MiniMax H3

​

Key capabilities

• Multimodal video generation - Supports text-to-video, image-to-video, first-and-last-frame, and multimodal reference workflows
• Native audio - Can generate synchronized native stereo sound
• Flexible output - Provider specifications cover 768P and 2K output, 4 to 15 seconds, at 24 fps
• Asynchronous workflow - Submit a task, then poll for its result

​

Workflow

1. POST /v1/video/generations -> task_id
2. GET /v1/video/generations/{task_id} -> status
3. When the task succeeds -> read the video URL

​

Text-to-video example

curl "https://api.mixroute.ai/v1/video/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-H3",
    "prompt": "A product film with precise typography, smooth camera movement, and synchronized stereo sound",
    "asset": false
  }'

import requests

response = requests.post(
    "https://api.mixroute.ai/v1/video/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "MiniMax-H3",
        "prompt": "A product film with precise typography, smooth camera movement, and synchronized stereo sound",
        "asset": False,
    },
    timeout=60,
)

print(response.json())

​

Query task status

curl "https://api.mixroute.ai/v1/video/generations/TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

​

Parameters