Castaly · Models · Video
Wan 3.0: Specs, Pricing and Examples
Generate video with Wan 3.0 in Castaly: 480p to 1080p, up to 30 seconds, built-in audio, and input from text, frames, references, a file or a web page, with a live price.
Models & Pricing
Prices are in USD. The listed group rate applies before any request-specific multiplier. Your account may have different access or discounts.
| Group | Price | Conditions | Unit | Price |
|---|---|---|---|---|
| Media | Output | 1080p | Per second | USD 0.1976 |
| Media | Output | 480p | Per second | USD 0.0494 |
| Media | Output | 720p | Per second | USD 0.0988 |
Wan 3.0 is Alibaba Cloud's video model, and it handles every input in one model: text, frames, references, a file or a web page. It renders 480p to 1080p at up to 30 seconds, and audio generation adds no cost. The live price is on this page.
Specifications
| Setting | Options |
|---|---|
| Model ID | wan3.0-video |
| Resolution | 480p, 720p, 1080p |
| Length | Auto, or any whole number of seconds from 2 to 30 |
| Ratio | 16:9, 9:16, 1:1, 4:3, 3:4, adaptive |
| Start from | A prompt, frames, a set of references, one file or one web page |
| References | Up to 10 images, 5 videos and 5 audio clips |
| Audio | Generate audio switch, no extra cost |
| Billing | Per second of video |
Sample
The prompt behind this clip:
"Macro slow-motion shot of steamed milk poured into a ceramic cup of espresso, forming a rosetta latte art pattern. Warm morning light from a window, wooden counter, soft steam rising, shallow depth of field, commercial food photography, no text."
Inputs
A request uses one of four input modes, which cannot be mixed:
- Text. A prompt on its own.
- Frames. A first frame, a last frame, or both.
- References. Up to 10 images, 5 videos and 5 audio clips.
- A source. One file or one web page.
How it is billed
Wan 3.0 bills per second of video, at a rate set by the resolution. The rate does not change with the ratio, the references or the audio switch. The final charge follows the length the provider reports for the finished clip, and failed tasks are refunded in full.
The Wan comparison has dated examples of what a clip costs.
Wan 3.0 or another model?
- Wan 3.0 Prime has the same inputs and settings at a higher rate. Run a prompt on both and keep the result you prefer.
- Seedance 2.5 to edit or extend an existing video.
- Kling 3.0 for 4K.
FAQ
How long can a Wan 3.0 video be?
Up to 30 seconds. Choose any whole number of seconds from 2 to 30, or use Auto duration and let the model decide.
Does Wan 3.0 charge extra for audio?
No. Generate audio does not change the per-second rate.
What is the difference between Wan 3.0 and Wan 3.0 Prime?
They accept the same inputs and settings. Prime costs more per second at every resolution.
Can I use Wan 3.0 through an API?
Yes. The same model ID works through the Modelflare API with the same account and balance. The request format is in the API documentation.