Wombo Chat API

openapi: 3.1.0
info:
  title: w.ai Inference Chat API
  version: v1
  description: OpenAI-compatible HTTP API for on-demand AI inference on the w.ai decentralized compute network (WOMBO). Provides model discovery, text and vision-language chat completions with tool calling and streaming, text-to-image generation and editing, and object detection / segmentation over images and video. Faithfully generated by the API Evangelist enrichment pipeline from the public documentation at https://docs.w.ai/w.ai-api/api-features ; not an official provider-published specification.
  contact:
    name: w.ai (WOMBO)
    url: https://docs.w.ai/
  x-provenance:
    generated: '2026-07-21'
    method: generated
    source: https://docs.w.ai/w.ai-api/api-features.md
servers:
- url: https://api.w.ai/v1
  description: Production
security:
- bearerAuth: []
tags:
- name: Chat
  description: Text and vision-language chat completions
paths:
  /chat/completions:
    post:
      tags:
      - Chat
      operationId: createChatCompletion
      summary: Create a chat completion
      description: Create a text or vision-language chat completion. Supports multimodal image_url content, tool/function calling and server-sent streaming.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: A chat completion (or an SSE stream when stream=true).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  schemas:
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        model:
          type: string
        choices:
          type: array
          items:
            type: object
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          example: llama-3.2-1b-4bit
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        max_tokens:
          type: integer
          minimum: 1
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1.0
        top_p:
          type: number
          minimum: 0
          maximum: 1
        frequency_penalty:
          type: number
          minimum: -2
          maximum: 2
        presence_penalty:
          type: number
          minimum: -2
          maximum: 2
        stream:
          type: boolean
          default: false
        response_format:
          type: object
          example:
            type: json_object
        tools:
          type: array
          items:
            type: object
        tool_choice:
          description: none, auto, required, or a specific function object.
          oneOf:
          - type: string
            enum:
            - none
            - auto
            - required
          - type: object
    ChatMessage:
      type: object
      required:
      - role
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          description: A string, or an array of content parts (text / image_url).
          oneOf:
          - type: string
          - type: array
            items:
              type: object
        tool_calls:
          type: array
          items:
            type: object
        tool_call_id:
          type: string
  responses:
    RateLimited:
      description: Too many requests.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadRequest:
      description: Invalid request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: wsk
      description: 'Developer API key issued at https://app.w.ai/developers/keys , sent as `Authorization: Bearer wsk-...`.'