What Wan 3.0 Reference is good at
Video models are billed per second or per clip: turn a description or a picture into a clip a few seconds long.
Video from text or up to 10 reference images for characters and scenes. Also turns PPT/PDF/Word files or web links into narrated 1080P explainer videos up to 30 seconds.
Good for
- Short video ads and product showcases
- Bringing a still image to life
- Short clips for social media
Less suited for
- Videos several minutes long: generate in parts and edit together
- Articles or code: use a chat model
Code sample
How to call it will be in the docs. You can sign up and create an API key now; you will not need a new key when it opens.
What it costs, roughly
Estimated from the unit price above; you are charged per generation.
| One 5-second clip5 × Rp 1.792 | Rp 8.960 |
| One 10-second clip10 × Rp 1.792 | Rp 17.920 |
| A 30-second ad (generated in parts)30 × Rp 1.792 | Rp 53.760 |
| A minimum Rp 50.000 top-up coversbilled per second | ≈ 27 s |
Model status
Calls over the last 24 hours.
Related models
One API key calls them all; to switch, just change the model name.
Other Alibaba models
Wan 3.0 Omni ReferenceComing soonRp 1.792 per second
Wan 3.0Coming soonRp 932 per second
HappyHorse ReferenceComing soonRp 3.117 per second
Wan 3.0 Text-to-VideoComing soonRp 1.792 per second
HappyHorse Video EditComing soonRp 3.117 per second
HappyHorse 1.1 ReferenceComing soonRp 2.986 per second
Alternatives at a similar price
Kling AvatarComing soonRp 1.792 per second
Hailuo H3 Max First-Last FrameComing soonRp 1.971 per second
Hailuo H3 Max Text-to-VideoComing soonRp 1.971 per second
MiniMax H3 MaxComing soonRp 1.971 per second