The AI arena is free today

Open Superagent
AI Organization10 models

WAN Video: AI models, benchmarks & research

WAN Video AI - Advanced video generation models

Open-weightMultimodalVideo generation
Model
WAN 3.0VideoNew
WAN 3.0 PrimeVideoNew
WAN 2.7Video
Wan AnimateVideo
WAN Video 2.6Video
WAN Video 2.6 I2VVideo
Wan 2.2 A14BVideo
Wan 2.1 14BVideo
WAN Video 2.5 Image-to-VideoVideo
WAN Video 2.5 Text-to-VideoVideo
At a glance

WAN Videomodels, benchmarks & research

Key facts about WAN Video's portfolio of 10 AI models — sourced from public benchmarks, provider APIs, and model releases.

Models
10 models across 0 families
Portfolio
10 video models
Licensing
8 open-weight, 2 proprietary

Top benchmark scores

No benchmark data yet.

Largest models

No parameter data.

Most affordable

No public pricing data.

FAQ

Common questions about WAN Video.

What is WAN Video?

WAN Video is an AI research organization that develops large language models and other AI systems. They have released 10 models across 0 model families.

How many AI models has WAN Video released?

WAN Video has released 10 AI models tracked on LLM Stats. See the Models tab for the full catalog with technical specifications, benchmark scores, and pricing.

Does WAN Video release open-weight models?

Yes. 8 of WAN Video's 10 models are released under open-weight licenses, while 2 are proprietary. Check the Models tab for per-model license details.

How can I use WAN Video's models?

Visit https://replicate.com/wan-video for official documentation and API access. Many of WAN Video's models are also available through third-party API providers — check the Pricing tab to compare pricing across providers.