Wan 3.0 is the 2026 flagship video model from Alibaba's Tongyi Lab, and unlike the Wan models that made the family famous, it is API-only: there are no published weights to download.
That single fact is the thing most write-ups get wrong, so it is worth stating up front. It is now on the 8frame canvas in two variants, priced per second of output: the base model from 24 credits for a 5-second 480p clip, and the Prime tier at a flat 34 credits for 5 seconds regardless of resolution. Everything below separates what we verified ourselves from what Alibaba claims for the model.
What is actually verifiable
No open weights. We queried the Hugging Face API for the Wan-AI organization on 2026-08-28. The newest published repositories are all in the Wan 2.2 line (the most recent upload being Wan2.2-Animate-2-14B-Distilled-Diffusers, 2026-08-06). There is no Wan 2.5 repo and no Wan 3.0 repo. You can run that check yourself in one request against huggingface.co/api/models?author=Wan-AI.
It reached Western infrastructure in late August 2026. Wan 3.0 first shipped in public beta on Alibaba's own cloud in early August. Our catalog sweep on 2026-08-24 found alibaba/wan-3.0/* and a separate alibaba/wan-3.0-prime/* tier active on fal with no published prices; the rates surfaced on 2026-08-28 (Prime through fal's pricing API, the base model through Replicate's alibaba/wan-3), and both are now on the canvas.
The open Wan line stopped at 2.2. Wan 2.1 and Wan 2.2 shipped with downloadable weights under Apache 2.0. Wan 2.5 was announced but never published weights, and Wan 3.0 continued that pattern. If someone tells you Wan 3.0 is open source, ask them for the repository link.
What Alibaba claims for the beta
The beta materials describe three headline changes over Wan 2.5: clips around 30 seconds generated in a single pass rather than stitched, output up to 1080p with synchronized audio produced in the same pass, and reference inputs that go beyond text and images to documents, spreadsheets, slides, PDFs, and web pages. That last one is the genuinely novel piece. Every other major model in 2026 takes text, images, and sometimes video as conditioning. Turning a deck into a video is a different input class.
We have not tested any of it, so treat those as vendor claims until someone runs a side-by-side.
Which Wan you can actually run today
| Model | Weights | Duration | 8frame price (5s) |
|---|---|---|---|
| Wan 2.2 | Apache 2.0, on Hugging Face | 5s tiers | 50 credits at 720p |
| Wan 2.5 | Not published | 5 / 10 / 15s | 102 credits at 1080p |
| Wan 3.0 | Not published | 2 to 30s | 24 at 480p, 48 at 720p, 95 at 1080p |
| Wan 3.0 Prime | Not published | 2 to 30s | 34 credits, flat across resolutions |
Credits cost $0.01 each in a top-up pack, so the cheapest Wan 3.0 clip is about $0.24 and a 5-second Wan 2.5 clip is about $1.02. The $19 Starter plan carries 1,000 credits a month. The number worth noticing: Wan 3.0 goes to 30 seconds in a single pass, and 30 seconds on Prime is 203 credits, roughly $2.
Related concepts
Wan 3.0 pricing explained covers the two variants and where each one is cheapest. Wan 3.0 vs Wan 2.5 is the upgrade question. Is Wan 3.0 open source walks through the license question with the receipts, and what is Wan covers the family's history.
Run Wan 3.0 from 24 credits a clip on the 8frame canvas alongside every other major model. The canvas is free and unlimited; generation is paid from $19/month. See how the field compares on identical prompts in best AI video generator 2026.