
                    type: string
                  request_id:
                    type: string
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key

````