# MiniMax H3 Reference

> Video AI Model by MiniMax — available on Layer

Reference-guided MiniMax H3 video at 2K that follows a reference clip shot for shot while the prompt changes the subject or action.

MiniMax H3 Reference is the reference-guided mode of MiniMax's H3 (Hailuo-03) video model, accepting up to 5 reference images, 3 video clips, and 3 audio clips (11 files total) alongside a prompt. A reference video is followed shot for shot, in framing and timing, while the prompt changes the subject or the action in it, so an existing clip or ad can be edited whole with a new subject that moves and acts inside the original shots. Image references keep characters and styles consistent, and output is 2K video with native stereo audio across selectable or adaptive aspect ratios. It is weak at restyling a clip, and an added subject tends to cover the HUD, reward numbers, or call to action, so the prompt should name those as kept clear.

## Specifications

| Property | Value |
|----------|-------|
| Provider | MiniMax |
| Category | Video |
| Price | 2 / second |
| Aspect Ratios | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
| Durations | 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s |

## Frequently Asked Questions

### How much does MiniMax H3 Reference cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 2 / second.

### How does Layer's pricing work?

There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.

### What Elo score does MiniMax H3 Reference have?

MiniMax H3 Reference has an Artificial Analysis Arena Elo of 1356, which places it #6 of the 84 scored video models on Layer. Gemini Omni Flash leads that ranking with an Elo of 1368.

---

[Try MiniMax H3 Reference](https://layer.ai/me/session/new?baseModelId=MINIMAX_H3_REFERENCE) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)