fal
H3 Max
fal's tune of MiniMax H3, for closer prompt following and a better look. On Leap, it sits beside 130 other models in one studio.
- Text to video
- Image to video
- Up to 15 s
- Up to 1080P
- 6 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
Start with an idea
Three ways to try H3 Max
Side by side
More video models on Leap
Questions
H3 Max on Leap, answered.
- Is this the real H3 Max?
- Yes. Leap sends your request to fal'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 fal account?
- No. One Leap account and one balance run H3 Max 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, H3 Max.
Start free, no card. Every run shows its price before it starts.
Make it with H3 MaxFor developers
Run H3 Max from code
- Model ID
- fal/h3-max
- 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
21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Default: 16:9
Durationduration
5, 10, 15 s, required. Default: 5 s
Resolutionresolution
480P, 768P, 1080P. Default: 768P
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": "fal/h3-max", "input": { "prompt": "A paper boat drifting down a rainy street at dusk" } }'