# MiniMax H3 Reference

> Video AI Model by MiniMax — available on Layer

Reference-guided MiniMax H3 video with multimodal image, video, and audio inputs at 2K.

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. It keeps subjects, motion, and sound consistent across generations while outputting 2K video with native stereo audio across selectable or adaptive aspect ratios. Built for character lock, style transfer, and multi-shot consistency in production pipelines.

## Specifications

| Property | Value |
|----------|-------|
| Provider | MiniMax |
| Category | Video |
| Price | 2 / second per 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 |

---

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