MiniMax · Image to video

MiniMax H3

MiniMax H3 focuses on cinematic character performance, coherent scene progression and coordinated audiovisual storytelling. It is useful for dialogue scenes, branded narratives and product clips where the action needs to feel connected rather than a collection of isolated movements. Specify the sequence of events and use the available frame controls to anchor the scene, with clear direction for performance, camera movement and pacing.

Generation mode

Image to video

Credit cost

32–195 credits

Observed generation time

Not enough public data

Release date

Not enough public data

Current credit pricing

Duration	Configuration	Credits
4 seconds	2K	52
4 seconds	768P	32
5 seconds	2K	65
5 seconds	768P	40
6 seconds	2K	78
6 seconds	768P	48
7 seconds	2K	91
7 seconds	768P	56
8 seconds	2K	104
8 seconds	768P	64
9 seconds	2K	117
9 seconds	768P	72
10 seconds	2K	130
10 seconds	768P	80
11 seconds	2K	143
11 seconds	768P	88
12 seconds	2K	156
12 seconds	768P	96
13 seconds	2K	169
13 seconds	768P	104
14 seconds	2K	182
14 seconds	768P	112
15 seconds	2K	195
15 seconds	768P	120

Availability and credit rows come from Flowctory's active production catalog. Observed time is shown only after at least five completed generations and is not a controlled benchmark. Model availability, limits, and costs can change.

Use model