---
title: "MiniMax AI 模型 — 透過 RunAPI 取得 API 存取"
url: "https://runapi.ai/zh-HK/providers/minimax.md"
canonical: "https://runapi.ai/zh-HK/providers/minimax.md"
locale: "zh-HK"
provider: "MiniMax"
line_count: 2
variant_count: 13
---

# MiniMax

Hailuo video generation at native 1080p with accurate physics simulation and complex motion.

MiniMax develops Hailuo, a video generation model producing text-to-video and image-to-video at native 1080p with accurate physics simulation, complex motion, and human pose fidelity.

## Models

- [Hailuo](https://runapi.ai/zh-HK/models/hailuo.md) — Video, 6 variants · from $0.300
- [MiniMax](https://runapi.ai/zh-HK/models/minimax.md) — Text, 7 variants · from $0.010

## Variants

| Model | Variant | Billing | Starting price | URL |
|---|---|---|---|---|
| Hailuo | `02-image-to-video-pro` | call | $0.570 | https://runapi.ai/zh-HK/models/hailuo/02-image-to-video-pro.md |
| Hailuo | `02-image-to-video-standard` | call | $0.300 | https://runapi.ai/zh-HK/models/hailuo/02-image-to-video-standard.md |
| Hailuo | `02-text-to-video-pro` | call | $0.570 | https://runapi.ai/zh-HK/models/hailuo/02-text-to-video-pro.md |
| Hailuo | `02-text-to-video-standard` | call | $0.500 | https://runapi.ai/zh-HK/models/hailuo/02-text-to-video-standard.md |
| Hailuo | `2.3-image-to-video-pro` | call | $0.900 | https://runapi.ai/zh-HK/models/hailuo/2.3-image-to-video-pro.md |
| Hailuo | `2.3-image-to-video-standard` | call | $0.500 | https://runapi.ai/zh-HK/models/hailuo/2.3-image-to-video-standard.md |
| MiniMax | `m2` | 1K tokens | $0.010 | https://runapi.ai/zh-HK/models/minimax/m2.md |
| MiniMax | `m2.1` | 1K tokens | $0.010 | https://runapi.ai/zh-HK/models/minimax/m2.1.md |
| MiniMax | `m2.5` | 1K tokens | $0.010 | https://runapi.ai/zh-HK/models/minimax/m2.5.md |
| MiniMax | `m2.5-highspeed` | 1K tokens | $0.020 | https://runapi.ai/zh-HK/models/minimax/m2.5-highspeed.md |
| MiniMax | `m2.7` | 1K tokens | $0.010 | https://runapi.ai/zh-HK/models/minimax/m2.7.md |
| MiniMax | `m2.7-highspeed` | 1K tokens | $0.020 | https://runapi.ai/zh-HK/models/minimax/m2.7-highspeed.md |
| MiniMax | `m3` | 1K tokens | $0.020 | https://runapi.ai/zh-HK/models/minimax/m3.md |

## LLM API endpoints

Base URL: `https://runapi.ai`

- `POST /v1/chat/completions` — OpenAI compatible
- `POST /v1/responses` — OpenAI Responses
- `POST /v1/messages` — Anthropic compatible
- `POST /v1beta/models/{model}:generateContent` — Gemini generateContent
- `POST /v1beta/models/{model}:streamGenerateContent` — Gemini streamGenerateContent

Use a compatible SDK for the endpoint you call with your RunAPI API key.

## Install a model skill

```sh
npx skills add runapi-ai/<line> -g
```

Replace `<line>` with a model slug from this provider, then use the skill docs, schemas, pricing notes, and setup steps while adding the model feature.

## FAQ

### 這是 MiniMax 的官方整合嗎？

RunAPI 提供託管 API 介面，價格、能力及錯誤行為都清晰透明。

### 我需要 MiniMax 帳戶嗎？

不用 — 你的 RunAPI 密鑰已足夠使用託管存取。

### 透過 proxy 會增加多少延遲？

通常少於 20 ms。RunAPI 會將 proxy 層維持在貼近 model 執行區域的位置。

### 圖片／影片會快取嗎？

生成結果會按 task ID 儲存並可供取回。輸入內容不會快取。

### 我可以使用自己的 key 嗎？

目前不支援 — 請使用 RunAPI 管理的存取。