MiniMax H3
One model for every starting point — a prompt, a keyframe pair, or reference images that keep a subject consistent.
All modelsSpecifications · Text + image + video + audio to video
- Input mode
- Text + image + video + audio to video
- Accepts
- reference image (up to 5), start frame, end frame, reference video, audio
- Aspect ratios
- 1:1, 3:4, 4:3, 16:9, 21:9, 9:16, adaptive
- Resolutions
- 480p, 768p, 2K, 4K
- Durations
- 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
- Max duration
- 15s
- Native audio
- No
Pricing
480p5¢/second
768p6¢/second
2K13¢/second
4K16¢/second
Build with this model: the MiniMax H3 API on the Hedra Developer Platform.
MiniMax H3 API →Real output · generated with MiniMax H3
