Wan Video Models by Alibaba
AlibabaProprietary
Alibaba releases · 54 in the last 12 months · this family litChangelog →
1 model2026
Last refreshed 2026-10-19. Next refresh: weekly.
Capabilities
VisionAll models
MultimodalAll models
Links
WebsiteAbout
Alibaba Tongyi's Wan video generation model family, the video side of the Wan multimodal line (alongside Wan Image). Wan 3.0 is the GA video model: up to 30-second clips with omni-reference input, native audio sync, and 480p/720p/1080p output, billed per generated second on Alibaba Cloud Model Studio.
Decision facts
- Best fit
- video generationvision and multimodal work
- Capability starting point
- Wan 3.0 with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Ovis Image
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Wan 3.0Current
Use when the workload needs video generation, multimodal inputs, and audio.
2026-08video generationmultimodal inputsaudio
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Wan 3.0 | Use when the workload needs video generation, multimodal inputs, and audio. | 2026-08 | video generationmultimodal inputsaudio | Current |
Release Timeline
1 release group2026-08
1 current
Wan 3.0
Currentvideo generationmultimodal inputsaudio
Specifications(1 models)
| Model | Released | Vision | Multimodal |
|---|---|---|---|
| Wan 3.0 | 2026-08 | Yes | Yes |





