Targon Images API

openapi: 3.0.1
info:
  title: Targon Chat Images API
  description: 'OpenAI-compatible REST API for Targon, the decentralized AI inference platform operated as Bittensor Subnet 4 by Manifold Labs. Inference is produced by a marketplace of miners running OpenAI-compliant endpoints and verified by validators. The public surface follows the OpenAI API shape: chat completions, legacy text completions, model listing, image generation, and search. All requests are authenticated with a Bearer API key.'
  termsOfService: https://targon.com
  contact:
    name: Targon Support
    url: https://docs.targon.com
  version: '1.0'
servers:
- url: https://api.targon.com/v1
  description: Targon OpenAI-compatible inference base URL.
security:
- bearerAuth: []
tags:
- name: Images
  description: Image generation from a text prompt.
paths:
  /images/generations:
    post:
      operationId: createImage
      tags:
      - Images
      summary: Create an image
      description: Generates one or more images from a text prompt using an image model served across the Subnet 4 miner marketplace. Compatible with the OpenAI Images API.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateImageRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImagesResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  responses:
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    RateLimited:
      description: Too many requests.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    CreateImageRequest:
      type: object
      required:
      - prompt
      properties:
        model:
          type: string
          description: The image model to use.
        prompt:
          type: string
          description: A text description of the desired image.
        n:
          type: integer
          default: 1
          description: The number of images to generate.
        size:
          type: string
          description: The size of the generated images.
          example: 1024x1024
        response_format:
          type: string
          enum:
          - url
          - b64_json
          default: url
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string
    ImagesResponse:
      type: object
      properties:
        created:
          type: integer
        data:
          type: array
          items:
            type: object
            properties:
              url:
                type: string
              b64_json:
                type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Targon API key passed as a Bearer token in the Authorization header: `Authorization: Bearer $TARGON_API_KEY`.'