Alibaba (Qwen) · video model · Released Jul 28, 2025Wan 2.2 A14B
Wan 2.2 A14B is a video model from Alibaba (Qwen), released Jul 28, 2025. It handles text to video.
- Arena score
- 1,170#43 of 48 · image to video
- Starting price
- —Not published
- Longest clip
- —Not published
- Resolution
- —No audio track
How it rates and what it costs
- Text to video arena
- 1,132 ±15#42 of 48 · 10,458 votes
- Image to video arena
- 1,170 ±10#43 of 48 · 27,054 votes
Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Sep 22, 2026.
The details
- Lab
- Alibaba (Qwen)
- Type
- Video model
- Released
- Jul 28, 2025
- Inputs
- Text prompts
- Output
- Video
- Can do
- Text to video
- Weights
- Open weights
- Availability
- 1 API host
More video models from Alibaba (Qwen)
About Wan 2.2 A14B
How good is Wan 2.2 A14B?
In blind side-by-side votes, Wan 2.2 A14B scores 1,132 for text to video (#42 of 48) and 1,170 for image to video (#43 of 48). Higher is better; scores within about 30 points of each other are effectively tied.
Who makes Wan 2.2 A14B?
Wan 2.2 A14B is a video model from Alibaba (Qwen), released Jul 28, 2025.
What can Wan 2.2 A14B do?
Wan 2.2 A14B accepts text prompts and produces video. In practice: text to video.
Is Wan 2.2 A14B open source?
Yes. Alibaba (Qwen) publishes the weights, so you can run it on your own hardware.
Where can I use Wan 2.2 A14B?
It is listed by 1 API host we track.
What are the alternatives to Wan 2.2 A14B?
The closest video models from other labs, by release date, are Seedance v1.0 Pro (ByteDance Seed, Jun 11, 2025), Veo 3.0 Fast (Google, Jul 31, 2025), Sora 2 (OpenAI, Oct 6, 2025) and Kling v2.5 Turbo (Kling AI, Sep 23, 2025).