M3 or M2 — which should I pick?

M3 is the flagship for coding and agents (main model); M2.x highspeed variants respond faster and fit the fast-model slot for subtasks.

SETUP GUIDE

How to run Claude Code & Codex with MiniMax

MiniMax's M-series (M3 / M2.x) is built for coding and long-running agent tasks. MiniMax offers both an Anthropic-compatible endpoint and an OpenAI Responses API endpoint — dual-engine ready.

Engine support (probe-verified, 2026-07-10)

Engine	MiniMax support
Claude Code	✅ Supported (Anthropic-compatible endpoint)
Codex	✅ Supported (OpenAI Responses API)

Step 1 — Get a MiniMax API key

Open platform.minimaxi.com → sign up / log in → account “Interface keys” → create and copy.

Console: https://platform.minimaxi.com/user-center/basic-information/interface-key

Step 2 — Configure the Snail launcher (3 steps)

Download the launcher for Mac / Windows from justalittlesnail.ai;
Paste the API key on the MiniMax card (the launcher validates connectivity immediately);
Pick a model and click Launch Claude Code — a dedicated terminal window opens.

Recommended models

Main: MiniMax-M3 (complex tasks) · Fast: MiniMax-M2.5-highspeed (subtasks / summaries). After saving the key, click “Refresh” on the card to pull the live model list.

FAQ

M3 or M2 — which should I pick?: M3 is the flagship for coding and agents (main model); M2.x highspeed variants respond faster and fit the fast-model slot for subtasks.

Multi-window sessions, a different model in each window

Download the Snail launcher

Other guides: DeepSeek · Qwen 通义千问 · Kimi · GLM 智谱 · MiMo · StepFun 阶跃星辰 · 百度千帆 ERNIE · Anthropic Claude 官方
 All guides (EN) · 中文版 · Home