Wan 3.0 now available on AI Gateway
Wan 3.0 just shipped on AI Gateway: text-to-video, image-to-video, and reference-based generation in one model — up to 30 seconds at 1080p with synced audio.
Why it matters
Alibaba's upgraded video model is now available through Vercel's AI Gateway with significant improvements over v2.7 (longer clips, higher res, async generation, unified model IDs). Practitioners building video features get a more capable, easier-to-integrate option.
The key facts
13 to knowWan 3.0 generates up to 30 seconds at 30 fps (vs. Wan 2.7's 15 seconds at 24 fps)
Supports 480p, 720p, and 1080p output with synchronized audio
Combines text-to-video, image-to-video, first/last-frame conditioning, and reference-based generation in single model
Asynchronous generation and webhook support reduce integration friction
References can include images (URL or base64), video, and audio (hosted URLs)
Available on AI Gateway and Vercel model playground
Wan 3.0 available on Vercel AI Gateway
Unified model: text-to-video, image-to-video, first/last-frame conditioning, reference-based generation
Up to 30 seconds at 30 fps (Wan 2.7 was 15 seconds at 24 fps)
Resolution support: 480p, 720p, 1080p with synchronized audio
Asynchronous generation with webhook support
Accepts image, video, and audio references
First/last-frame conditioning for controlled generation
Go to the source
Vercel Blogvercel.com
Publisher excerpt: is now available on AI Gateway as .Wan 3.0 from Alibabaalibaba/wan-v3.0-video Wan 3.0 combines text-to-video, image-to-video, first- and last-frame conditioning, and reference-based generation in one model. References can include images, video, and audio. It generates clips up to 30 seconds at 30…