Video Generationtextimagevideoaudio

MiniMax H3 Max

MiniMax H3 Max 支持文生视频、图生视频及参考生视频，支持 480P/768P 输出及原生音频。

输入

生成方式

当前模板仅支持以下输入方式

文生视频

仅使用文本描述生成视频，无需上传图片。

提示词

参考图（可选）

支持 PNG、JPG、WebP · 可将文件拖到此区域

Style

Duration

515

Resolution

Aspect ratio

Prompt expansion

准备开始生成

API 参考

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "minimax-h3-max",
  "prompt": "A cat walking across a room",
  "style": "style1",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9",
  "prompt_expansion": false
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API 文档

Overview#

MiniMax H3 Max supports text-to-video, image-to-video, and reference-to-video at 480P/768P, with native audio.

API#

POST https://api.token360.ai/v1/videos using model minimax-h3-max. Use frame_images for first/last-frame image-to-video. Use input_references for reference images, videos, or audio. See the model parameter schema for supported durations, aspect ratios, and other options.