# GoModel — OpenAI-Compatible AI Gateway

> GoModel is a lightweight AI gateway in Go that exposes a unified OpenAI-compatible API across many providers, plus logging/analytics for cost and usage.

## Install

Copy the content below into your project:

## Quick Use

```bash
docker run --rm -p 8080:8080 \
  -e OPENAI_API_KEY="your-openai-key" \
  enterpilot/gomodel

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5-chat-latest","messages":[{"role":"user","content":"Hello!"}]}'
```

## Intro

GoModel is a lightweight AI gateway in Go that exposes a unified OpenAI-compatible API across many providers, plus logging/analytics for cost and usage.

- **Best for:** Teams standardizing LLM access, routing, and cost tracking behind one gateway
- **Works with:** Docker; OpenAI-compatible clients/SDKs; provider API keys via env vars (per README)
- **Setup time:** 5–20 minutes

## Practical Notes

- GitHub: 865 stars · 69 forks; pushed 2026-05-12 (verified via GitHub API).
- README shows `docker run -p 8080:8080` and a first-call example to `/v1/chat/completions`.
- README lists multiple providers (OpenAI, Anthropic, Gemini, DeepSeek, Groq, OpenRouter, Ollama, vLLM, Bedrock, etc.).

## Main

Operational checklist for gateways:

1. **Prefer env files in production.** README warns against passing secrets via `-e` on the command line.
2. **Log request IDs.** Keep a request-id header in your clients so you can trace failures end-to-end.
3. **Start with one provider + one model.** Add routing only after you have stable monitoring and quotas.
4. **Pin “model allowlists.”** Expose only the models you approve (per README provider-model configuration patterns).

Treat the gateway as infrastructure: version it, monitor it, and keep credentials scoped and rotated.

### FAQ

**Q: Is it only for OpenAI?**
A: No—README says it provides an OpenAI-compatible API across many providers depending on credentials you set.

**Q: Do I need to pass all keys?**
A: No—README says it detects available providers from the credentials you supply (at least one).

**Q: How do I avoid leaking secrets?**
A: Use `--env-file` instead of `-e` and keep `.env` out of git history.

## Source & Thanks

> Source: https://github.com/ENTERPILOT/GoModel
> License: MIT
> GitHub stars: 865 · forks: 55

---

<!-- ZH -->

## 快速使用

```bash
docker run --rm -p 8080:8080 \
  -e OPENAI_API_KEY="your-openai-key" \
  enterpilot/gomodel

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5-chat-latest","messages":[{"role":"user","content":"Hello!"}]}'
```

## 简介

GoModel 是用 Go 写的轻量 AI 网关：用一套 OpenAI 兼容 API 接入多家模型供应商，并提供日志/分析面板，便于做路由、限流与成本统计，也方便快速定位失败请求与重试链路。

- **适合谁：** 用一个网关统一接入、路由与成本统计的团队
- **可搭配：** Docker；OpenAI 兼容的客户端/SDK；通过环境变量配置各家 API key（见 README）
- **准备时间：** 5–20 分钟

## 实战建议

- GitHub：865 stars · 69 forks；最近更新 2026-05-12（GitHub API 验证）。
- README 给出 `docker run -p 8080:8080` 以及 `/v1/chat/completions` 的首个请求示例。
- README 列出多家供应商（OpenAI/Anthropic/Gemini/DeepSeek/Groq/OpenRouter/Ollama/vLLM/Bedrock 等）。

## 主要内容

网关上线前的检查清单：

1. **生产优先用 env-file。** README 提醒不要把密钥直接写在命令行 `-e`（可能泄露到历史与进程列表）。
2. **记录 request-id。** 客户端固定带 request-id，方便端到端排错。
3. **先 1 家供应商、1 个模型跑通。** 监控与配额稳定后再逐步加路由策略。
4. **固定模型白名单。** 只暴露你批准的模型集合（README 有 provider/model 配置模式）。

把网关当基础设施管理：版本化、监控化、凭据最小化并定期轮换。

### FAQ

**只能接 OpenAI 吗？**
答：不是。README 表示可通过不同凭据接入多家供应商，但统一走 OpenAI 兼容 API。

**需要把所有 key 都配上吗？**
答：不需要。README 表示只要提供至少一组凭据，网关会自动识别可用的供应商。

**怎么避免密钥泄露？**
答：用 `--env-file` 替代命令行 `-e`，并确保 `.env` 不进入 git 历史。

## 来源与感谢

> Source: https://github.com/ENTERPILOT/GoModel
> License: MIT
> GitHub stars: 865 · forks: 55


---
Source: https://tokrepo.com/en/workflows/gomodel-openai-compatible-ai-gateway
Author: Script Depot