FLUX 3
Early access at launch (2026-07-23); FLUX 3 Image announced 'in coming weeks' and open FLUX 3 [dev] planned later in 2026 - not verified as released. Action weights: flux-3-action-base/-so101/-droid (HF, 2026-09-22).
- Input
- text, image, video
- Output
- video, audio
- License
- proprietary
- Pricing
- per second: $0.17 (per second of video (HD, text/image-to-video); FHD 0.29, QHD 0.40, UHD 0.80, draft 0.06; continuation 0.41/s HD) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| BFL API | flux-3-video | https://api.bfl.ai/v1/flux-3-video | docs |
| Hugging Face (FLUX 3 Action open weights) | — | huggingface.co/black-forest-labs/flux-3-action-base | — |
Notable capabilities (3)
- Unified image/video/audio/action model: Single architecture jointly trained on images, video, audio and robot action prediction; each modality said to strengthen the others. source
- Video with native synced audio: Text/image-to-video up to ~20 s with optional in-sync audio, plus video continuation and video editing (/v1/flux-tools/video-edit-v1). source
- FLUX 3 Action for robotics: Video-prediction engine reused for robot control (FLUX-mimic with mimic robotics, tested by Audi); open-weight Action checkpoints on HF (FLUX Kommunity license). source
BFL's first video (+audio) model and multimodal "visual intelligence" foundation. Async API: submit, then poll the returned polling_url.
curl -X POST https://api.bfl.ai/v1/flux-3-video -H "x-key: $BFL_API_KEY" -H "Content-Type: application/json" \
-d '{"mode":"t2v","prompt":"a fox running through dawn mist","duration":5}'
Sources: https://docs.bfl.ai/flux_3/flux3_overview , https://docs.bfl.ai/quick_start/pricing , https://www.globenewswire.com/news-release/2026/07/23/3332364/0/en/black-forest-labs-unveils-flux-3-a-new-multimodal-frontier-model-for-visual-intelligence.html
Other Black Forest Labs models
FLUX.2 [klein] (4B / 9B) · FLUX.2 [max] · FLUX.2 [dev] · FLUX.2 [pro] · FLUX.1 Kontext [pro] / [max]