MiniMax H3 Max

Create with MiniMax H3 Max

MiniMax's post-trained H3 variant for prompt-faithful, polished video from text, controlled frames, or multimodal references.

What does the output look like?

Animated character and scene transitions

A storyboard-led sequence from Starpop’s singing-ad case study. The published clip shows an animated character followed by visual cutaways.

Starpop example: MiniMax H3 Max singing-ad case study

What can MiniMax H3 Max do?

MiniMax H3 Max video generation with strong prompt adherence, polished aesthetics, first/last frame control, multimodal references, and clips up to 15 seconds

  • Prompt-faithful cinematic video
  • Animating designed start and end frames
  • Keeping subjects and style consistent across mixed references
Inputs
Text, Image, Video, Audio
Durations
5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
Aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Output options
480p, 768p, 1080p
Typical generation time
About 10 minutes
  • 1080p uses latent refinement from a native 768p source. Image-to-video follows the source image's aspect ratio instead of the selected text-to-video ratio.
  • A last frame requires a first frame. Reference mode accepts up to 12 files; each video or audio clip must be 2–15 seconds, with no more than 15 seconds combined per media type, and audio requires an image or video.

How much does MiniMax H3 Max cost?

Base estimate

$0.05–$0.16 USD / second

0.5–1.6 credits / second

Estimated dollar cost uses the Solo monthly plan at $0.10 USD per credit. Your cost per credit depends on your plan.

Example: a 5-second clip

$0.25–$0.80 USD(2.5–8 credits)

Reference media and video editing may add to this estimate.

Video cost scales with duration. Resolution, sound, reference media, and generation mode can affect the final charge. Check the total shown in Starpop before generating.

How to use MiniMax H3 Max

  1. Click “Create with MiniMax H3 Max” and sign in or create an account. After setup, Starpop opens a new video workspace tab with the model selected.
  2. Choose Frames for text or start/end images, or References for a mixed image, video, and audio input set.
  3. Explain the role of each reference and choose the duration and resolution. Audio guidance requires a visual reference.
  4. Review the credit estimate and generate. Check the result in your workspace, then download it or adjust your inputs to try again.
Create with MiniMax H3 Max

More about using this model