H3 MaxAI video generator
fal's tune of MiniMax H3, for closer prompt following and a better look. On Leap, it sits beside 174 other models in one studio.
- Text to video
- Image to video
- Up to 15 s
- Up to 1080P
- 6 aspect ratios
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
AI video generator
H3 Max at a glance
H3 Max is a video model from fal. It makes video from words, a first frame or a last frame, 5, 10 or 15 seconds long, at up to 1080P.
- Made by
- fal
- Makes
- Video
- Starts from
- Words, a first frame or a last frame
- Length
- 5, 10 or 15 seconds
- Resolution
- 480P, 768P or 1080P
- Shapes
- 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
- Prompt
- Up to 10,000 characters
- Price per run
- $0.34 to $3.15
- Updated
- October 5, 2026
- 01Describe it, or start from a photo
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Made on Leap
More from H3 Max
Wax print on the wind over Lagos
Down the line into open-ocean blue
A yellow-and-navy swirl slumps on a lake dock
An emerald swirl melts at the drive-in
From the dunes to orbit
From a frozen lake to orbit
From low tide to orbit
A lilac swirl melts on a sunny plaza
Pick the right one
H3 Max and its siblings
| Model | Best for | Length | Resolution | Price per run |
|---|---|---|---|---|
| H3 Max (this page) | fal's tune of MiniMax H3, for closer prompt following and a better look. | 5, 10 or 15 seconds | Up to 1080P | $0.34 to $3.15 |
| H3 Max Turbo | The faster H3 Max, at half the price. | 5, 10 or 15 seconds | Up to 1080P | $0.17 to $1.65 |
| H3 Max Turbo Extend | Continues your video by 5, 10 or 15 seconds from a prompt that says what happens next, and returns the whole video with its new ending. | 5, 10 or 15 seconds | Up to 2K | $0.17 to $3.15 |
Side by side
More video models on Leap
No prompt needed
Or start from a recipe
Recipes write the prompt for you: add a photo, pick a look, and get a finished result.
Questions
H3 Max, answered
- What is H3 Max?
- H3 Max is a video model from fal. fal's tune of MiniMax H3, for closer prompt following and a better look. It is new on Leap and in preview: it works, and it may still change. On Leap it runs in one studio beside every other top model, with one account.
- Can H3 Max start from a photo?
- Yes. H3 Max starts from words, a first frame or a last frame. The photo becomes the first frame, cropped to the video's shape.
- How long can the videos be?
- 5, 10 or 15 seconds. You choose the length before you press go, and the price follows it.
- What resolution and sizes does it make?
- Up to 1080P, in 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16.
- How is it different from H3 Max Turbo and H3 Max Turbo Extend?
- H3 Max: fal's tune of MiniMax H3, for closer prompt following and a better look. H3 Max Turbo: The faster H3 Max, at half the price. H3 Max Turbo Extend: Continues your video by 5, 10 or 15 seconds from a prompt that says what happens next, and returns the whole video with its new ending. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- A 5-second 768P clip costs $0.55 at the default settings. By length and resolution, a run costs $0.34 to $3.15. You see the exact price before you press go, and a run that fails costs nothing.
- Is H3 Max free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.34 (a 5-second 480P clip), so $5 covers 14 of those. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as fal/h3-max, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need a fal account?
- No. Leap sends your request to fal's model and gives you what it makes. One Leap account runs H3 Max and every other model, in the studio, through the API and from your agents.
Your idea, H3 Max.
Every run shows its price before it starts, and one that fails costs nothing.
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.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "fal/h3-max", "input": { "prompt": "A paper boat drifting down a rainy street at dusk" } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"