Black Forest Labs

Black Forest Labs Models

Black Forest Labs FLUX.1, FLUX 1.1 Pro, Kontext, FLUX.2 Pro and FLUX 3 via API: text-to-image and instruction-based image editing models.

Black Forest Labs develops the FLUX text-to-image and image editing models. The company was founded in 2024 and is headquartered in Freiburg, Germany; its founders include Robin Rombach, Andreas Blattmann and Patrick Esser, whose earlier latent diffusion work led to Stable Diffusion.

Available models

5 model groups found

FLUX Kontext

4 capabilities
  • Black Forest Labs: FLUX.1 Kontext Max · Text to Image
    black-forest-labs/flux-kontext-max/text-to-image
    Text to Image$0.08 / image
  • Black Forest Labs: FLUX.1 Kontext Max · Image to Image
    black-forest-labs/flux-kontext-max/image-to-image
    Image to Image$0.08 / image
  • Black Forest Labs: FLUX.1 Kontext Pro · Text to Image
    black-forest-labs/flux-kontext-pro/text-to-image
    Text to Image$0.04 / image
  • Black Forest Labs: FLUX.1 Kontext Pro · Image to Image
    black-forest-labs/flux-kontext-pro/image-to-image
    Image to Image$0.04 / image
2 capabilities
  • Black Forest Labs: FLUX 3 · Text to Image
    black-forest-labs/flux-3/text-to-image
    Text to Image$0.024 / megapixel
  • Black Forest Labs: FLUX 3 · Image to Image
    black-forest-labs/flux-3/image-to-image
    Image to Image$0.024 / megapixel

FLUX 2

8 capabilities
  • Black Forest Labs: FLUX.2 Dev · Text to Image
    black-forest-labs/flux-2-dev/text-to-image
    Text to Image$0.012 / megapixel
  • Black Forest Labs: FLUX.2 Dev · Image to Image
    black-forest-labs/flux-2-dev/image-to-image
    Image to Imageabout $0.024 / image
  • Black Forest Labs: FLUX.2 Klein 9B · Text to Image
    black-forest-labs/flux-2-klein-9b/text-to-image
    Text to Image$0.006 / megapixel
  • Black Forest Labs: FLUX.2 Klein 9B · Image to Image
    black-forest-labs/flux-2-klein-9b/image-to-image
    Image to Image$0.011 / megapixel
  • Black Forest Labs: FLUX.2 Max · Text to Image
    black-forest-labs/flux-2-max/text-to-image
    Text to Image$0.07 / megapixel
  • Black Forest Labs: FLUX.2 Max · Image to Image
    black-forest-labs/flux-2-max/image-to-image
    Image to Imageabout $0.10 / request
  • Black Forest Labs: FLUX.2 Pro · Text to Image
    black-forest-labs/flux-2-pro/text-to-image
    Text to Imageabout $0.03 / request
  • Black Forest Labs: FLUX.2 Pro · Image to Image
    black-forest-labs/flux-2-pro/image-to-image
    Image to Imageabout $0.045 / request

FLUX 1.1

2 capabilities
  • Black Forest Labs: FLUX 1.1 Pro · Text to Image
    black-forest-labs/flux-1.1-pro/text-to-image
    Text to Image$0.04 / megapixel
  • Black Forest Labs: FLUX 1.1 Pro Ultra · Text to Image
    black-forest-labs/flux-1.1-pro-ultra/text-to-image
    Text to Image$0.06 / image

FLUX 1

3 capabilities
  • Black Forest Labs: FLUX.1 Dev · Text to Image
    black-forest-labs/flux-dev/text-to-image
    Text to Image$0.025 / megapixel
  • Black Forest Labs: FLUX.1 Dev · Image to Image
    black-forest-labs/flux-dev/image-to-image
    Image to Image$0.03 / megapixel
  • Black Forest Labs: FLUX.1 Schnell · Text to Image
    black-forest-labs/flux-schnell/text-to-image
    Text to Image$0.003 / megapixel

About

Black Forest Labs builds FLUX image models with flow matching, a generative training method. FLUX.1 launched in August 2024 and FLUX.2 in November 2025, and FLUX 3 is the newest generation; some versions are released as open weights and others only as hosted models.

  • FLUX.1 and FLUX 1.1: Text-to-image; open-weight FLUX.1 Schnell and Dev, plus the hosted FLUX 1.1 Pro and the 4 MP FLUX 1.1 Pro Ultra.
  • FLUX.1 Kontext: Instruction-based image editing in Kontext Pro and Kontext Max: change part of an image by describing the edit in plain words.
  • FLUX.2 Pro: Text-to-image and image editing from the second FLUX generation.
  • FLUX 3: Text-to-image and image editing from the newest FLUX generation, from quick 512px square drafts up to 4K output.

Build with the API

One MuseSpan API key calls every Black Forest Labs model on this page: copy a model ID and send it as the model field of your request.