Black Forest Labs added FLUX 3 Image to its API on October 1, 2026. It follows the FLUX 3 multimodal foundation model announced on July 23 and FLUX 3 Video, which arrived as a preview on August 4.
What is new
- One endpoint. The prompt decides whether the model generates a new image or edits an existing one. There is no separate mode setting.
- Bounding boxes in the prompt. You can add a JSON list of boxes to place a headline, a face in a crowd or each panel of a grid.
- Pixel-exact local edits. Mark the element to change and the rest of the image stays as it was. You can recolor, replace, move, resize or remove several elements in one request.
- Up to ten references. Refer to each image by its position in the prompt to restyle an image or combine references.
- Up to 4K output, from 768-pixel square previews to about 16 megapixels, at 15 aspect ratios.
Pricing
BFL lists per-image prices by resolution: $0.041 at 768 square, $0.048 at 1K, $0.100 at 2K and $0.607 at 4K.
Why it matters
Layout control is the feature to watch. Placing text and objects exactly where you want them is a common pain point for designers using AI images.
Source: Black Forest Labs release notes. We summarise in our own words; check the source for the full details.