Wan models on AI Gateway
By Steven Van ·
Alibaba's Wan video models join AI Gateway in beta, open to Pro and Enterprise plans and paid AI Gateway users via AI SDK 6 or the playground.
Alibaba's Wan models are now available through Vercel's AI Gateway, adding text-to-video, image-to-video, and reference-to-video generation. The models produce stylized videos with smooth motion and can use existing footage or images to keep new scenes consistent.
- Character Reference (R2V): extracts character appearance and voice from reference videos or images to generate new scenes
- Flash variants: faster generation for quicker iteration
- Flexible resolutions: 480p, 720p, and 1080p output
Video generation is in beta, available on Pro and Enterprise plans and to paid AI Gateway users. Models can be called programmatically with AI SDK 6's generateVideo function, or tried without code in the AI Gateway playground embedded on each model's page, which lets users compare providers, tweak prompts, and download results. Available models include alibaba/wan-v2.6-t2v, alibaba/wan-v2.6-i2v, alibaba/wan-v2.6-i2v-flash, alibaba/wan-v2.6-r2v, alibaba/wan-v2.6-r2v-flash, and alibaba/wan-v2.5-t2v-preview.