---
title: "MiniMax API — 變體、價格與 model skill | RunAPI"
url: "https://runapi.ai/zh-HK/models/minimax.md"
canonical: "https://runapi.ai/zh-HK/models/minimax.md"
locale: "zh-HK"
model: "MiniMax"
provider: "MiniMax"
modality: "text"
variant_count: 7
price_from_cents: 1
---

# MiniMax API

MiniMax text API access via RunAPI — 230B MoE models from 200K to 1M context, up to 80.5% SWE-bench Verified.

**Provider:** MiniMax
**Modality:** Text
**Catalog:** 7 variants

MiniMax's M-series are sparse Mixture-of-Experts text models (230B total / ~10B active, 256 experts) built for cost-efficient coding. M2 through M2.7 offer 200K context with progressively stronger agentic capabilities — M2.7 reaches 56.2% on SWE-bench Pro. MiniMax-M3 restores 1M context with a new Sparse Attention architecture, scoring 80.5% on SWE-bench Verified and 59.0% on SWE-bench Pro. Highspeed variants run the same weights at ~100 tokens/sec for latency-sensitive work. All are available through RunAPI with one key and per-token billing.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| MiniMax-M2 | `m2` | $0.010 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.md |
| MiniMax-M2.1 | `m2.1` | $0.010 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.1.md |
| MiniMax-M2.5 | `m2.5` | $0.010 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.5.md |
| MiniMax-M2.5-highspeed | `m2.5-highspeed` | $0.020 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.5-highspeed.md |
| MiniMax-M2.7 | `m2.7` | $0.010 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.7.md |
| MiniMax-M2.7-highspeed | `m2.7-highspeed` | $0.020 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m2.7-highspeed.md |
| MiniMax-M3 | `m3` | $0.010 | 1K tokens | https://runapi.ai/zh-HK/models/minimax/m3.md |


## API endpoints

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

- `POST /v1/chat/completions`

Use the OpenAI or Anthropic SDK with your RunAPI API key. No extra SDK required.

## Context

MiniMax M-series text models are 230B MoE LLMs with 200K–1M context, delivering frontier coding scores at a fraction of the cost of dense models. Through RunAPI they share a single API key with pay-as-you-go token billing, callable from the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages surfaces. These are MiniMax's text models, distinct from MiniMax Hailuo video generation.

## FAQ

### 我應該先用邊個版本？

先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本，之後再升級到 pro 用於正式生產。

### 有免費方案嗎？

新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。

### 你哋支援串流結果嗎？

如有提供串流，RunAPI 會端到端串流。

### 失敗會點樣收費？

生成失敗不會收費。

### 輸出有快取嗎？

已生成輸出會儲存，並可按任務 ID 取回。輸入內容不會快取。

### 可以商業使用嗎？

可以——除非模型授權明確限制，否則每個版本都包括商業使用。相關限制會在版本頁面列明。

### 限流點樣計？

每個密鑰的限流會跟使用等級而提升。最新限制請參考定價頁。

### 可以在邊度報告問題？

可以在公開 GitHub repo 開 issue，或者電郵支援。