---
title: "MiniMax H3 API — Variants, pricing & model skill"
url: "https://runapi.ai/models/minimax-h3.md"
canonical: "https://runapi.ai/models/minimax-h3.md"
locale: "en"
model: "MiniMax H3"
provider: "MiniMax"
modality: "video"
variant_count: 1
price_from_cents: 37
---

# MiniMax H3 API

MiniMax H3 video API for 2K text-to-video, image-to-video, and multi-reference generation from images, video, and audio.

**Provider:** MiniMax
**Modality:** Video
**Catalog:** 2 endpoints

MiniMax H3 generates 4–15 second videos at 768p or 2K. Create from a text prompt, animate a first or final frame, or guide character, motion, scene, and sound consistency with multiple reference assets.

## Variants

Single-SKU line. The SDK model ID is `minimax-h3` and all usage details are documented here.

## Pricing

| Endpoint | Pricing | Billing |
|---|---|---|
| `text_to_video` | $0.370 | second |
| `image_to_video` | $0.370 | second |

## Spec sheet

| Field | Value |
|---|---|
| Model ID | `minimax-h3` |
| Provider | MiniMax |
| Modality | video |
| Task type | asynchronous |
| Billing unit | second |
| API endpoint | `/api/v1/minimax_h3/image_to_video` |


## Install the skill

```sh
npx skills add runapi-ai/minimax-h3 -g
```

The skill gives your coding tool the model docs, schemas, pricing notes, and setup steps needed to add MiniMax H3 features to an application.

## Context

Use one RunAPI model ID for text-to-video and image-to-video. Reference mode accepts up to 9 images, 3 videos, and 3 audio clips; audio references must accompany an image or video reference.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.