Models/Collections/Wan

Wan

From Alibaba's Tongyi lab, one of the most prolific open-weight publishers in AI (Wan, Qwen). Strong video and image generation, with open-weight releases you can self-host.

Models

All-in-one multimodal video generation with native 30-second clips, large reference capacity, and precise video editing

$0.05/ second480p
Run

Lower-latency Wan3.0 video generation with the same multimodal workflows and output quality

$0.068/ second480p
Run

Multimodal video generation with reference consistency, video editing, and native audio

$0.10/ second720p
Run

Unified image generation and editing with avatar customization, color control, and multilingual text rendering

$0.03/ image
Run

Premium image generation with enhanced composition stability and precise prompt comprehension

$0.075/ image
Run

High fidelity image generation built on the Wan2.6 visual stack

$0.03/ image
Run

Fast distilled image-to-video generation model

$0.05/ second720p · audio
Run

Multimodal video generation with multi-shot and native sound

$0.10/ second720p
Run

Wan2.5-Preview AI Text to Video with Native Audio

$0.0946/ second720p
Run

High fidelity Wan2.5 image generation for rich single frames

$0.027/ image
Run

Model guides

Wan3.0

Prompting Wan 3.0

How to write prompts for Wan 3.0 that get you the shot: how the model reads layered directives, camera language, style and register range, directing native audio, and the dimensions and duration rules.

Read the guide →
Wan3.0

Image inputs with Wan 3.0

How to use images with Wan 3.0's video generation: pin an image as the first frame, morph between two frames, and carry subject or product identity across new scenes with reference images.

Read the guide →
Wan3.0

Video and audio references with Wan 3.0

How to use video and audio references with Wan 3.0: carrying a subject across new scenes with referenceVideos, driving video from an audio source with referenceAudios, and combining multiple reference types in one call.

Read the guide →
Wan3.0

Document and web inputs with Wan 3.0

How to turn structured content into video with Wan 3.0: recipes as cooking videos and public webpages as short landmark or historical montages.

Read the guide →