Video generation

MiniMax H3 Max Turbo

by fal.ai

The fast tier of fal's post‑trained H3.
Twice the speed, nearly the same look.

MiniMax H3 Max Turbo

Key features

A lathe peels a bright curl of steel from a spinning barTry now

Technical specifications

MiniMax H3

Distilled by fal from their own H3 Max

2 modes

Text to video and image to video, both live

5 to 15s

Five to ten seconds is the recommended range

Up to 768p

Native 480p and 768p, a step above 720p HD

24 FPS

The cadence film and broadcast are shot at

Native

Stereo sound generated alongside the picture

11 languages

Inherited from H3, which is stable across 11

6 ratios

21:9, 16:9, 4:3, 1:1, 3:4, and 9:16 supported

Use cases

One setup, several looks

Relight and reframe the same setup inside one take, so a lighting call gets judged as motion instead of as a still.

Previz and animatics

Block the shot, watch it, adjust it, watch it again, with the loop tight enough to explore a doubtful idea.

Interactive generation

Anything with a person waiting on the result: a generate button in a product, a chat loop, a live demo.

Catalogue and per-SKU work

Throughput decides whether a whole product range is feasible, rather than just the twenty best sellers.

Sound-led scenes

Picture and audio are predicted together, so a scene built around one precise sound arrives carrying it.

Titles and kinetic type

Quote the exact words and they come back correctly spelled, so a title card ships as generated.

Prompt examples

Lathe shop

A lathe peels a bright curl of steel from a spinning bar

Edit prompt

Ferry deck

Gulls hang beside a ferry rail as the wake churns below

Edit prompt

Print room

A proof sheet lifts off the press, ink still tacky

Edit prompt

Night kitchen

A pass bell rings twice as plates slide under the lamps

Edit prompt

Chalk board

A hand works a proof across a green chalkboard

Edit prompt

Bell tower

A bronze bell swings and the pigeons scatter off the ledge

Edit prompt

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is MiniMax H3 Max Turbo?
MiniMax H3 Max Turbo is the fast tier of H3 Max, which is itself fal's post-trained version of MiniMax's open-weight H3. fal distilled H3 Max for throughput and released Turbo as a preview in September 2026. It returns five to fifteen second clips at up to 768p and 24fps with native stereo audio, and accepts the same briefs H3 Max does.
Is MiniMax H3 Max Turbo made by MiniMax?
No, and the name misleads twice over. MiniMax built and open-sourced H3. fal post-trained those weights into H3 Max, then distilled H3 Max into Turbo, and hosts both exclusively. MiniMax has never announced a model called H3 Max or H3 Max Turbo, so treat Turbo as fal's fast edition of fal's own tuned edition of an open MiniMax model.
How much faster is MiniMax H3 Max Turbo than H3 Max?
About twice as fast, which is fal's own figure. H3 Max already returned a five-second 768p clip in under three seconds, so on that figure the same clip lands in around half that, and a fifteen-second generation comes back in well under fifteen seconds. Past that point the render finishes before you could have watched the result play.
What does MiniMax H3 Max Turbo give up for the speed?
A little quality and one mode. fal targets the 97th percentile of H3 Max on their own evaluations, and reports Turbo still scores above base MiniMax H3. The mode it drops is reference to video, so holding a character or style steady from supplied images, clips, and audio stays with H3 Max. Everything else, including the resolution ceiling, is identical.
How is MiniMax H3 Max Turbo different from MiniMax H3?
They sit at opposite ends of the same family. Base H3 is the one that reaches 2K and carries the reference mode, and it is what you finish on. Turbo is tuned entirely for how quickly a 768p result arrives, and it is what you explore on. Because both derive from the same weights, the look carries across the handoff in a way it does not between vendors.
Why does MiniMax H3 Max Turbo stop at 768p?
Because 768p is what the open weights generate. H3 is a three-part system: a preprocessor that interprets the brief, a base model that renders at 768p, and a separate stage that regenerates the result at 2K. MiniMax open-sourced only the base model, so anything post-trained or distilled from those weights has no 2K stage to hand off to.
Does MiniMax H3 Max Turbo generate sound?
Yes. The underlying model predicts video and audio together rather than scoring the clip afterwards, so a generation returns stereo sound with the picture. That makes audio worth writing into the brief: name the effects you want, the room tone, and the exact moment a cue should land, rather than arranging all of it in a later pass.
Can I use MiniMax H3 Max Turbo on Morphic?
Yes. Pick MiniMax H3 Max Turbo in the model picker, switch the prompt bar to video, and write the shot as a brief covering subject, action, camera, light, and the sound you want. Takes land on the Canvas, so you can run the same brief through H3 Max or another model and compare them side by side before choosing.

Other models

Lyria 3.5

Google DeepMind

Google's best-sounding music model. Full songs with structure, vocals, and lyrics.

Inworld TTS 2

Inworld

Ninety-five voices, 100+ languages. Speech that starts in under a second.

Gemini Omni Flash 1.1

Google DeepMind

Google's video model where the edit is a sentence. Now with 4K output and 40-second scenes.

MiniMax H3 Max

fal.ai

fal's post-trained MiniMax H3. Tuned for prompt adherence, rebuilt for speed.