Post-Cutoff
Search For AI agents

Alibaba Cloud (Tongyi Lab)Wan familyCurrentVideo generationReleased 24 Aug 2026

Wan 3.0

Alibaba’s closed Wan 3.0 video model: up to 30 s, 1080P, native audio, inputs from text, images, video, audio, documents and web pages. Asynchronous DashScope API (create a task, then poll by task_id; result URLs expire after 24 h).

Model idwan3.0-video

Price$0.05 per second 480p

Checked25 October 2026

Where it stands

5newer video generation models since its release

All video generation models

Weights
Closed weights; access is hosted only.

How to call it

5 ways to use Wan 3.0, with the model id each provider expects.

Providers, model ids, endpoints and docs for Wan 3.0
ProviderModel idEndpointDocs
Alibaba Cloud Model Studio (DashScope) wan3.0-video https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis alibabacloud.com
Alibaba Cloud Model Studio (faster Prime tier) wan3.0-video-prime alibabacloud.com
Qwen Cloud wan3.0-video qwencloud.com
OpenRouter alibaba/wan-3.0
OpenRouter (Prime) alibaba/wan-3.0-prime

Pricing

Prices for Wan 3.0
Per second 480p$0.05
Per second 720p$0.10
Per second 1080p$0.20

As published: “USD per second, Singapore (International) region list price for wan3.0-video, with a limited-time 30% discount shown; other regions 0.041/0.083/0.165 per s. Prime (faster) variant wan3.0-video-prime 0.068/0.14/0.28 per s in Singapore. Input + output video duration both billed; failed requests free”.

Source: alibabacloud.com, checked 25 October 2026.

Specs

Input
Text, images, video, audio and PDF
Output
Video and audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
24 August 2026
Status
Current
Type
Video generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • 30-second single-pass clips with native audio

    Up to 30 s per generation (2-30 s or smart duration) at up to 1080P, with dialogue, music and sound effects generated together; double Wan 2.7’s 15 s limit.

    Source: alibabacloud.com

  • Documents and web pages as input

    First

    Besides text, images, video and audio, one request can take a file (pdf, docx, pptx, xlsx, txt, md) or a public web link as source material for the video.

    Source: alibabacloud.com

  • Multi-reference generation and editing

    Up to 20 references per request (10 images, 5 videos, 5 audio clips, 15 s total each for video/audio), plus first/last-frame modes and editing of an existing generation.

    Source: alibabacloud.com

Notes

Artificial Analysis text-to-video leaderboard (read 2026-10-25): #1, Elo 1175; AA price 12.00 USD per minute of 1080p (= 0.20/s). Public beta from early Aug 2026 (application-based), GA on Model Studio 2026-08-24 (CNY 0.3/0.6/1.2 per s for 480P/720P/1080P). Prime has the same capabilities as standard, only faster and pricier (Alibaba blog 2026-10-07). Async API: create task with X-DashScope-Async: enable, poll /api/v1/tasks/{task_id}; host is region-specific. Closed weights (Wan 2.2 was the last open-weight Wan flagship). Alibaba says audio texture and in-video text accuracy still need work. ‘first: true’ for document input is Alibaba’s framing, not independently checked. No timeline entry exists yet.

Artificial Analysis text-to-video (with audio) leaderboard, read 2026-10-25: rank 1, Elo 1175 (https://artificialanalysis.ai/video/leaderboard/text-to-video).

Sources: https://www.alibabacloud.com/en/news/product/video-generation-model-wan30-officially-launched-nsb · https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide · https://www.alibabacloud.com/help/en/model-studio/model-pricing · https://www.alibabacloud.com/blog/603618 · https://www.alizila.com/alibaba-unveils-wan3-0-with-twice-as-long-video-outputs-from-a-richer-variety-of-inputs/ · https://thenextweb.com/news/alibaba-wan3-video-model-after-share-sale