gpt-load

Self-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, scheduling, failover, request logs and usage. 自托管 AI 网关：多渠道多凭据统一接入，含密钥与订阅账号、调度容错、日志与用量。

⭐ 6,607 stars on GitHub · 🍴 710 forks · 📜 License: mit · 💻 Language: Go

What is gpt-load?

Managing fragmented AI model providers, varying subscription tiers, and restrictive rate limits quickly becomes a routing nightmare for any application. By acting as a unified entry point, this Go-based gateway consolidates disparate API keys, cloud platforms, and even

Topics: the project is tagged with popular topics:

• 🏷️ ai-gateway
• 🏷️ anthropic
• 🏷️ api-gateway
• 🏷️ claude
• 🏷️ claude-code
• 🏷️ codex
• 🏷️ gemini
• 🏷️ gin
• 🏷️ go
• 🏷️ golang

📸 Screenshots

Quick install

The project supports Docker Compose:

git clone https://github.com/tbphp/gpt-load.git
cd gpt-load
docker compose up -d

Check the README in the repo for required env variables.

Minimum system requirements

⚡ Deploy fast on VSIS

Use the VSIS VPS Lite 2GB RAM / 2 vCPU / 25GB SSD (~104k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running gpt-load smoothly.

🎯 Benefits:

• One-command docker compose up -d deploy in 2 minutes
• Dedicated IPv4, root access, unmetered domestic bandwidth
• Daily snapshot backup
• Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources

• 🔗 GitHub: tbphp/gpt-load
• 🌐 Homepage: https://www.gpt-load.com
• 📚 Official docs: see README in the repo
• 💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 10/09/2026. Star/fork counts may have changed — see live numbers via the GitHub link.