Together AI Images API

openapi: 3.2.0
info:
  title: Together Images API
  description: The Together REST API. Please see https://docs.together.ai for more details.
  version: 2.0.0
  termsOfService: https://www.together.ai/terms-of-service
  contact:
    name: Together Support
    url: https://www.together.ai/contact
  license:
    name: MIT
    url: https://github.com/togethercomputer/openapi/blob/main/LICENSE
servers:
- url: https://api.together.ai/v1
security:
- bearerAuth: []
tags:
- name: Images
paths:
  /images/generations:
    post:
      tags:
      - Images
      summary: Create image
      description: Use an image model to generate an image for a given prompt.
      x-codeSamples:
      - lang: Python
        label: Together AI SDK (v2)
        source: "# Docs for v1 can be found by changing the above selector ^\nfrom together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nresponse = client.images.generate(\n    model=\"black-forest-labs/FLUX.1-schnell\",\n    steps=4,\n    prompt=\"A cartoon of an astronaut riding a horse on the moon\",\n)\n\nprint(response.data[0].url)\n"
      - lang: Python
        label: Together AI SDK (v1)
        source: "from together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nresponse = client.images.generate(\n    model=\"black-forest-labs/FLUX.1-schnell\",\n    steps=4,\n    prompt=\"A cartoon of an astronaut riding a horse on the moon\",\n)\n\nprint(response.data[0].url)\n"
      - lang: TypeScript
        label: Together AI SDK (TypeScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst response = await client.images.generate({\n  model: \"black-forest-labs/FLUX.1-schnell\",\n  prompt: \"A cartoon of an astronaut riding a horse on the moon\",\n});\n\nconsole.log(response.data[0].url);\n"
      - lang: JavaScript
        label: Together AI SDK (JavaScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst response = await client.images.generate({\n  model: \"black-forest-labs/FLUX.1-schnell\",\n  prompt: \"A cartoon of an astronaut riding a horse on the moon\",\n});\n\nconsole.log(response.data[0].url);\n"
      - lang: Shell
        label: cURL
        source: "curl -X POST \"https://api.together.ai/v1/images/generations\" \\\n     -H \"Authorization: Bearer $TOGETHER_API_KEY\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\n       \"model\": \"black-forest-labs/FLUX.1-schnell\",\n       \"prompt\": \"A cartoon of an astronaut riding a horse on the moon\"\n     }'\n"
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - prompt
              - model
              properties:
                prompt:
                  type: string
                  description: A description of the desired images. Maximum length varies by model.
                  example: cat floating in space, cinematic
                model:
                  type: string
                  description: 'The model to use for image generation.<br> <br> [See all of Together AI''s image models](https://docs.together.ai/docs/serverless-models#image-models)

                    '
                  example: black-forest-labs/FLUX.1-schnell
                  anyOf:
                  - type: string
                    enum:
                    - black-forest-labs/FLUX.1-schnell-Free
                    - black-forest-labs/FLUX.1-schnell
                    - black-forest-labs/FLUX.1.1-pro
                  - type: string
                steps:
                  type: integer
                  default: 20
                  description: Number of generation steps.
                image_url:
                  type: string
                  description: URL of an image to use for image models that support it.
                seed:
                  type: integer
                  description: Seed used for generation. Can be used to reproduce image generations.
                n:
                  type: integer
                  default: 1
                  description: Number of image results to generate.
                height:
                  type: integer
                  default: 1024
                  description: Height of the image to generate in number of pixels.
                width:
                  type: integer
                  default: 1024
                  description: Width of the image to generate in number of pixels.
                negative_prompt:
                  type: string
                  description: The prompt or prompts not to guide the image generation.
                response_format:
                  type: string
                  description: Format of the image response. Can be either a base64 string or a URL.
                  enum:
                  - base64
                  - url
                guidance_scale:
                  type: number
                  description: Adjusts the alignment of the generated image with the input prompt. Higher values (e.g., 8-10) make the output more faithful to the prompt, while lower values (e.g., 1-5) encourage more creative freedom.
                  default: 3.5
                output_format:
                  type: string
                  description: The format of the image response. Can be either be `jpeg` or `png`. Defaults to `jpeg`.
                  default: jpeg
                  enum:
                  - jpeg
                  - png
                image_loras:
                  description: An array of objects that define LoRAs (Low-Rank Adaptations) to influence the generated image.
                  type: array
                  items:
                    type: object
                    required:
                    - path
                    - scale
                    properties:
                      path:
                        type: string
                        description: The URL of the LoRA to apply (e.g. https://huggingface.co/strangerzonehf/Flux-Midjourney-Mix2-LoRA).
                      scale:
                        type: number
                        description: The strength of the LoRA's influence. Most LoRA's recommend a value of 1.
                reference_images:
                  description: An array of image URLs that guide the overall appearance and style of the generated image. These reference images influence the visual characteristics consistently across the generation.
                  type: array
                  items:
                    type: string
                    description: URL of a reference image to guide the image generation.
                disable_safety_checker:
                  type: boolean
                  description: If true, disables the safety checker for image generation.
      responses:
        '200':
          description: Image generated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageResponse'
components:
  schemas:
    ImageResponseDataB64:
      type: object
      required:
      - index
      - b64_json
      - type
      properties:
        index:
          type: integer
        b64_json:
          type: string
        type:
          type: string
          enum:
          - b64_json
    ImageResponse:
      type: object
      properties:
        id:
          type: string
        model:
          type: string
        object:
          description: The object type, which is always `list`.
          const: list
        data:
          type: array
          items:
            oneOf:
            - $ref: '#/components/schemas/ImageResponseDataB64'
            - $ref: '#/components/schemas/ImageResponseDataUrl'
            discriminator:
              propertyName: type
      required:
      - id
      - model
      - object
      - data
    ImageResponseDataUrl:
      type: object
      required:
      - index
      - url
      - type
      properties:
        index:
          type: integer
        url:
          type: string
        type:
          type: string
          enum:
          - url
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      x-bearer-format: bearer
      x-default: default