Wan3.0-Video is an All-in-One video generation model that supports multi-modal inputs including text, image, video, and audio, enabling text-to-video, image-to-video (first frame/first-last frame), and reference-based video generation within a single model. It supports 480P, 720P, and 1080P resolution output, with a maximum video duration of 30 seconds. This model is currently in invitational preview.
Inference service provider
The inference service for the wan3.0-video model is provided by Alibaba Cloud Model Studio.
Model capabilities
|
Capability |
Support status |
Capability |
Support status |
|
Input modalities |
Text Image Video Audio File Link |
Output modalities |
Video |
|
Model playground |
|
Function Calling |
|
|
Structured output |
|
Web search |
|
|
Prefix completion |
|
Context caching |
|
|
Batch inference |
|
Model fine-tuning |
|
Context limits
|
Parameter |
Value |
Parameter |
Value |
|
Maximum input length |
— |
Maximum output length |
— |
|
Context length |
— |
Pricing
This topic only shows the original price for model calls, excluding any limited-time promotions or other offers. Please visit the Model Studio console for promotional offers.
China (Beijing)
|
Billing item |
Price (USD) |
Unit |
|
Video generation (480P) |
0.041256 |
Per second |
|
Video generation (720P) |
0.082513 |
Per second |
|
Video generation (1080P) |
0.165025 |
Per second |
Singapore
Deployment scope: International
|
Billing item |
Price (USD) |
Unit |
|
Video generation (480P) |
0.05 |
Per second |
|
Video generation (720P) |
0.1 |
Per second |
|
Video generation (1080P) |
0.2 |
Per second |
Rate limits
China (Beijing)
|
Parameter |
Value |
|
RPM (Requests per minute) |
— |
Singapore
Deployment scope: International
|
Parameter |
Value |
|
RPM (Requests per minute) |
— |