# minimax-h3

> minimax-h3 is a MiniMax video model in Nodaro for image to video and text to video, from 230 credits per run.

Source: https://nodaro.ai/docs/models/video/minimax-h3

MiniMax Hailuo 3 — premium multimodal tier: first/last frame + image/video/audio references, native audio, 2K (default) or 768P output, 4-15s per-second pricing.

- Maker: MiniMax
- Modes: Image to video, Text to video
- Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
- Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive
- Resolutions: 2K, 768P
- Features: Start and end frame, Generates audio, Reference images, Reference video
- API type: `minimax-h3`

## Credits

| Tier | Credits |
| --- | --- |
| default 6s @2K — see:Ns variants | 550 |
| 4s @2K (min) | 370 |
| 8s @2K | 730 |
| 15s @2K (max) | 1370 |
| 4s @768P (min) | 230 |
| 8s @768P | 450 |
| 15s @768P (max) | 850 |

## Use minimax-h3 in Nodaro

- [Generate Video](https://nodaro.ai/docs/nodes/video/generate-video)
- [Generate Video Pro](https://nodaro.ai/docs/nodes/video/generate-video-pro)
- [Lip Sync](https://nodaro.ai/docs/nodes/video/lip-sync)

## Prompt tips

- Natural-language prompts up to 7000 chars. Front-load what matters: subject → action → scene/environment → lighting → camera move → style. One camera movement per shot.
- Output 2K (default) or 768P (cheaper tier). Aspect: pure text-to-video needs a concrete ratio (21:9/16:9/4:3/1:1/3:4/9:16); reference runs default to adaptive (match the input).
- References go by ordinal in attachment order (@Image 1, Video 1) — earlier = higher priority. Caps: 9 images, 3 videos (2-15s each, ≤15s total), 3 audio clips (≤15s total).
- Reference audio drives speech/lip-sync but never rides alone — pair it with an image or video reference. Audio input is free; the first 5 input images are free, extras bill per image.
- No negative-prompt parameter — put constraints in the prompt text: 'keep it subtitle-free, do not generate a watermark, do not generate a logo'.

## Similar models

- [Hailuo 02 I2V Pro](https://nodaro.ai/docs/models/video/hailuo-02-i2v-pro)
- [Hailuo 2.3 Pro](https://nodaro.ai/docs/models/video/hailuo-2-3-pro)
- [Hailuo 2.3 Standard](https://nodaro.ai/docs/models/video/hailuo-2-3-standard)
- [Hailuo 02 Standard](https://nodaro.ai/docs/models/video/hailuo-02-standard)

## Frequently asked questions

### How many credits does minimax-h3 cost in Nodaro?

minimax-h3 costs between 230 and 1370 credits per run, depending on the settings. Pricing: 550 credits (default 6s @2K — see:Ns variants); 370 credits (4s @2K (min)); 730 credits (8s @2K); 1370 credits (15s @2K (max)); 230 credits (4s @768P (min)); 450 credits (8s @768P); 850 credits (15s @768P (max)).

### What can minimax-h3 do?

minimax-h3 supports image to video and text to video. MiniMax Hailuo 3 — premium multimodal tier: first/last frame + image/video/audio references, native audio, 2K (default) or 768P output, 4-15s per-second pricing.

### Which Nodaro nodes can run minimax-h3?

Choose minimax-h3 as the model on the Generate Video node, the Generate Video Pro node and the Lip Sync node.

### How long are minimax-h3 clips?

minimax-h3 makes clips of 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14 and 15 seconds.

### Which aspect ratios does minimax-h3 support?

minimax-h3 supports 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 and adaptive.

### Does minimax-h3 generate sound?

Yes. minimax-h3 generates audio together with the video.