wan
Wan is Alibaba Cloud Bailian's video generation model family, covering text-to-video, image-to-video (first/last frame), reference-to-video (multimodal input), video editing and digital humans, up to 30 seconds per generation.
Text-to-video; image-to-video (first/last frame); reference-to-video (image/video/audio/file/web multimodal references); video editing (instruction editing, local replacement); video extension; digital human (image + audio driven).
Commercial ads, film production, social media marketing, brand promotion, e-commerce, digital human broadcasting.
Asynchronous generation (1-5 min); result URL and task_id valid for 24h; reference material count/duration limits; direct upload of real-face material not supported (compliance solutions available).
| Model | Input / 1M | Output / 1M | Cache Read / 1M | Per 1M |
|---|---|---|---|---|
| — | — | 1M | ||
| — | — | 1M | ||
| — | — | 1M | ||
| — | — | 1M | ||
Wan2.7 T2v wan2.7-t2v-2026-06-12 |
| — |
720P$0.0897/sec 1080P$0.1495/sec |
| — |
| 1M |
Wan3.0 video wan3.0-video | — | 480P$0.0448/sec 720P$0.0897/sec 1080P$0.1794/sec | — | 1M |
Wan2.2 Animate Mix wan2.2-animate-mix | — | Standard Mode$0.0896/sec Pro Mode$0.1343/sec | — | 1M |
Wan2.2 Animate Move wan2.2-animate-move | — | Standard Mode$0.0597/sec Pro Mode$0.0896/sec | — | 1M |