Wan 3 Video is Alibaba's video generation model. A multimodal video generation model that supports text-to-video, image-to-video, and reference-based generation with synchronized audio output.
Specifications
Canonical IDalibaba-wan-3-video
TypeVideo Generation
StatusActive
CreatorAlibabaAlibaba
Providers
Input ModalitiesImage
Output ModalitiesVideo
Release Date · 9 days ago

Capabilities

Input1/5
Text·
Image
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Vercel AI Gateway logo
Vercel AI Gateway
alibaba/wan-v3.0-video

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Wan 3 Video PrimeAvailable
Wan 3 VideoCurrent
Wan 2.7 R2VAvailable
Wan 2.7 T2VAvailable
Wan 2.6 I2VAvailable
Wan 2.6 I2V FlashAvailable
Wan 2.6 R2VAvailable
Wan 2.6 R2V FlashAvailable
Wan 2.6 T2VAvailable
Wan 2.5 T2V PreviewAvailable
Wan 2.1 1.3B T2VAvailable

Model IDs

alibaba-wan-3-video
alibaba/wan-v3.0-video