Latest models
- MiniMax H3 (Hailuo) (July 31, 2026) Current
A general-purpose multimodal model that generates video with native stereo sound, up to 15 seconds at 2K. MiniMax describes it as an open model. Source: MiniMax research ↗
Checked October 7, 2026. See the full AI model tracker.
What we like
- Video with native stereo sound, up to 15 seconds at 2K
- Understands text, images, video and audio together
- MiniMax describes it as an open model
Watch out for
- Check which resolutions and durations your plan includes
- Open-weight availability and licence terms should be confirmed on MiniMax's pages
- Expect to iterate for a usable take
MiniMax H3 is the model behind the Hailuo video app. MiniMax released it on July 31, 2026.
What is current
H3 is a general-purpose multimodal generation model. MiniMax says it understands unified context across text, images, video and audio, and generates video with native stereo sound, up to 15 seconds at 2K resolution. MiniMax describes it as an open model and says it is suited to advertising, branding, e-commerce, product design and gaming. It is available in the Hailuo AI editor and through the MiniMax API. See the model tracker.
How prompting works
Describe a single shot, its camera movement and the sound. For brand work, put exact words in quotation marks and describe where they appear.
Who should use it
Creators and marketers who want 2K clips with sound. Compare it with Veo, Kling and Seedance.