Alibaba
Wan 3.0
Alibaba's newest video model, with sound, from text or a first frame. On Leap, it sits beside 130 other models in one studio.
- Text to video
- Image to video
- Up to 15 s
- Up to 1080p
- With sound
- 5 aspect ratios
- Start free, no card
- Every top model, one account
- Pay per run, priced before it starts
- 01Describe it, or start from a photo
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Side by side
More video models on Leap
Questions
Wan 3.0 on Leap, answered.
- Is this the real Wan 3.0?
- Yes. Leap sends your request to Alibaba's model through its provider and gives you back what it makes. Switch to any other model in the same studio when an idea needs it.
- What does it cost?
- In dollars, per run: the provider's list price plus 10%. You see the exact price before every run, a run that fails costs nothing, and there is no subscription. Every model's price is on the pricing page.
- Do I need a Alibaba account?
- No. One Leap account and one balance run Wan 3.0 and every other model, in the studio, through the API and from your agents.
- What happens to what I make?
- It stays in your library while your account is active, ready to use anywhere.
Your idea, Wan 3.0.
Start free, no card. Every run shows its price before it starts.
Make it with Wan 3.0For developers
Run Wan 3.0 from code
- Model ID
- alibaba/wan-3.0
- Makes
- Video
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
Promptprompt
Text, up to 10,000 characters, required
First framefirst_frame
An imageAn image the video starts from. It is cropped to the video's shape.
Last framelast_frame
An image
Aspect ratioaspect_ratio
16:9, 4:3, 1:1, 3:4, 9:16
Durationduration
5, 10, 15 s, required. Default: 5 s
Resolutionresolution
480p, 720p, 1080p. Default: 1080p
Soundaudio
On or off. Default: onGenerate dialogue, effects and music with the video.
Enable Prompt Expansionsettings.enable_prompt_expansion
On or off. Default: onEnable intelligent prompt rewriting.
Enable Thinkingsettings.enable_thinking
On or off. Default: offEnable enhanced reasoning before generation.
Seedseed
0 to 4294967295The same seed and input give the same image.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result. Agents can call it through the MCP server at mcp.tryleap.ai.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "alibaba/wan-3.0", "input": { "prompt": "Wildlife documentary footage on a 600mm telephoto lens, late afternoon on the Chobe River in Botswana. A family of African elephants wades across the wide brown river in a line from left to right, water up to their bellies. In the middle, a small calf is almost completely underwater and holds the tip of its trunk straight up out of the water like a snorkel, its mother walking right beside it. The lead female reaches the shallows, flaps her ears and shakes her head, spraying water. Golden backlight, warm haze, glittering droplets, natural muted documentary colour with no HDR look, gentle long-lens drift. Sound: river water sloshing, a low elephant rumble, birds, a distant hippo grunt." } }'