---
title: "Deploy JimiHub - Gemini to OpenAI Proxy"
description: "Centralized Gemini API proxy, key management, and quota tracker."
category: "AI/ML"
url: https://railway.com/deploy/jimihub
---

# Deploy JimiHub - Gemini to OpenAI Proxy

Centralized Gemini API proxy, key management, and quota tracker.

**[Deploy JimiHub - Gemini to OpenAI Proxy on Railway](https://railway.com/template/jimihub)**

- **Creator:** Muhammad Bilal
- **Category:** AI/ML

## Template content

### dreamhartley705/jimihub:latest

- **Image:** dreamhartley705/jimihub:latest
- **Public domain:** Yes

## Documentation


# Deploy and Host JimiHub on Railway

JimiHub is an open-source proxy service designed to seamlessly convert OpenAI Chat Completions API requests into Google Gemini API requests. It features multi-API key rotation, request load balancing, global model quota management, and a built-in administrative Web UI for monitoring usage and managing worker credentials across distributed applications.

## About Hosting JimiHub

Hosting JimiHub on Railway provides a zero-maintenance containerized deployment for your API proxy infrastructure. Railway runs the prebuilt Docker container (`dreamhartley705/jimihub:latest`) on its high-availability infrastructure, automatically managing public HTTPS networking, SSL certificates, and internal traffic routing to the application's default container port (`3000`).

To maintain persistent application state across container deployments—such as user session databases, worker keys, and key rotation settings—JimiHub relies on local filesystem storage mounted at `/app/data`. Railway handles this seamlessly via persistent volumes, ensuring continuous uptime without data loss during application restarts or redeployments.

## Common Use Cases

- Rotating multiple Google Gemini API keys to bypass default rate limits and distribute traffic loads.
- Bridging OpenAI-compatible applications and client libraries to work directly with Google Gemini models without code modifications.
- Monitoring usage statistics and centralizing API key quotas across teams or multi-tenant background services via a unified administrative dashboard.

## Dependencies for JimiHub Hosting

- **Railway Persistent Volume**: Required to retain SQLite database files and administrative configurations across container redeployments.
- **Google Gemini API Key(s)**: Required for upstream LLM request execution and proxy routing.

### Deployment Dependencies

- [Official GitHub Repository](https://github.com/dreamhartley/JimiHub)
- [Docker Hub Image Registry Page](https://hub.docker.com/r/dreamhartley705/jimihub)
- [Google AI Studio API Key Portal](https://aistudio.google.com/)

### Implementation Details

#### Docker

JimiHub is deployed using the official prebuilt Docker container image:

```text
dreamhartley705/jimihub:latest

```

Railway automatically pulls and deploys this image without requiring local build steps.

---

#### Public Networking

| Setting | Value |
| --- | --- |
| **Proxy Type** | HTTP Proxy |
| **Target Port** | `3000` |

---

#### Environment Variables

| Variable | Required | Description |
| --- | --- | --- |
| `ADMIN_PASSWORD` | Yes | Password used to authenticate access to the JimiHub admin panel. |
| `PORT` | Yes | Internal web server listening port (defaults to `3000`). |
| `GEMINI_BASE_URL` | Yes | Upstream Google Gemini API base endpoint URL. |
| `GITHUB_PROJECT` | No | Optional GitHub repository (`username/repo-name`) for remote backup sync. |
| `GITHUB_PROJECT_PAT` | No | Optional GitHub Personal Access Token with `repo` scope for syncing. |
| `GITHUB_ENCRYPT_KEY` | No | Optional 32-character string used to encrypt sync data saved to GitHub. |

**Raw Editor Environment Template:**

```env
ADMIN_PASSWORD=your_secure_password_here # Administrator password used to authenticate and log in to the JimiHub admin panel
PORT=3000 # Internal port on which the web container listens (Railway routes public traffic here automatically)
GEMINI_BASE_URL=[https://generativelanguage.googleapis.com](https://generativelanguage.googleapis.com) # Upstream Google Gemini API base URL used for polling requests
GITHUB_PROJECT= # OPTIONAL: GitHub repository in "username/repo-name" format to enable remote config syncing
GITHUB_PROJECT_PAT= # OPTIONAL: GitHub Personal Access Token (PAT) with 'repo' scope permissions for syncing
GITHUB_ENCRYPT_KEY= # OPTIONAL: A secret 32-character string used to encrypt sync data saved to your GitHub repo

```

---

#### Persistent Storage

A persistent volume must be attached to the service to ensure settings, API keys, and metrics persist across container restarts.

1. Open your service in the **Railway Dashboard**.
2. Navigate to **Settings** -> **Volumes**.
3. Click **Add Volume**.
4. Set the Mount Path to:

```text
/app/data

```

---

#### Database

No separate database service (e.g., PostgreSQL or Redis) is required. JimiHub utilizes an embedded local database stored within the `/app/data` volume.

---

#### Build & Start

No custom build or start commands are required.

---

#### Accessing the Application

1. In the Railway Service settings, go to **Networking** -> **Public Networking** and click **Generate Domain**.
2. Access the Web Admin Panel by navigating to `https:///login` or `https:///admin`.
3. Log in using the password configured in `ADMIN_PASSWORD`.
4. Add your Google Gemini API key(s) and generate Worker API keys within the management panel.
5. Update your client applications to use `https:///v1` as their OpenAI Base URL.

## Why Deploy JimiHub 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 JimiHub 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/jimihub