V6 is a new model launched by PixVerse at the end of March 2026. The kf2v (first-and-last-frame-to-video) model connects any two images with smoother, more natural video transitions. Supports 15-second videos, direct output of music and video, and text in multiple languages.
Inference Service Provider
The inference service provider for pixverse/pixverse-v6-kf2v is PixVerse.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Image Text | Output Modality | Video |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | — | Max Output Length | — |
Context Window | — |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit QwenCloud console for promotional offers.
- Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Video Generation(360P) | 0.032 | Per second |
Video Generation(540P) | 0.04 | Per second |
Video Generation(720P) | 0.054 | Per second |
Video Generation(1080P) | 0.103 | Per second |
Video Generation(360P no audio) | 0.023 | Per second |
Video Generation(540P no audio) | 0.032 | Per second |
Video Generation(720P no audio) | 0.04 | Per second |
Video Generation(1080P no audio) | 0.08 | Per second |
Rate Limits
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 300 |