Back to feed
News Story
APriority76
小互 (X)
1 sources

Alibaba Releases Wan3.0: Native 30-Second Video Generation with Multi-Format Reference

Alibaba has released Wan3.0, an AI model that generates native 30-second videos with realistic rendering and all-in-one reference capabilities, supporting text, images, audio, video, and additional formats like documents, spreadsheets, slides, and web pages. The model offers 480p and 720p resolutions at $0.05/sec and $0.10/sec respectively.

SynthePulse Insight · AI deep reading

Alibaba Wan3.0 Released: Native 30-Second Video Generation, Pricing and All-Round References Highlighted

Version 1 · 1 source

Alibaba releases Wan3.0, supporting native 30-second video generation, realistic rendering, and expanding reference inputs to documents, spreadsheets, slides, etc. Pricing is $0.05 per second for 480p and $0.10 per second for 720p.

  • Wan3.0 supports native 30-second video generation, completed in a single run.
  • Rendering quality is described as 'realistic,' but specific technical details are not disclosed.
  • Reference inputs are no longer limited to text, images, audio, and video; they also include documents, spreadsheets, slides, web pages, etc.
  • Supported input formats include doc, xls, ppt, pdf, txt, key, pages, numbers, md, url.
  • Pricing is $0.05 per second for 480p and $0.10 per second for 720p.
  • Experience is available at Alibaba Cloud Model Studio and Qwen Cloud.
Open section navigationRelease Overview

Release Overview

Alibaba released Wan3.0 on August 6, 2026, an AI video generation model featuring native 30-second video generation and realistic rendering.

The release information was disseminated through the social media account 'Xiao Hu,' which is a third-party retelling; specific technical details and official announcements have not been directly confirmed.

Core Capabilities: Native 30 Seconds and All-Round References

Wan3.0's most prominent feature is native 30-second video generation, meaning it can generate videos up to 30 seconds in a single run without stitching or multiple generations.

The rendering quality is described as 'realistic,' but no specific technical metrics or comparative data are provided; this description is a claim from the source.

In terms of reference capabilities, Wan3.0 supports more input types beyond text, images, audio, and video, including documents, spreadsheets, slides, web pages, etc. Specific formats include doc, xls, ppt, pdf, txt, key, pages, numbers, md, url.

Pricing and Availability

Pricing is per second: $0.05 per second for 480p resolution and $0.10 per second for 720p resolution.

Experience is available at Alibaba Cloud Model Studio (modelstudio.console.alibabacloud.com/ap-southeast-1…) and Qwen Cloud (qwencloud.com/models/wan3.0-…), but specific available regions and complete links are not fully disclosed.

Credibility boundary

This report is based on information from the third-party social media account 'Xiao Hu' and is a retelling; it has not obtained official announcements or first-hand materials from Alibaba. All feature descriptions and pricing are claims from the source, and actual performance, availability, and prices may be adjusted.

Insight takeaway

Wan3.0 shows differentiation in video generation duration and reference input types, but it awaits official confirmation and real-world testing.

Primary report

小互 (X)

Primary source