Use this file to discover all available pages before exploring further.
Async processing mode, returns task ID for subsequent queries
Supports text-to-video and image-to-video (first frame)
Supports 6-second and 10-second durations, 768p/1080p resolution
Supports 15 camera directives for cinematic control
Supports prompt optimization and watermark control
Important Change: For better performance and cost control, we no longer support passing base64 image data directly in first_frame_image. Please use the Upload Image API first to upload images and get URLs, then call this endpoint.
Video content description (max 2000 characters)Describe scene, action, and style in detail for better results. Supports camera directives (see Camera Directives table below).Example: "A cute cat running on grass, sunny day"
Use [directive] syntax in the prompt to control camera movement. Supports 15 directive types:
Category
Directives
Pan
[Pan left][Pan right]
Tilt
[Tilt up][Tilt down]
Push/Pull
[Push in][Pull out]
Pedestal
[Pedestal up][Pedestal down]
Truck
[Truck left][Truck right]
Zoom
[Zoom in][Zoom out]
Other
[Shake][Tracking shot][Static shot]
Usage tips:
Combine up to 3 directives in one bracket for simultaneous movement (e.g., [Pan left, Pedestal up])
Sequence directives in the prompt for ordered camera moves
Explicit commands yield more accurate results than natural language descriptions
Example:
{ "model": "MiniMax-Hailuo-2.3", "prompt": "[Push in] A cat running in a garden, camera slowly pushes in for a close-up", "duration": 6, "metadata": { "resolution": "768p" }}
{ "model": "MiniMax-Hailuo-2.3", "prompt": "[Push in] A cat running in a garden, camera slowly pushes in for a close-up", "duration": 6, "metadata": { "resolution": "768p" }}
Query Task ResultsVideo generation is an async task that returns a task ID upon submission. Use the Get Task Status endpoint to query generation progress and results.