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

# Create a response (Responses API)

> OpenAI Responses API translated onto the same models and billing as chat completions. Accepts a string or array `input` plus optional `instructions`; use `max_output_tokens` for the output limit and `stream: true` for server-sent `response.*` events. Stateless: each call stands alone.



## OpenAPI

````yaml /openapi.json post /v1/responses
openapi: 3.1.0
info:
  title: Refuseless API
  version: 1.0.0
  description: >-
    OpenAI-compatible hosted inference for a named lineup of refusal-removed
    open weights.
servers:
  - url: https://api.refuseless.com
security:
  - bearerAuth: []
paths:
  /v1/responses:
    post:
      tags:
        - Completions
      summary: Create a response (Responses API)
      description: >-
        OpenAI Responses API translated onto the same models and billing as chat
        completions. Accepts a string or array `input` plus optional
        `instructions`; use `max_output_tokens` for the output limit and
        `stream: true` for server-sent `response.*` events. Stateless: each call
        stands alone.
      operationId: createResponse
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ResponseRequest'
            example:
              model: glm-5.3-abliterated
              input: Write a tight system prompt.
              max_output_tokens: 512
      responses:
        '200':
          description: Response object, or event stream when stream=true
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResponseObject'
        '400':
          description: Missing model or input
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
        '402':
          description: Insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
        '404':
          description: Unknown model
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
        '429':
          description: Model busy or warming — honor retry-after
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
        '503':
          description: Gateway or model unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError'
components:
  schemas:
    ResponseRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          examples:
            - glm-5.3-abliterated
        input:
          description: String prompt or array of input items / messages.
        instructions:
          type: string
          description: System prompt prepended to the input.
        max_output_tokens:
          type: integer
          description: Output limit. Aliases max_completion_tokens, max_tokens.
        max_completion_tokens:
          type: integer
        max_tokens:
          type: integer
        stream:
          type: boolean
          default: false
        temperature:
          type: number
        top_p:
          type: number
        stop:
          description: Stop sequences, where supported.
        tools:
          type: array
          items:
            type: object
            additionalProperties: true
        tool_choice:
          additionalProperties: true
        response_format:
          type: object
          additionalProperties: true
        reasoning_effort:
          type: string
          enum:
            - 'off'
            - low
            - high
            - max
          description: >-
            Model-card reasoning effort. reasoning.effort is the same field. off
            disables reasoning. Omitted requests on a model marked thinking-off
            run with reasoning off. Other models default to low.
      additionalProperties: true
    ResponseObject:
      type: object
      required:
        - id
        - object
        - created_at
        - model
        - status
        - output
        - usage
      properties:
        id:
          type: string
          examples:
            - resp-abc123
        object:
          type: string
          examples:
            - response
        created_at:
          type: integer
        model:
          type: string
        status:
          type: string
          enum:
            - completed
            - incomplete
            - failed
        output:
          type: array
          items:
            type: object
            additionalProperties: true
        usage:
          type: object
          properties:
            input_tokens:
              type: integer
            output_tokens:
              type: integer
            total_tokens:
              type: integer
    ApiError:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          required:
            - code
            - message
            - type
          properties:
            code:
              type: string
              examples:
                - invalid_key
                - insufficient_credits
                - model_not_found
                - model_busy
                - model_warming
                - upstream_error
                - model_unavailable
            message:
              type: string
            type:
              type: string
              examples:
                - api_error
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      x-default: YOUR_API_KEY

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.