Multimodal video model for text, first/last-frame and image, video or audio reference generation. Outputs 4–15 seconds at 768P or 2K. The first five input images per task are free; subsequent images cost $0.04 each, and audio input is free.
| 768P | 2K | |
|---|---|---|
| Output video | $0.08 | $0.13 |
| Input video | $0.08 | $0.13 |
| Any resolution | |
|---|---|
| Input image | $0.04 |
| Model | Max duration | Max resolution | Resolutions | FPS |
|---|---|---|---|---|
| Hailuo 01 | 5s | 1280x720 | 1280x720, 720x1280 | 24 fps |
| Hailuo 02 | 10s | 1920x1080 | 1920x1080, 1080x1920, 1280x1280 | 24 fps |
| MiniMax H3 Highspeed | 15s | 768P | 480P, 768P | — |
| MiniMax H3 Lite | 15s | 768P | 480P, 768P | — |
| MiniMax H3 Max | 15s | 768P | 480P, 768P | — |
| MiniMax H3 | 15s | 2K | 768P, 2K | — |
| MiniMax Hailuo 02 | 10s | 1080P | 512P, 768P, 1080P | — |
| MiniMax Hailuo 2.3 Fast | 10s | 1080P | 768P, 1080P | — |
| MiniMax Hailuo 2.3 | 10s | 1080P | 768P, 1080P | — |
/v1/models/hailuo/MiniMax-H3Multimodal video model for text, first/last-frame and image, video or audio reference generation. Outputs 4–15 seconds at 768P or 2K. The first five input images per task are free; subsequent images cost $0.04 each, and audio input is free.