RightNow AI Responses API

openapi: 3.1.0
info:
  title: RunInfra Audio Responses API
  description: OpenAI-compatible HTTP API for verified RunInfra inference deployments.
  version: '2026-04-24'
  contact:
    name: RunInfra support
    email: jaber@runinfra.ai
    url: https://runinfra.ai/contact
servers:
- url: https://api.runinfra.ai/v1
  description: Production
security:
- bearerAuth: []
tags:
- name: Responses
paths:
  /responses:
    post:
      operationId: createResponse
      summary: Create response
      description: Responses-shaped chat-completions compatibility adapter for compatible LLM and vision-language deployments. Does not implement full state, include, reasoning, hosted-tool, conversation-item, or background-job semantics.
      tags:
      - Responses
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ResponsesRequest'
      responses:
        '200':
          description: Response object or SSE stream if stream=true
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResponsesResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ResponsesEvent'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          $ref: '#/components/responses/Conflict'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          $ref: '#/components/responses/InternalServerError'
        '502':
          $ref: '#/components/responses/BadGateway'
        '503':
          $ref: '#/components/responses/Unavailable'
        '504':
          $ref: '#/components/responses/GatewayTimeout'
components:
  responses:
    RateLimited:
      description: Rate limit exceeded
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait before retrying
        X-RateLimit-Remaining:
          schema:
            type: integer
          description: Remaining requests in the window
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: Model or deployment not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    GatewayTimeout:
      description: Gateway timeout
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    UnprocessableEntity:
      description: Request cannot be replayed or processed safely
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    PaymentRequired:
      description: Insufficient credits
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    InternalServerError:
      description: Unexpected gateway error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadGateway:
      description: Upstream serving backend transient failure
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Forbidden:
      description: Key scope mismatch or plan limit exceeded
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unavailable:
      description: Endpoint stopped, provisioning, or at capacity
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Conflict:
      description: Idempotency conflict
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadRequest:
      description: Malformed request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    ResponsesEvent:
      type: object
      properties:
        type:
          type: string
          example: response.output_text.delta
        delta:
          type: string
        response:
          $ref: '#/components/schemas/ResponsesResponse'
    Error:
      type: object
      properties:
        error:
          type: object
          required:
          - message
          - type
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type: string
              nullable: true
            code:
              type: string
              nullable: true
    ResponsesResponse:
      type: object
      required:
      - id
      - object
      - model
      properties:
        id:
          type: string
          example: resp_abc123
        object:
          type: string
          example: response
        created_at:
          type: integer
        model:
          type: string
        output_text:
          type: string
          description: Convenience text extracted from output content when available.
        output:
          type: array
          items:
            type: object
        usage:
          $ref: '#/components/schemas/Usage'
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
    Tool:
      type: object
      required:
      - type
      - function
      properties:
        type:
          type: string
          enum:
          - function
        function:
          type: object
          required:
          - name
          properties:
            name:
              type: string
            description:
              type: string
            parameters:
              type: object
              description: JSON Schema
    ResponseFormat:
      oneOf:
      - type: object
        properties:
          type:
            type: string
            enum:
            - text
      - type: object
        properties:
          type:
            type: string
            enum:
            - json_object
      - type: object
        required:
        - type
        - json_schema
        properties:
          type:
            type: string
            enum:
            - json_schema
          json_schema:
            type: object
            required:
            - name
            - schema
            properties:
              name:
                type: string
              strict:
                type: boolean
                default: false
              schema:
                type: object
                description: JSON Schema
    ResponsesRequest:
      type: object
      required:
      - model
      - input
      properties:
        model:
          type: string
          example: llama-3.3-70b
        input:
          oneOf:
          - type: string
          - type: array
            items:
              type: object
        instructions:
          type: string
          description: System-level instruction text mapped into a chat system message.
        stream:
          type: boolean
          default: false
          description: When true, the response is a server-sent event stream.
        max_output_tokens:
          type: integer
          minimum: 1
        temperature:
          type: number
          minimum: 0
          maximum: 2
        top_p:
          type: number
          minimum: 0
          maximum: 1
        tools:
          type: array
          items:
            $ref: '#/components/schemas/Tool'
        tool_choice:
          oneOf:
          - type: string
            enum:
            - none
            - auto
            - required
          - type: object
            properties:
              type:
                type: string
                enum:
                - function
              function:
                type: object
                properties:
                  name:
                    type: string
        response_format:
          $ref: '#/components/schemas/ResponseFormat'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: RunInfra API key. Generate at https://runinfra.ai/settings/api-keys