MiniMax H3 Video Generation
nexscope_minimax_h3_video_generationGenerate a MiniMax H3 video from 1 to 9 required reference images. The model is fixed by this API, so videoType must not be supplied in the request.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"videoTime": "<videoTime>",
"prompt": "<prompt>",
"resolution": "<resolution>",
"imageList": "<imageList>"
},
"name": "nexscope_minimax_h3_video_generation"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| isPro | No | Whether to use the model's professional generation mode when supported. Defaults to false. | |
| prompt | Yes | Video generation prompt describing motion, subject consistency, camera movement, and the ecommerce scene. Maximum 10000 characters. | |
| imageList | Yes | Public reference image URLs. Provide 1 to 9 images. | |
| videoTime | Yes | Video duration in seconds. Supported values: 5, 10, 15. | |
| resolution | Yes | Output resolution. Supported values: 768p, 2k. | |
| aspectRatio | No | Target video aspect ratio supported by this model. Supported values: adaptive, 9:16, 16:9, 1:1, 4:3, 3:4, 21:9. | |
| promptOptimizer | No | Whether Nexscope should optimize the video prompt before generation. Defaults to false. |