[ video model ]

Wan 3.0

Alibaba (Wan 3.0)

Alibaba's newest Wan: first-frame and multi-reference video, with sound at no extra charge. Alibaba Wan 3.0 — first-frame and multi-reference video, audio at the same price.

Using Wan 3.0 in uooki

uooki has no model picker. You name the model in the conversation and the agent routes to it — “make the clip with Wan 3.0” is the whole interface. Common spellings and older ids resolve to the same model, so you do not have to match our internal naming.

Leave the model out and the agent picks one for you based on what you asked for. Naming it is for when you have a reason to — this page is about those reasons.

What it is good at

  • Short clips from a first frame, with sound included
  • Clips built from several reference images, up to ten
  • Chinese-context scenes, and motion styling outside the Kling and Seedance houses

Where it is not the right pick

uooki runs it at 720p; the upstream default is 1080p, which costs twice as much. A first frame and reference images are two different modes: one image animates that frame, several images are references the model interprets freely.

When to reach for something else

  • Hailuo 2.3

    Cost matters more than the motion styling.

  • Seedance 2.5

    You need more than ten reference images.

  • Kling V3

    You want the top-ranked text-to-video model.

Specifications

TypeVideo generation
BillingBilled per second of video generated.
PlanAvailable on every plan
AudioYes — generated with sound
Reference imagesUp to 10
CreditsSee pricing

Specifications are read from uooki’s model registry, not written by hand — if the registry changes, this table changes with it.

Model id

What uooki calls upstream when you pick Wan 3.0. You never need this to use it — it is here so the vendor name and the actual model are unambiguous.

apimartwan3.0-video

Try it in a sentence.

Describe what you want and name Wan 3.0 in the same breath. The Free plan is $0 and starts with 100 one-time credits.