AI inference platform fal has introduced H3 Max, a video model fine-tuned from the open-source MiniMax H3. The company said the new model improves prompt understanding and visual quality while being optimized for fal’s own inference stack. On Artificial Analysis’ leaderboard for videos with audio, H3 Max ranked No. 1 in image-to-video at 1205 Elo, ahead of ByteDance’s Seedance 2.0 and the original H3. In text-to-video, it posted 1235 Elo, placing third and sitting 4 points behind Wan 3.0 in first place. fal also highlighted speed and pricing. It said a 5-second 768p video can be generated in under 3 seconds, with throughput about 35 times that of the original H3 API. At launch, H3 Max is offered at a 50% discount, with 768p pricing set at $0.04 per second, or $2.4 for one minute of video. The price will return to $0.08 per second after Sept. 1. The model currently supports up to 768p, while the original H3 can generate 2K video. fal said the initial release includes text-to-video and image-to-video, while Reference-to-Video is not yet available.
AI inference platform fal has released H3 Max, a video model fine-tuned from the open-source MiniMax H3. The company said the model improves prompt understanding and visual output, and has also been accelerated for fal’s in-house inference system.
Leaderboard results
On Artificial Analysis’ leaderboard for videos with audio, H3 Max ranked first in image-to-video with an Elo score of 1205, ahead of ByteDance’s Seedance 2.0 and the original H3. In text-to-video, it scored 1235 Elo and ranked third, just 4 points behind Wan 3.0 in the top spot.
Speed and launch pricing
fal said it can generate a 5-second 768p video in under 3 seconds. The company put throughput at roughly 35 times that of the original H3 API.
At launch, H3 Max is being offered at a 50% discount. Pricing for 768p output is set at $0.04 per second, or $2.4 for one minute of video. After Sept. 1, the price will return to $0.08 per second.
Current limits
H3 Max has a narrower scope than the original H3. It currently supports up to 768p, while the original H3 can generate 2K video. The initial release includes only text-to-video and image-to-video. Reference-to-Video has not gone live yet.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
