fal engineer Rehan Sheikh has connected H3 Max directly to Twitch in an experiment that turns AI video generation into a live, continuously updating stream. Because the model can generate footage faster than viewers consume it, the system can play one segment while rendering the next in the background, making a theoretically endless broadcast possible. Sheikh described the setup as an "infinite interdimensional television," and MiniMax later reposted the experiment. fal then continued with a broader H3 Max Live test. The stream is not pre-rendered: viewers can type !prompt in the Twitch chat, and fal said new instructions can appear on screen within seconds, letting the audience shape each scene as the broadcast unfolds. According to the source material, the lack of a fixed script or running time means the program can continue as long as generation continues. The report said the key shift is speed. H3 Max has reduced waiting time to below playback time, clearing a threshold that previously kept AI video from functioning as a true live format. fal Research said H3 Max was trained on top of MiniMax’s open-source H3 and accelerated for fal’s inference system. Official figures cited in the report said it can generate a 5-second video in under 3 seconds, with throughput about 35 times that of MiniMax’s official H3 API. On Artificial Analysis’ audio-enabled ranking, its image-to-video model sits first at 1202 Elo, while its text-to-video model ranks third at 1235 Elo behind only Wan 3.0 and Gemini Omni Flash.

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.