Flux Image Generation API

openapi: 3.1.0
info:
  title: Flux Image Generation API
  description: >-
    REST API for generating images from text prompts using Black Forest Labs'
    FLUX models including FLUX.1 [pro], FLUX.1 [dev], FLUX.1 [schnell], and
    FLUX 1.1 [pro] variants. The API uses an asynchronous pattern where a
    generation request returns a task ID and polling URL. The caller then
    polls the result endpoint until the image is ready. Authentication
    requires an API key passed in the X-Key header.
  version: 'v1'
  contact:
    name: Black Forest Labs Support
    url: https://docs.bfl.ai/
  termsOfService: https://bfl.ai/legal/flux-api-service-terms
externalDocs:
  description: Flux API Documentation
  url: https://docs.bfl.ai/
servers:
  - url: https://api.bfl.ai/v1
    description: Black Forest Labs Flux API
tags:
  - name: Generation
    description: >-
      Endpoints for submitting image generation requests using FLUX models.
      Each endpoint targets a specific model variant and returns a task ID
      for polling.
  - name: Results
    description: >-
      Endpoints for polling the status and retrieving the result of an
      asynchronous image generation task.
security:
  - apiKeyAuth: []
paths:
  /flux-pro-1.1:
    post:
      operationId: generateFluxPro11
      summary: Generate image with FLUX 1.1 [pro]
      description: >-
        Submits an asynchronous image generation request using the FLUX 1.1
        [pro] model, which offers improved prompt adherence and image quality
        over FLUX.1 [pro]. Returns a task ID and polling URL. The caller must
        poll GET /v1/get_result?id={id} until the status is Ready, then
        download the image from the returned sample URL.
      tags:
        - Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FluxProGenerationRequest'
      responses:
        '200':
          description: Generation task accepted. Poll the returned ID for results.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad request. Invalid parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized. Missing or invalid API key.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation error. Request body failed schema validation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
  /flux-pro:
    post:
      operationId: generateFluxPro
      summary: Generate image with FLUX.1 [pro]
      description: >-
        Submits an asynchronous image generation request using the original
        FLUX.1 [pro] model. Returns a task ID for polling. The pro model
        delivers high-quality images with strong prompt following and supports
        a full range of aspect ratios via width and height parameters.
      tags:
        - Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FluxProGenerationRequest'
      responses:
        '200':
          description: Generation task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
  /flux-dev:
    post:
      operationId: generateFluxDev
      summary: Generate image with FLUX.1 [dev]
      description: >-
        Submits an asynchronous image generation request using the FLUX.1
        [dev] model. The dev model is a distilled version of FLUX.1 [pro]
        intended for non-commercial use, offering a balance of quality and
        speed. Requires accepting the FLUX.1 [dev] non-commercial license.
      tags:
        - Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FluxDevGenerationRequest'
      responses:
        '200':
          description: Generation task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
  /flux-schnell:
    post:
      operationId: generateFluxSchnell
      summary: Generate image with FLUX.1 [schnell]
      description: >-
        Submits an asynchronous image generation request using the FLUX.1
        [schnell] model. Schnell is the fastest FLUX variant, optimized for
        local development and personal use. It typically requires only 1-4
        inference steps and returns results faster than other variants.
      tags:
        - Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FluxSchnellGenerationRequest'
      responses:
        '200':
          description: Generation task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
  /flux-pro-1.1-ultra:
    post:
      operationId: generateFluxPro11Ultra
      summary: Generate image with FLUX 1.1 [pro] Ultra
      description: >-
        Submits an image generation request using the FLUX 1.1 [pro] Ultra
        model, which supports higher resolution outputs up to 4 megapixels
        and includes an optional raw mode for more photorealistic results.
        Returns a task ID for polling.
      tags:
        - Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FluxUltraGenerationRequest'
      responses:
        '200':
          description: Generation task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
  /get_result:
    get:
      operationId: getResult
      summary: Flux Poll for generation result
      description: >-
        Polls the status of an asynchronous image generation task by ID.
