Wan Video is Alibaba Tongyi Lab's video generation model family (Wan3.0 as of August 2026), available via wan.video and Alibaba Cloud Model Studio. It generates up to 30-second clips with native audio-visual output from text, image, audio, video, and document inputs, with built-in editing and multi-modal reference.
Alternatives & similar tools
Related picks from editorial notes.
Also mentioned
Kling AI
PixVerse
Google Veo
Runway Gen models
Seedance / Luma Dream Machine
Features & details
Full overview from our catalog (read-only reference).
Category (short)
AI Video Generation
Category
AI Video Generation
Pricing (CSV)
Free Trial
Directory pricing
Freemium
Sponsored note
no
Target audience
Builders and studios that want long single-shot AI video (up to 30s) and document-to-video via Alibaba Cloud. Not ideal for: users who want a simple Western SaaS checkout with one flat consumer SKU and no cloud account.
Best for
Builders and studios that want long single-shot AI video (up to 30s) and document-to-video via Alibaba Cloud. Not ideal for: users who want a simple Western SaaS checkout with one flat consumer SKU and no cloud account.
Pricing notes
Verified August 2026 at https://modelstudio.alibabacloud.com/intl/blog/wan3-ai-video-generation-model/ and https://modelstudio.console.alibabacloud.com/model-releases/wan3.0-video. Wan3.0 API list prices: $0.05/sec (480P), $0.10/sec (720P), $0.20/sec (1080P). Console also showed time-limited ~30% offer pricing ($0.035 / $0.07 / $0.14 per sec until Sep 24, 2026 UTC+8) — final bill subject to console. wan.video is the brand/product front end; public self-serve consumer subscription ladder was not clearly published on the fetched brand page (heavy client JS). Also available inside Alibaba Cloud AI Token Plans. Confirm regional console rates before production budgets.
Pros & cons
Editorial notes to help compare fit before opening the vendor site.
Pros
30-second generations beat many short-clip-only models
Document-to-video is a practical differentiator
Transparent per-second API list prices
Strong multimodal reference and edit/extend story
Cons
Requires Alibaba Cloud / regional account friction for many Western users
Consumer wan.video pricing less transparent than API docs
Audio texture and on-screen text called out as still improving
Promo vs list price can confuse cost estimates
Review notes
Context from the listing review and editorial research.
NEW tool. DISAMBIGUATION: Wan / Wanx / Tongyi Wanxiang video family from Alibaba — not an unrelated "WAN" networking acronym. Closest directory peers are Kling, Veo, PixVerse. Prefer Name "Wan Video" for slug clarity.
Extended features
In-depth description and capability notes.
Up to 30-second single-pass generation (Wan3.0)
Text, image, audio, video, and document-to-video (PPT/PDF/DOC/XLS and more)
First-frame / first-last-frame and multi-modal reference
Native dialogue, BGM, and SFX in generation
Video edit/extend without full regeneration
Resolutions 480P / 720P / 1080P
API model ID wan3.0-video (plus Prime/faster variants)
Consumer brand site at wan.video; developer path via Model Studio / DashScope
Use cases
Developers and creators generate longer story-length AI clips, turn decks or docs into video briefs, and iterate with reference consistency for ads, shorts, and product storytelling through Alibaba's API or the Wan web product.