Black Forest Labs FLUX 3 (Image)

Black Forest Labs FLUX 3 Image creates images and edits up to 10 references, checking the web so real subjects come out right. 768 px to 4K.

FLUX 3 Image is Black Forest Labs' main image model. It draws a picture from a text prompt, and edits or combines up to ten reference pictures: write each change as an instruction, name the pictures by number and say what each is for (the first as the setting, the second as an object to put in).

The model rewrites your prompt before it draws and, with grounding on (the default), looks up what the prompt names on the web, so real products, places and events come out right; set grounding to false for faster results from the prompt alone.

Use it for product and campaign visuals, posters, concept art, changing one detail of a photo, restyling, or blending several pictures into one scene. It makes one image per request and does not make video (see FLUX 3 Video).

Inputs: prompt (required); images (up to 10 links or uploads, the first is the picture that gets edited; leave out to create from the prompt alone); aspect_ratio (auto, or one of 15 from 21:9 to 9:21); resolution (768sq, 1k by default, 1.5k, 2k, 4k, or match_input to keep the first picture's size when editing); width and height (256-6256 px, sent together, up to 16.8 MP, up to 4.2 MP with images); grounding (on by default); safety_tolerance (0 strictest to 4, default 2).

Price per image by size: 768sq $0.041, 1k $0.048, 1.5k $0.07, 2k $0.10, 4k $0.607. The default 1k image is $0.048. Edits and references cost the same as a new picture; a custom width and height bill the smallest size that covers them. A request that fails or is stopped by content moderation is not charged.

Price: From $0.041 per run, depending on resolution, width and height; one image, by size tier: a custom width and height bill the smallest tier that covers them. One run with default settings costs $0.048.

Run Black Forest Labs FLUX 3 (Image) via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-image/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A glass bottle of cold-pressed orange juice on a wet stone ledge at sunrise, condensation drops, soft backlight, editorial product photo","resolution":"1k","aspect_ratio":"16:9"}'

API documentation · Create a free account · Pricing

Related models