        Returns the current status (Pending, Processing, Ready, Error, or
        Content Moderated). When status is Ready, the response includes a
        sample field containing a pre-signed URL to download the generated
        image. The URL expires after a short time, so the image should be
        downloaded promptly.
      tags:
        - Results
      parameters:
        - $ref: '#/components/parameters/taskIdParam'
      responses:
        '200':
          description: Task status and result (if ready).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResultResponse'
        '401':
          description: Unauthorized.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Task not found.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: X-Key
      description: >-
        API key obtained from the Black Forest Labs developer portal at
        https://api.bfl.ai. Pass the key in the X-Key request header for
        all authenticated endpoints.
  parameters:
    taskIdParam:
      name: id
      in: query
      required: true
      description: The task ID returned by a generation request.
      schema:
        type: string
        format: uuid
  schemas:
    FluxProGenerationRequest:
      type: object
      description: >-
        Request body for FLUX.1 [pro] and FLUX 1.1 [pro] image generation.
        Specifies the prompt, image dimensions, output format, and model
        quality parameters.
      required:
        - prompt
      properties:
        prompt:
          type: string
          description: >-
            Text description of the image to generate. Detailed, descriptive
            prompts generally yield better results.
          maxLength: 10000
        width:
          type: integer
          description: >-
            Width of the generated image in pixels. Must be a multiple of 32.
            Defaults to 1024.
          minimum: 256
          maximum: 1440
          default: 1024
        height:
          type: integer
          description: >-
            Height of the generated image in pixels. Must be a multiple of 32.
            Defaults to 768.
          minimum: 256
          maximum: 1440
          default: 768
        steps:
          type: integer
          description: >-
            Number of diffusion steps. Higher values produce better quality
            but take longer. Defaults vary by model.
          minimum: 1
          maximum: 50
        guidance:
          type: number
          description: >-
            Classifier-free guidance scale. Higher values follow the prompt
            more closely but may reduce image naturalness.
          minimum: 1.5
          maximum: 5.0
          default: 3.5
        seed:
          type: integer
          description: >-
            Random seed for reproducible generation. If omitted, a random
            seed is used.
          minimum: 0
        safety_tolerance:
          type: integer
          description: >-
            Content safety filter tolerance level from 0 (most strict) to
            6 (least strict). Default is 2.
          minimum: 0
          maximum: 6
          default: 2
        output_format:
          type: string
          description: Output image format.
          enum:
            - jpeg
            - png
          default: jpeg
        prompt_upsampling:
          type: boolean
          description: >-
            If true, automatically enhances the prompt before generation
            using an LLM to improve image quality and prompt adherence.
          default: false
    FluxDevGenerationRequest:
      type: object
      description: >-
        Request body for FLUX.1 [dev] image generation. Similar to the pro
        request but with parameters tuned for the distilled dev model.
      required:
        - prompt
      properties:
        prompt:
          type: string
          description: Text description of the image to generate.
          maxLength: 10000
        width:
          type: integer
          description: Width of the generated image in pixels.
          minimum: 256
          maximum: 1440
          default: 1024
        height:
          type: integer
          description: Height of the generated image in pixels.
          minimum: 256
          maximum: 1440
          default: 768
        steps:
          type: integer
          description: Number of diffusion inference steps.
          minimum: 1
          maximum: 50
          default: 28
        guidance:
          type: number
          description: Guidance scale for prompt adherence.
          minimum: 1.5
          maximum: 5.0
          default: 3.5
        seed:
          type: integer
          description: Random seed for reproducibility.
          minimum: 0
        safety_tolerance:
          type: integer
          description: Safety filter tolerance (0-6).
          minimum: 0
          maximum: 6
          default: 2
        output_format:
          type: string
          description: Output image format.
          enum:
            - jpeg
            - png
          default: jpeg
    FluxSchnellGenerationRequest:
      type: object
      description: >-
        Request body for FLUX.1 [schnell] image generation. Schnell is
        optimized for speed with fewer inference steps required.
