Wan API
Wan by Alibaba generates videos up to 30 seconds with native audio from text, frames or references, plus video editing, extension and image generation.
Explore the model lineup
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
Wan 3.0 Text to Video
Wan 3.0 by Alibaba turns a text prompt into a video of up to 30 seconds at 30fps, with native dialogue, music, and sound effects.
Wan 3.0 Video
Alibaba Wan 3.0 Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio.
Wan 3.0 Image to Video
Wan 3.0 by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Wan 3.0 Video Edit
Wan 3.0 Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.
Wan 3.0 Reference to Video
Wan 3.0 by Alibaba generates up to 30-second videos with native audio from reference images, videos, and audio, keeping subjects, motion, and voice consistent with the references.
Wan 3.0 Video Extend
Wan 3.0 Video Extend by Alibaba continues an input video forward from a text instruction, optionally guided by reference images and audio, with native audio.
Wan 3.0 Prime Text to Video
Wan 3.0 Prime by Alibaba turns a text prompt into a video of up to 30 seconds at 30fps, with native dialogue, music, and sound effects.
Wan 3.0 Prime Video
Alibaba Wan 3.0 Prime Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio.
Wan 3.0 Prime Image to Video
Wan 3.0 Prime by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Wan 3.0 Prime Video Edit
Wan 3.0 Prime Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length.
Wan 3.0 Prime Reference to Video
Wan 3.0 Prime by Alibaba generates up to 30-second videos with native audio from reference images, videos, and audio, keeping subjects, motion, and voice consistent with the references.
Wan 3.0 Prime Video Extend
Wan 3.0 Prime Video Extend by Alibaba continues an input video forward from a text instruction, optionally guided by reference images and audio, with native audio.
Wan 2.7 Text to Image
Alibaba Wan 2.7 text-to-image model with high-quality generation and selectable aspect ratio.
Wan 2.7 Text to Video
Alibaba Wan 2.7 text-to-video model with cinematic visuals, native audio generation, and configurable duration and resolution.
Wan 2.7 Pro Text to Image
Alibaba Wan 2.7 Pro text-to-image model with enhanced quality and selectable aspect ratio.
Wan 2.7 Pro Image to Image
Alibaba Wan 2.7 Pro image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.
Wan 2.7 Image to Image
Alibaba Wan 2.7 image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.
Wan 2.7 Image to Video
Alibaba Wan 2.7 image-to-video model transforming still images into video with native audio generation.
Wan 2.7 Video Edit
Alibaba Wan 2.7 video editing model.
Wan 2.7 Reference to Video
Alibaba Wan 2.7 reference-to-video model generating video guided by reference content.
Wan 2.7 Video Extend
Alibaba Wan 2.7 Video Extend continues an input clip from a text instruction, optionally ending on a chosen last frame, for a total length of up to 15 seconds.
Wan 2.6 Text to Video
Alibaba Wan 2.6 text-to-video model with cinematic visuals, configurable duration (5 or 10 seconds) and resolution.
Wan 2.6 Text to Image
Alibaba Wan 2.6 text-to-image model with high-quality generation and selectable aspect ratio.
Wan 2.6 Image to Image
Alibaba Wan 2.6 image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.
Wan 2.6 Image to Video
Alibaba Wan 2.6 image-to-video model transforming still images into video. Supports first-frame-to-video only.
Wan 2.6 Flash Image to Video
Wan 2.6 Flash by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Wan 2.6 Reference to Video
Alibaba Wan 2.6 reference-to-video model generating video guided by reference content.
Wan 2.6 Flash Reference to Video
Alibaba Wan 2.6 Flash reference-to-video model that places characters from reference images or videos into a new scene, with optional generated audio and multi-shot control.
Model lineup
The most used endpoints first.
| Model | Task | What it does |
|---|---|---|
| Wan 3.0 Video | Text → video | Alibaba Wan 3.0 Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio |
| Wan 2.7 Image to Video | Image → video | Alibaba Wan 2.7 image-to-video model transforming still images into video with native audio generation |
| Wan 3.0 Prime Video | Text → video | Alibaba Wan 3.0 Prime Video generates videos up to 30 seconds with native audio from text, a first/last frame, or reference images, videos, and audio |
| Wan 2.7 Text to Video | Text → video | Alibaba Wan 2.7 text-to-video model with cinematic visuals, native audio generation, and configurable duration and resolution |
| Wan 2.7 Reference to Video | Reference → video | Alibaba Wan 2.7 reference-to-video model generating video guided by reference content |
| Wan 2.6 Image to Video | Image → video | Alibaba Wan 2.6 image-to-video model transforming still images into video |
| Wan 2.6 Reference to Video | Reference → video | Alibaba Wan 2.6 reference-to-video model generating video guided by reference content |
| Wan 3.0 Text to Video | Text → video | Wan 3.0 by Alibaba turns a text prompt into a video of up to 30 seconds at 30fps, with native dialogue, music, and sound effects |
| Wan 3.0 Image to Video | Image → video | Wan 3.0 by Alibaba - animate still images into dynamic videos with AI |
| Wan 3.0 Video Edit | Video → video | Wan 3.0 Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping… |
| Wan 3.0 Reference to Video | Reference → video | Wan 3.0 by Alibaba generates up to 30-second videos with native audio from reference images, videos, and audio, keeping subjects, motion, and voice… |
| Wan 3.0 Video Extend | Video → video | Wan 3.0 Video Extend by Alibaba continues an input video forward from a text instruction, optionally guided by reference images and audio, with… |
Alibaba's video and image family
Wan covers video generation, editing and extension, as well as text-to-image and image editing.
Versions
- Wan 3.0 and 3.0 Prime: up to 30 seconds at 30fps with native dialogue, music and sound effects, from text, a first/last frame, or reference images, video and audio. Edit and Extend endpoints keep or continue the original clip.
- Wan 2.7: text, image and reference to video with native audio, video edit, extension up to 15 seconds, plus text-to-image and image editing (Standard and Pro).
- Wan 2.6: 5 or 10 second clips, a Flash tier, and image generation and editing.
The unified Wan 3.0 Video endpoint accepts all input modes in one model. For Alibaba's language models, see Qwen.
Start using Wan API on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model alibaba/wan/3.0/video. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "alibaba/wan/3.0/video", "prompt": "A plush toy astronaut floats through a cosy knitted galaxy, playful FPV camera"}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
What is the difference between Wan 3.0 and 3.0 Prime?
Both accept the same inputs and cover the same tasks. Prime is a separate tier with its own price; compare outputs and prices on the model cards.
How long can Wan videos be?
Up to 30 seconds on Wan 3.0. Wan 2.7 Extend reaches up to 15 seconds total, and Wan 2.6 generates 5 or 10 second clips.
Can Wan edit an existing video?
Yes. Wan 3.0 Video Edit restyles or modifies a clip from an instruction and keeps its length. Wan 2.7 also has a Video Edit endpoint.
Does Wan generate images?
Yes. Wan 2.7 and 2.6 include text-to-image and image-to-image endpoints.
Build with Wan API.
One key, consistent APIs, and usage-based pricing across every model on this page.