Nano GPT logo
NanoGPT

MiniMax H3 Max

Try Model

Generate from text, first/last frames, or image/video/audio references.

Added Aug 26, 2026

Details

Starting Price
From $0.250 per video
Model type
both

Final price depends on the selected settings and is shown before generation.

Settings

Generation controls available for this model.

Output Format

up to 1,080p
Square
Portrait
Landscape

Default Duration

5

11 duration options

Aspect Ratio

Select

Default

16:9

Options (7)

adaptive, 21:9, 16:9, 4:3 +3 more

Duration (seconds)

Select

Default

5

Options (11)

5, 6, 7, 8 +7 more

Mode

Select

Default

auto

Options (2)

Auto-detect, Reference to Video

Prompt Expansion

Select

Default

balanced

Options (3)

disabled, balanced, quality

Reference mode supports balanced or quality.

Reference audio URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Reference image URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Reference video URLs

Text

Default

N/A

Optional URL, one URL per line, or a JSON array of URLs.

Resolution

Select

Default

768p

Options (3)

480p, 768p, 1080p

Safety Checker

Toggle

Default

Yes

Showing 9 of 10 settings.

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Video

#2 / 31

ELO

1117.0

Appearances

5,755

95% CI

-12/12

Release Date 2026-08 · Matched as MiniMax H3 Max (based on MiniMax H3)

Artificial Analysis API

Examples

Loading examples…