Next-generation open, general-purpose multimodal video model supporting text-to-video, image-to-video, first-and-last-frame generation, and multimodal references. Supports 768P / 2K output and videos from 4 to 15 seconds
| Model | Context | Max out | Pricing |
|---|---|---|---|
| minimax-h3-max | — | — | $0$0 |
| minimax-h3 | — | — | $0$0 |
| minimax-m3.1-flash | 1M | — | $0.1$0.5 |
| minimax-m2.7 | 205K | — | $0.21$0.84 |
| minimax-m3 | 1M | — | $0.24$0.96 |
| minimax-m2.1-lightning | 205K | — | $0.3$2.4 |
| minimax-m2.1 | 205K | — | $0.3$1.2 |
| minimax-m2.5 | 1M | — | $0.3$1.2 |
| minimax-m2 | 205K | — | $0.3$1.2 |
| minimax-m2.5-highspeed | 205K | — | $0.6$2.4 |
| minimax-m2.7-highspeed | 205K | — | $0.6$2.4 |
/v1/models/vercel/minimax/minimax-h3Next-generation open, general-purpose multimodal video model supporting text-to-video, image-to-video, first-and-last-frame generation, and multimodal references. Supports 768P / 2K output and videos from 4 to 15 seconds