Video Generationtextimagevideoaudio

MiniMax H3 Lite

MiniMax H3 Lite 主打低成本创意探索与批量生成，支持文生视频、图生视频、首尾帧及多模态参考生视频，输出 480P 或 768P 原生音频视频。

输入

生成方式

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 JPG/JPEG、PNG、WebP、HEIC、HEIF · 可拖拽上传

Duration

415

Resolution

Aspect ratio

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-lite",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9"
}'

# 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 Lite targets lower-cost creative exploration and batch generation at 480P or 768P. It supports text-to-video, image-to-video, first-and-last-frame, and multimodal references with native audio.

API#

POST https://api.token360.ai/v1/videos using model minimax-h3-lite. Use frame_images for first/last-frame input and input_references for reference images, videos, or audio. Reference-to-video requires a concrete aspect ratio.