      required:
        - prompt
      properties:
        prompt:
          type: string
          description: Text description of the image to generate.
          maxLength: 10000
        width:
          type: integer
          description: Width of the generated image in pixels.
          minimum: 256
          maximum: 1440
          default: 1024
        height:
          type: integer
          description: Height of the generated image in pixels.
          minimum: 256
          maximum: 1440
          default: 768
        steps:
          type: integer
          description: Number of inference steps. Schnell typically uses 1-4 steps.
          minimum: 1
          maximum: 12
          default: 4
        seed:
          type: integer
          description: Random seed for reproducibility.
          minimum: 0
        safety_tolerance:
          type: integer
          description: Safety filter tolerance (0-6).
          minimum: 0
          maximum: 6
          default: 2
        output_format:
          type: string
          description: Output image format.
          enum:
            - jpeg
            - png
          default: jpeg
    FluxUltraGenerationRequest:
      type: object
      description: >-
        Request body for FLUX 1.1 [pro] Ultra image generation. Supports
        higher resolution outputs and an optional raw mode for photorealistic
        results without additional artistic processing.
      required:
        - prompt
      properties:
        prompt:
          type: string
          description: Text description of the image to generate.
          maxLength: 10000
        aspect_ratio:
          type: string
          description: >-
            Aspect ratio of the generated image. Ultra uses aspect ratios
            instead of explicit width/height.
          enum:
            - '21:9'
            - '16:9'
            - '4:3'
            - '3:2'
            - '1:1'
            - '2:3'
            - '3:4'
            - '9:16'
            - '9:21'
          default: '16:9'
        seed:
          type: integer
          description: Random seed for reproducibility.
          minimum: 0
        safety_tolerance:
          type: integer
          description: Safety filter tolerance (0-6).
          minimum: 0
          maximum: 6
          default: 2
        output_format:
          type: string
          description: Output image format.
          enum:
            - jpeg
            - png
          default: jpeg
        raw:
          type: boolean
          description: >-
            If true, generates more natural, less processed images with a
            more photorealistic aesthetic.
          default: false
    TaskResponse:
      type: object
      description: >-
        Response returned when an image generation task is accepted. Contains
        the task ID and a polling URL for checking status.
      properties:
        id:
          type: string
          format: uuid
          description: >-
            Unique identifier for the generation task. Use this ID to poll
            GET /v1/get_result for the result.
        polling_url:
          type: string
          format: uri
          description: >-
            Convenience URL for polling the result. Equivalent to
            GET /v1/get_result?id={id}.
    ResultResponse:
      type: object
      description: >-
        Response from the result polling endpoint. When status is Ready,
        the sample field contains a pre-signed URL to download the
        generated image.
      properties:
        id:
          type: string
          format: uuid
          description: The task ID.
        status:
          type: string
          description: >-
            Current status of the generation task.
          enum:
            - Pending
            - Processing
            - Ready
            - Error
            - Content Moderated
            - Request Moderated
        result:
          type: object
          description: >-
            Generation result, present only when status is Ready.
          properties:
            sample:
              type: string
              format: uri
              description: >-
                Pre-signed URL to download the generated image. Expires
                after a short time (typically a few minutes).
            prompt:
              type: string
              description: The prompt used for generation (may differ if prompt_upsampling was used).
            seed:
              type: integer
              description: The seed used for generation.
    ErrorResponse:
      type: object
      description: Error response returned when a request fails.
      properties:
        detail:
          type: string
          description: Human-readable error message describing the failure.
        status_code:
          type: integer
          description: HTTP status code.
    ValidationErrorResponse:
      type: object
      description: Validation error response returned when the request body fails schema validation.
      properties:
        detail:
          type: array
          description: Array of validation error details.
          items:
            type: object
            properties:
              loc:
                type: array
                description: Location of the validation error in the request.
                items:
                  oneOf:
                    - type: string
                    - type: integer
              msg:
                type: string
                description: Validation error message.
              type:
                type: string
                description: Error type identifier.