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

# Create a response

> OpenAI's Responses API. Supports streaming (usage settled on the terminal response.completed event).



## OpenAPI

````yaml /openapi-inference.json post /responses
openapi: 3.1.0
info:
  title: Omnia Inference API
  description: >-
    OpenAI-compatible inference endpoints: chat completions, embeddings, rerank,
    and the Responses API. Authenticated with a workspace API key
    (sk_sovereign_...).
  version: 1.0.0
servers:
  - url: https://gateway.omnia-voice.com/v1
    description: Production
security:
  - bearerAuth: []
paths:
  /responses:
    post:
      tags:
        - Responses
      summary: Create a response
      description: >-
        OpenAI's Responses API. Supports streaming (usage settled on the
        terminal response.completed event).
      operationId: createResponse
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              properties:
                model:
                  type: string
                  example: Qwen/Qwen3-32B
                input:
                  description: >-
                    The input to respond to — a string or a structured input
                    array.
                instructions:
                  type: string
                  description: System-style instructions for the model.
                stream:
                  type: boolean
                  default: false
                  description: Stream the response as server-sent events.
                temperature:
                  type: number
                top_p:
                  type: number
                max_output_tokens:
                  type: integer
                  description: Maximum output tokens.
                stop:
                  description: Stop sequences.
                seed:
                  type: integer
                response_format:
                  type: object
                text:
                  type: object
                  description: Text/format options.
                tools:
                  type: array
                  items:
                    type: object
                tool_choice: {}
                parallel_tool_calls:
                  type: boolean
                reasoning:
                  type: object
                  description: Reasoning options for reasoning-capable models.
                reasoning_effort:
                  type: string
                metadata:
                  type: object
                user:
                  type: string
      responses:
        '200':
          description: >-
            A response object. Usage is reported as input_tokens /
            output_tokens.
          content:
            application/json:
              schema:
                type: object
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/InsufficientBalance'
        '404':
          $ref: '#/components/responses/ModelNotFound'
components:
  responses:
    BadRequest:
      description: Missing a required field (e.g. model, messages/input/query/documents).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing, malformed, or revoked API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              message: Invalid API key
              type: invalid_request_error
              code: invalid_api_key
    InsufficientBalance:
      description: Your wallet can't cover the request's worst-case cost.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              message: Insufficient balance. Please top up your wallet.
              type: insufficient_quota
              code: insufficient_balance
    ModelNotFound:
      description: The model is not offered (or the id is wrong).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              message: The model 'x' does not exist or is not available.
              type: invalid_request_error
              code: model_not_found
  schemas:
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your workspace API key, e.g. sk_sovereign_..., sent as Authorization:
        Bearer <key>.

````