Wan3.0 API redefines multimodal video creation. Experience the next evolution of video generation, combining longer narratives, stronger reference consistency, precise editing, and immersive audiovisual creation for more complete visual storytelling. Live on KLIFGEN now — no subscription, just pay per use with credits from 40 credits a clip.
Wan3.0 is Alibaba's latest all-in-one video generation model, designed for longer-form storytelling, richer reference understanding, stronger visual consistency, and more precise creative control. Wan3.0 API enables creative generation based on different types of input materials, including text, images, audio, keyframes, documents, and webpages, helping shape scenes, motion, sound, visual identity, and narrative direction through more flexible references.
Text can do far more than describe a simple scene. With Wan 3.0 API, written instructions can shape characters, environments, camera movement, action logic, lighting, pacing, atmosphere, and even the emotional rhythm of a video, making detailed prompts a flexible starting point for more structured creation.
A detailed prompt is a full shot list — scene by scene, beat by beat.
Image references help define the look of a video before motion begins. Character appearance, clothing, props, locations, materials, composition, and overall style can all be guided visually, allowing Wan3.0-Video API to bring recognizable details into moving scenes with stronger continuity.
@Image1, @Image2 and so onAudio can shape the feel of a scene just as much as visuals do. Speech, music, rhythm, vocals, and other sound references give Wan 3.0 Video API more context for pacing, mood, performance energy, and audiovisual coordination, helping the final result feel more unified.
@Audio1, @Audio2 and so onKeyframes provide strong visual anchors for how a sequence should begin, evolve, or conclude. By using opening or ending visual references, Wan3.0 API can guide subject continuity, transition logic, and scene development in a way that keeps the generated video more directionally consistent.
Creative source material does not always start as a prompt. Briefs, presentations, spreadsheets, PDFs, text documents, and webpages can also provide valuable structure and context, allowing Wan 3.0 API to turn existing information into part of the video generation workflow instead of treating it as separate preparation work.
Wan3.0 expands video creation beyond conventional prompts by incorporating richer creative context into the generation process. Different types of reference materials, including images, videos, audio, documents, and webpages, can help guide scene development, visual consistency, and creative direction.
Longer native generation gives scenes more space to establish context, develop actions, transition between story beats, and reach a more satisfying conclusion. Wan 3.0 API supports videos up to 30 seconds while intelligently adapting duration to the requested content, opening more room for narrative structure and creative freedom.
Characters, clothing, props, environments, audio cues, and spatial relationships can remain closely aligned with their original references throughout changing actions and scenes. Wan3.0-Video API strengthens detail reproduction and continuity, making reference-driven creation more dependable when visual identity needs to remain stable.
Wan 3.0 is billed per second of finished video — no subscription, no monthly fee, and audio is included. Reference images, video, audio and documents are all free. Pick your resolution and length and you know the price before you press generate.
| Resolution | Per second | 5 seconds | 15 seconds | 30 seconds |
|---|---|---|---|---|
| 480p | 8 credits | 40 credits | 120 credits | 240 credits |
| 720p | 16 credits | 80 credits | 240 credits | 480 credits |
| 1080p | 32 credits | 160 credits | 480 credits | 960 credits |
You pay for the length of the video you generate — nothing else. Credits never expire.
| Feature | WAN 2.7 | Wan 3.0 |
|---|---|---|
| Max duration | 15 seconds | 30 seconds |
| Resolution | 720p / 1080p | 480p / 720p / 1080p |
| Reference images | 1 | Up to 10 |
| Audio references | — | Up to 5 files |
| First / last frame control | — | Yes |
| Documents & webpages as input | — | Yes |
| Native audio | — | Yes |
| Availability on KLIFGEN | Available now | Available now |
Base Package: 500 credits
Cost per Credit: $0.0100
Perfect for: Testing and small projects
Bonus: 50 extra credits
Cost per Credit: $0.0099
Perfect for: Regular content creation
Bonus: 2,500 extra credits
Cost per Credit: $0.0095
Perfect for: Professional projects
Bonus: 10,000 extra credits
Cost per Credit: $0.0091
Perfect for: High-volume production
Get bonus credits when you top up larger amounts. All pricing is transparent with no hidden fees.
Your credits work across every model on KLIFGEN — use whichever suits the shot.
8 credits per second at 480p, 16 credits per second at 720p and 32 credits per second at 1080p. A 5-second 480p clip is 40 credits, and a full 30-second 720p video is 480 credits.
Up to 30 seconds, generated in one pass. You choose 5, 10, 15, 20 or 30 seconds — the full range is available on every job.
Text, up to 10 reference images, up to 5 audio references, a first and last keyframe, one document or one webpage. Reference them from the prompt as @Image1, @Audio1 and so on. Keyframes can't be combined with reference images, documents or webpages.
Yes. Synchronized audio is generated with the video at no extra cost, and you can turn it off if you prefer a silent clip.
480p, 720p and 1080p. Draft at 480p to iterate cheaply, then run the final at 720p or 1080p.
No. KLIFGEN is pay-per-use. You buy credits, you spend them on generations, and that's it. Credits never expire.
Yes. Every model on KLIFGEN, including Wan 3.0, has a simple HTTP API. Full documentation is in your profile once you create an account.
Up to 30 seconds of multimodal video with sound, from 40 credits a clip — no subscription, just credits.