Theme
MiniMax video
MiniMax video currently documents a single model, , with two integration styles: the official /v1/video/generations route and the OpenAI-compatible /v1/videos route.
Both routes cover the same generation scenarios, inferred automatically from request parameters:
| Scenario | Parameters | Aspect ratio |
|---|---|---|
| Text-to-video | only | Default ; cannot be |
| Image-to-video | or | Forced |
| Multimodal reference to video | / | Default |
Image-to-video and multimodal reference-to-video are mutually exclusive and cannot be mixed.
OpenAI format
Submit with POST /v1/videos, remix with POST /v1/videos/{video_id}/remix, and query with GET /v1/videos/{task_id}.
MiniMax video generation
`POST /v1/videos` — OpenAI-style MiniMax-H3 task submission
View docs →MiniMax task query
`GET /v1/videos/{task_id}` — OpenAI-style `video` object query
View docs →Official format
Create tasks with POST /v1/video/generations and query with GET /v1/video/generations/{task_id}, submitting a multimodal content array.
Endpoint summary
| Capability | Method | Path | Format |
|---|---|---|---|
| Create task | POST | OpenAI | |
| Remix | POST | OpenAI | |
| Query task | GET | OpenAI | |
| Create task | POST | Official | |
| Query task | GET | Official |