Wan3.0-Video-Prime is the accelerated version of the Wan video generation model, delivering significantly faster generation speed while maintaining high-quality output. It 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.
Inference service provider
The inference service for the wan3.0-video-prime model is provided by QwenCloud.
Model capabilities
Capability | Support status | Capability | Support status |
|---|---|---|---|
Input modalities | Text Image Video Audio File Link | Output modalities | Video |
Model playground | Supported | Function Calling | Unsupported |
Structured output | Unsupported | Web search | Unsupported |
Prefix completion | Unsupported | Context caching | Unsupported |
Batch inference | Unsupported | Model fine-tuning | Unsupported |
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 QwenCloud console for promotional offers.
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
Billing item | Price (USD) | Unit |
|---|---|---|
Video generation (480P) | 0.068 | Per second |
Video generation (720P) | 0.14 | Per second |
Video generation (1080P) | 0.28 | Per second |
Rate limits
- Singapore
- China North 2 (Beijing)
- Germany (Frankfurt)
- China (Hong Kong)
- Japan (Tokyo)
- US (Virginia)
Parameter | Value |
|---|---|
RPM (Requests per minute) | 300 |