Fal launches FLUX 3 Max video model, 22× faster than Seedance 2.5
fal announced FLUX 3 Max on October 19, 2026, a video generation model post‑trained with Black Forest Labs on the FLUX 3 foundation model. The model is available immediately through fal’s inference platform and is priced at $0.0425 per second of 720p output video, a 75 % discount that runs until November 7, 2026. fal reports that FLUX 3 Max achieved a 1,139 Elo rating across 4,868 votes in…
What you can do with it
AI at Work →Create ads with fal.ai API
What you get You can make product demos and produce social clips.
Produces 720p video from text or images in roughly real-time.
- Who for
- marketers
- Cost
- paid from $0.0425 per second
- Effort
- minutes
Use it for
- Create ads
- Make product demos
- Produce social clips
Watch out Discount ends November 7, 2026
Key points from the news
- FLUX 3 Max reaches 1,139 Elo on 4,868 votes in Artificial Analysis Video Arena
- Generates a 10‑second 720p video in 10.95 seconds, 22× faster than Seedance 2.5
- Pricing is $0.0425 per second of output, a 75% discount until November 7 2026
The launch builds on earlier work such as H3 Max, which produced video in 3.49 seconds and delivered a 50‑point Elo improvement. fal’s Head of Research Kaan Oktay said the new model also improves inference speed by more than 11 ×. The product page lists additional comparison figures, placing FLUX 3 Max near the top of the image‑to‑video leaderboard alongside MiniMax H3 and Gemini Omni Flash 1.1.
The story so far
4 episodes →- Fal launches FLUX 3 Max video model, 22× faster than Seedance 2.5this story
Fal Debuts FLUX 3 Max Video Model Post-Trained With Black Forest Labs
Unite.AI · 19 October 2026
Loading the full article…
This text was published by Unite.AI and written by Jonas Reeve, Cognitive AI & AGI, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Google makes Gemini 4 Argon generally available · 2 src
- DeepSeek’s Flash ties Anthropic’s Opus 5.5 in browser-agent benchmark · 2 src
- MiniMax releases M3.1 Flash model at $0.15 per 1M input tokens · 4 src
- Meta releases Muse Spark Open, an 816B-parameter open-weight multimodal model · 1 src
- Mercury 3 [Inception Labs] - Matching Luna/Haiku at 1000 tokens/sec · 2 src
Comments
via GitHub Discussions