Wan 3.0 now available on AI Gateway

Alibaba's Wan 3.0 video generation model is now available on Vercel's AI Gateway as `alibaba/wan-v3.0-video`, supporting text-to-video, image-to-video, first/last frame conditioning, and reference-based generation with clips up to 30 seconds at 30fps in 480p, 720p, or 1080p, with audio by default. The gateway introduces three asynchronous generation routes—poll, experimental_startVideo, and webhook—to handle background jobs, and the model can be tried in the playground.

Wan 3.0 from Alibaba https://vercel.com/ai-gateway/models/wan-v3.0-video is now available on AI Gateway as alibaba/wan-v3.0-video . One model covers text to video, image to video, first and last frame conditioning, and reference-based generation, and it takes image, video, and audio as references. Clips run up to 30 seconds at 30fps, in 480p, 720p, or 1080p, and the output carries audio by default. That consolidates what took several models before. Wan 2.7 shipped as separate -t2v and -r2v IDs, each capped at 15 seconds and 24fps. Try the new asynchronous generation https://vercel.com/docs/ai-gateway/modalities/video-generation asynchronous-generation on AI Gateway, which runs the job in the background instead of holding a request open. Three routes do it, and they differ in what waits. Pass poll and the gateway tracks the generation while the SDK makes short status requests until it lands. This is the smallest change from a plain call. experimental startVideo returns as soon as the gateway accepts the job, so nothing waits and the job outlives the process that started it. That suits serverless functions, queues, and fanning out a batch. Or pass a webhook and the gateway posts one event to your endpoint when the generation lands, so nothing polls at all. The docs cover all three, including how to verify a delivery https://vercel.com/docs/ai-gateway/modalities/video-generation verifying-the-delivery . Pass references under inputReferences , each with its URL and media type, and describe the scene in the prompt. The limits differ by kind. Audio references have to be hosted URLs, where images also accept base64. First and last frame conditioning takes one image each and cannot be combined with references. You can also try Wan 3.0 with no code in the model playground https://vercel.com/ai-gateway/models/wan-v3.0-video . To see more, browse all video models https://vercel.com/ai-gateway/models?type=video .