MiniMax M3 (GMI Cloud)
GMI Cloud 官方提供的 MiniMax M3 推理端点。限时 14 天 100% 全量免费,支持 1M MSA 稀疏注意力与 OpenAI 协议直连。
About the Model
Why Choose MiniMax M3?
MiniMax M3 is MiniMax's flagship full-stack code and reasoning model for long-range autonomous agents and massive refactors. It scored 59.0% on SWE-bench Pro in 2026, with 1M context support.
How to Access for Free (via GMI Cloud)
免费依据与活动说明
2026 年 8 月 24 日至 9 月 6 日,GMI Cloud 与 MiniMax 官方联合开展「MiniMax Week」限时免费活动。在活动期间调用 minimax-m3 完全 0 费用,不扣除任何余额,无需绑定信用卡,无需预充值。
全链路与 IDE 接入
支持标准 OpenAI 兼容协议。可在 Cursor、Claude Code、Trae、OpenCode 等工具中直接配置 Base URL 为 https://api.gmi-serving.com/v1 并填入 API Key 即可使用。
Try it in your browser
Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.
Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.
Code Examples
curl https://api.gmi-serving.com/v1/chat/completions \
-H "Authorization: Bearer $GMI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [
{"role": "user", "content": "请分析基于分布式 Raft 协议的选主逻辑并给出优化方案。"}
],
"temperature": 0.2
}'
Community Feedback
Comments are tied to your GitHub account — sign in to join the discussion.