Video model · Alibaba ·
Wan 3.0 is a video model by Alibaba. In Endless it costs from 16 credits per video and is available on the Hobby plan and up.
Wan 3.0 is Alibaba's video model for 2 to 30 second clips with sound from text or image, video and audio references, at a lower cost than Prime.
From 16 credits per video
Wan 3.0 is Alibaba's all-in-one video model, launched in August 2026. Text-to-video, image-to-video and reference-to-video, separate models in Wan 2.x, now live in one model. Clips run from 2 to 30 seconds at 480p, 720p or 1080p and 30 fps.
Combine references in one prompt: up to 10 images for subject, style and composition, a clip of up to 15 seconds for motion and framing, and up to five audio clips, 15 seconds combined, that drive timing and lip sync. Refer to them by position, as in 'the subject in Image 1 walks past Video 1'. Or attach one image as the first frame and animate it.
Sound is generated in the same pass as the picture; write dialogue as quoted lines in the prompt, or turn audio off. Wan 3.0 Prime is the high-speed version of the same model: the same capabilities and a shorter wait, at a higher price per second. Choose Wan 3.0 when cost matters more than turnaround.
In your workspace, open Video and pick Wan 3.0 in the model picker.
Write a prompt with the subject, camera and motion, or start from an image you upload or generate.
Generate, then refine in chat or on a canvas. Every clip is saved to your workspace assets.
by Alibaba
Up to 30 seconds with sound, mixing image, video and audio references
From 17 credits per video
by ByteDance
30-second clips in one pass, guided by up to 50 references
From 51 credits per video
by Google
Video and sound in one pass, 3 to 10 seconds up to 4K, with clip editing
From 14 credits per video
Wan 3.0 is on the Hobby plan and higher. Create a free workspace to try the other models first, then upgrade when you need it.