Deploy and Host hajimi - Gemini API Proxy on Railway

hajimi is a high-performance Gemini API proxy built with FastAPI that exposes Google Gemini models through an OpenAI-compatible API. It supports API key rotation, AI Studio and Vertex AI, streaming responses, multimodal inputs, online search, caching, rate limiting, and an easy-to-use web dashboard for managing your AI gateway.

About Hosting hajimi - Gemini API Proxy

hajimi provides a production-ready API gateway for Google's Gemini models while maintaining compatibility with the OpenAI Chat Completions API. This Railway template deploys hajimi with persistent storage, allowing you to securely manage Gemini API keys, configure advanced proxy features, and expose a stable REST API for AI applications. Built on FastAPI, hajimi includes automatic API key polling, streaming and non-streaming responses, multimodal support, optional web search, Vertex AI compatibility, configurable rate limits, caching, and an intuitive web interface. Railway handles deployment, networking, health checks, and scaling so you can focus on building AI-powered applications.

Common Use Cases

• Deploy an OpenAI-compatible Gemini API gateway for AI applications and agents.
• Manage multiple Gemini API keys with automatic polling, failover, and rate limiting.
• Build AI chatbots, coding assistants, automation tools, and LLM-powered applications using Gemini or Vertex AI.

Dependencies for hajimi - Gemini API Proxy Hosting

• Gemini API Keys (Google AI Studio) or Vertex AI Credentials
• Persistent Storage (configuration, cache, and application data)

Deployment Dependencies

• GitHub Repository: https://github.com/wyeeeee/hajimi
• Container Image: https://github.com/wyeeeee/hajimi/pkgs/container/hajimi
• Google AI Studio: https://aistudio.google.com/
• Vertex AI Documentation: https://cloud.google.com/vertex-ai/docs

Implementation Details

Architecture

This Railway template deploys a single FastAPI service that acts as an intelligent proxy between your applications and Google's Gemini APIs.

Key Features

• OpenAI-compatible Chat Completions API
• Gemini AI Studio and Vertex AI support
• Automatic API key rotation and polling
• Streaming and pseudo-streaming responses
• Multimodal support (text, images, and files)
• Online search-enabled models
• Built-in web dashboard
• Configurable rate limiting and abuse protection
• Concurrent request processing with intelligent response caching
• Model whitelist and blacklist support
• Password-protected administration panel
• Docker-based deployment optimized for production

Supported API Endpoints

• /v1/chat/completions
• /v1/models
• /vertex/chat/completions
• /vertex/models
• /aistudio/chat/completions
• /aistudio/models

Why Deploy hajimi - Gemini API Proxy 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 hajimi - Gemini API Proxy 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.