MiniMax H3 is an open video generation model with an API, a local PC version, and a fal-based variant called H3 Max that runs roughly 36 times faster than the official Hailuo.ai generation time. The open weights are available as of August 9, and H3 Max offers a discount until September 1.
MiniMax released H3, an open video generation model, on August 3, and the community moved quickly. H3 generates up to 15 seconds of audio-synced video from text, images, or voice, and it supports 768p or 2K resolution. In a blind test by Artificial Analysis, H3 ranked second for text-to-video, behind Gemini Omni Flash and ahead of Seedance 2.0. The model was available via API at announcement, with open weights planned soon.
By August 9, the open weights were out, and ASCII.jp tested H3 on a local PC with an RTX 4090. The model's Omni Reference feature, previously a cloud-only selling point, accepts up to nine images, three videos, and three audio tracks. ASCII.jp ran both live-action and anime-style prompts to gauge local performance.
On August 30, the AI cloud service fal introduced MiniMax H3 Max, which generates 15-second videos in about 13 seconds while keeping quality. H3 Max undercuts the official Hailuo.ai generation time by a factor of roughly 36 and beats Seedance 2.0 on price per second. It offers 5-second videos free up to five times daily, supports Japanese prompts, and costs $0.08 per second at 768p, with a 50% off sale until September 1.
Synthesized by Yomimono from the cited Yomimono stories below, each itself sourced, then editorially reviewed. Every fact links the story it came from.
Structured graph also available as JSON at /public/entities/minimax-h3.
CC BY 4.0.
When a claim about MiniMax H3 was confirmed, debunked, or disputed against open-web sources. The record stays even after a claim drops off the facts list.
The video generation AI MiniMax H3, released as an open-weight model on August 3, has spawned rapid community updates. The AI cloud service fal developed MiniMax H3 Max, which generates 15-second videos in about 13 seconds while maintaining quality. It offers 5-second videos free up to five times daily, with Japanese prompt support, and costs $0.08 per second at 768p, a 50% off sale until September 1.
Chinese AI firm MiniMax released MiniMax H3, an open video generation model that matches ByteDance's Seedance 2.0 in cloud performance. Its Omni Reference feature accepts up to nine images, three videos, and three audio tracks, and it runs on a local PC with an RTX 4090. ASCII.jp tested it with live-action and anime-style prompts.
Chinese AI firm MiniMax announced MiniMax H3, a video generation model that creates up to 15 seconds of audio-synced video from text, images, or voice. It supports 768p or 2K resolution and accepts multiple media inputs at once. In a blind test by Artificial Analysis, H3 ranked second for text-to-video, behind Gemini Omni Flash and ahead of Seedance 2.0. The model is available via API now, with open weights planned soon.