---
title: "Deploy CLIProxyAPI - No API Key Needed"
description: "OpenAI/Gemini/Claude/Codex compatible API proxy for CLI with OAuth support"
category: "AI/ML"
url: https://railway.com/deploy/cliproxyapi-no-api-key-needed
---

# Deploy CLIProxyAPI - No API Key Needed

OpenAI/Gemini/Claude/Codex compatible API proxy for CLI with OAuth support

**[Deploy CLIProxyAPI - No API Key Needed on Railway](https://railway.com/template/cliproxyapi-no-api-key-needed)**

- **Creator:** Muhammad Bilal
- **Category:** AI/ML
- **Total deploys:** 13

## Template content

### eceasy/cli-proxy-api:latest

- **Image:** eceasy/cli-proxy-api:latest
- **Start command:** `sh -c "cd /CLIProxyAPI && cp config.example.yaml /data/config.yaml && /CLIProxyAPI/CLIProxyAPI --config /data/config.yaml"`

### Postgres https://devicons.railway.app/i/postgresql.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:18

## Documentation

# Deploy and Host CLIProxyAPI - No API Key Needed on Railway

CLIProxyAPI is a powerful proxy server that exposes CLI-based AI models such as Gemini CLI, OpenAI Codex, Claude Code, Qwen Code, iFlow, and Antigravity through OpenAI-compatible APIs. It enables OAuth-based authentication, eliminating the need for API keys while providing load balancing, streaming responses, and seamless integration with popular AI coding assistants.

## About Hosting CLIProxyAPI - No API Key Needed

Deploying CLIProxyAPI on Railway provides a simple, production-ready environment for running an OAuth-powered AI proxy without managing your own infrastructure. The deployment uses the official Docker image with a persistent Railway Volume to securely store configuration files and OAuth credentials across restarts. Once deployed, you can authenticate one or more AI providers through the built-in management interface and connect your favorite AI coding tools using the generated API endpoint. Railway automatically handles networking, HTTPS, deployments, and scaling, making it easy to self-host CLIProxyAPI with minimal setup.

## Common Use Cases

* Connect AI coding assistants such as Cursor, Continue, Cline, Windsurf, Roo Code, and other OpenAI-compatible clients without using provider API keys.
* Manage multiple OAuth accounts with automatic load balancing and failover across supported AI providers.
* Self-host an OpenAI-compatible API gateway for teams, personal development environments, and AI-powered applications.

## Dependencies for CLIProxyAPI - No API Key Needed Hosting

* Railway Volume mounted at `/data` for persistent configuration and OAuth credentials.
* OAuth authentication with one or more supported providers (Gemini CLI, OpenAI Codex, Claude Code, Qwen Code, iFlow, or Antigravity).

### Deployment Dependencies

* GitHub Repository: https://github.com/router-for-me/CLIProxyAPI
* Documentation: https://help.router-for.me/
* Docker Image: https://hub.docker.com/r/eceasy/cli-proxy-api
* Configuration Guide: https://help.router-for.me/configuration/options.html

### Implementation Details

Deploy using the official Docker image:

```text
eceasy/cli-proxy-api:latest
```

Mount a persistent Railway Volume at:

```text
/data
```

Configure the following environment variables:

| Variable              | Value                    | Required |
| --------------------- | ------------------------ | -------- |
| `DEPLOY`              | `cloud`                  | ✅ Yes    |
| `PORT`                | `8317`                   | ✅ Yes    |
| `MANAGEMENT_PASSWORD` | Choose a strong password | ✅ Yes    |

Example:

```env
DEPLOY=cloud
PORT=8317
MANAGEMENT_PASSWORD=your-secure-password
```

> **Important:** `MANAGEMENT_PASSWORD` is required to log in to the built-in Management Web UI. Make sure to remember this password, as it will be used to access the dashboard where you authenticate AI providers, configure accounts, and manage CLIProxyAPI.

Mount a Railway Volume at `/data` to persist your configuration and OAuth credentials across deployments.

If your deployment requires a custom start command, use:

```bash
sh -c "[ -f /data/config.yaml ] || cp /CLIProxyAPI/config.example.yaml /data/config.yaml && /CLIProxyAPI/CLIProxyAPI --config /data/config.yaml"
```

After deployment:

1. Generate a Railway public domain.
2. Open the Management Web UI using your Railway domain.
3. Log in using the password configured in the `MANAGEMENT_PASSWORD` environment variable.
4. Authenticate your preferred AI provider(s) (Gemini CLI, OpenAI Codex, Claude Code, Qwen Code, iFlow, or Antigravity).
5. Configure your AI coding tool using:

   * **Base URL:** `https:///v1`
   * **API Key:** `sk-cliproxyapi-default-key-change-me` (or your custom API key if configured).

## Why Deploy CLIProxyAPI - No API Key Needed on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying CLIProxyAPI - No API Key Needed on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/cliproxyapi-no-api-key-needed