Video · Black Forest Labs

FLUX 3 video

Black Forest Labs' first video model (August 2026), with sound and clips up to 20 s. Pick it to link two images, to extend a clip or for a long shot with sound.

Anonymized Moderate cost
Latest versionFLUX 3 videoAugust 4, 2026
Artificial Analysis Text to Video Arena with audio1,127 Elo#5 of 18 on Artificial Analysis Text to Video Arena with audio
Price$0.0845 per second of video$0.423 a 5 s clip
Key specClips up to 20 s, with sound

What sets it apart

FLUX 3 is Black Forest Labs' first video family: clips of 5 to 20 s with native audio, five modes (text, image, first and last frame, keyframes, extend) and a cheap Draft tier for previews. An open-weight Dev backbone is announced.

  • 5 to 20 s with native audio
  • 1 to 10 timed keyframes
  • Draft tier for cheap previews

Strengths and limits

Where it shines

  • Speech, effects and ambience generated with the picture
  • Up to 20 s per clip
  • First and last frame mode

Think twice when

  • Mid-range to high price per second
  • Extending needs a source clip under 15 s and 50 MB
  • 5, 10, 15 or 20 s, native sound
  • 720p, 1080p, 1440p or 2160p

Use cases

Scene with keyframes

Use my 3 keyframes (a closed letter, a hand opening it, a smiling face). 12 seconds, soft piano, paper rustle.

Up to 10 timed keyframes pin the story beats.

Continue an existing shot

Continue my 4 second clip for 10 more seconds: the dog runs into the field, same light and framing, with joyful barking.

Continuation takes an existing clip with its audio.

Spoken ad line

A barista slides a cup across the counter and says 'First one is on us.' 6 seconds, cafe ambience, close-up.

Dialogue lines in quotes are voiced with the picture.

Against its rivals

  • Veo 3 and 3.1Veo is polished but limited to 8 s.#7 of 22 on Artificial Analysis Image to Video Arena (1,082 Elo)
  • Seedance 2.5Seedance 2.5 reaches 30 s with more references.#2 of 18 on Artificial Analysis Text to Video Arena with audio (1,142 Elo)
  • MiniMax H3 (Hailuo)MiniMax H3 is open weights, 15 s at up to 2K.#1 of 22 on Artificial Analysis Image to Video Arena (1,195 Elo)
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. FLUX 3 videoLatest
    • First BFL video model: text, image, first and last frame, keyframes and continuation of an existing clip.
    • Native dialogue, effects and ambience, 5 to 20 s clips from 720p up to 2160p.
    Source : pixverse.ai

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis Text to Video Arena with audio: #5 of 18 models measured in the catalog. The duel for clips with sound: picture, voices, effects and how well they match. An Elo rating: higher is preferred more often. Only models that make their own sound take part.

Artificial Analysis Text to Video Arena with audioElo rating · Artificial Analysis, October 4, 2026
  1. 1. Wan 3.0Wan 3.01,156
  2. 2. Seedance 2.5Seedance 2.51,142
  3. 3. MiniMax H3MiniMax H3 (Hailuo)1,138
  4. 4. MiniMax H3 MaxMiniMax H3 (Hailuo)1,134
  5. 5. Flux 3FLUX 3 video1,127
  6. 6. Seedance 2.0Seedance 2.0 and 1.51,119
  7. 7. Gemini Omni Flash 1.1Gemini Omni Flash1,113
  8. 8. Grok Imagine 1.5Grok Imagine video1,044
  9. 9. HappyHorse 1.1HappyHorse1,043
  10. 10. Wan 2.7Wan 2.x1,029
See the numbers
ModelElo
1. Wan 3.01,156
2. Seedance 2.51,142
3. MiniMax H31,138
4. MiniMax H3 Max1,134
5. Flux 31,127
6. Seedance 2.01,119
7. Gemini Omni Flash 1.11,113
8. Grok Imagine 1.51,044
9. HappyHorse 1.11,043
10. Wan 2.71,029

Artificial Analysis Text to Video Arena: #5 of 5 models measured in the catalog. People watch two silent clips made from the same description, without knowing the models, and pick the better one. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Text to Video ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. Wan 3.0Wan 3.01,129
  2. 2. MiniMax H3MiniMax H3 (Hailuo)1,118
  3. 3. MiniMax H3 MaxMiniMax H3 (Hailuo)1,115
  4. 4. Seedance 2.5Seedance 2.51,102
  5. 5. Flux 3FLUX 3 video1,094
See the numbers
ModelElo
1. Wan 3.01,129
2. MiniMax H31,118
3. MiniMax H3 Max1,115
4. Seedance 2.51,102
5. Flux 31,094

All 4 models in this family

ModelUsePrivacyPrice
Flux 3flux-3-text-to-videoText to videoAnonymized$0.0845 per second of video$0.423 a 5 s clip
Flux 3flux-3-image-to-videoImage to videoAnonymized$0.0845 per second of video$0.423 a 5 s clip
Flux 3 First Last Frameflux-3-first-last-frame-to-videoImage to videoAnonymized$0.0845 per second of video$0.423 a 5 s clip
Flux 3 Extendflux-3-extend-videoText to videoAnonymizedShown in the app

Specifications

SpecificationFLUX 3 video
ReleasedAugust 4, 2026
WeightsClosed
Acceptstext, images, video
Producesvideo, audio
Clip length5 to 20 s, with sound
Resolutions720p, 1080p, 1440p, 2160p
Price$0.0845 per second of video
PrivacyAnonymized

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.