fal and Black Forest Labs launch FLUX 3 Max video model: tied #1 in image-to-video quality, a 10-second clip in about 12 seconds, roughly 22x faster than Seedance 2.5
On Oct 19 (UTC) fal released FLUX 3 Max, a video model built by fal Research with Black Forest Labs through post-training, reinforcement learning and inference optimization on top of the FLUX 3 foundation model. It handles text-to-video, image-to-video and keyframes, up to 20 seconds, at 720p or 1080p, with audio on by default. On Artificial Analysis's preliminary image-to-video arena it scores 1,139 Elo, level with Seedance 2.5 and within the confidence interval of leader MiniMax H3 (1,141), and fal says a 10-second clip takes about 12.45 seconds. A 75% launch discount runs until Nov 7, putting 720p at $0.0425 per second.
Key Takeaways
- Artificial Analysis AA-Video-I2V v1.1 (preliminary): FLUX 3 Max at 1,139 Elo, level with Seedance 2.5 and just under MiniMax H3 at 1,141; "tied #1" rests on overlapping confidence intervals
- Speed (fal-reported, 10-second 16:9 at 720p): FLUX 3 Max 12.45s, Gemini Omni Flash 1.1 47.37s, Seedance 2.5 277.80s; the press release quotes 10.95s instead
- Versus the original FLUX 3: Elo up from 1,089 to 1,139 (+50) and a 10-second clip down from 126.44s to about 12s (11.5x per the press release, about 10x per the product page)
- Pricing: promotional $0.0425/s at 720p and $0.0725/s at 1080p until Nov 7, then $0.17/s and $0.29/s, billed per output second
- API options: 5-20 second duration, multiple aspect ratios, reasoning_level (low/high), generate_audio on by default; model IDs blackforestlabs/flux-3-max/*
Linked Models & Agents: