OpenAI API Proxy

Fiammetta
Watcher Proxy

Intelligent OpenAI API proxy router. Multi-platform load balancing, automatic circuit breaker recovery, SSE streaming, token quota management — one-line config to connect, seamless SDK compatibility.

Core Features

Enterprise-grade proxy capabilities for OpenAI API, ready to use out of the box

Multi-Platform Routing

Support any OpenAI-compatible platform with weighted load balancing and automatic failover

SSE Streaming

Full support for Chat Completions / Completions streaming and non-streaming proxy

API Key Management

Flexible key distribution, quota control, plan templates and usage tracking

Circuit Breaker & Rate Limiting

Automatic circuit breaker recovery, platform-level RPM/TPM rate limiting for system stability

Usage Statistics

Detailed request logs, token usage statistics, audit logs and system events

SDK Compatible

Standard /v1 path, compatible with OpenAI SDK, just modify base_url to connect

Quick Start

Just modify base_url to connect, seamless SDK compatibility

quickstart.js
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://your-domain.com/v1',
  apiKey: 'sk-your-api-key',
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}
01

Configure Environment

Set DATABASE_URL, JWT_SECRET, ADMIN and other environment variables

02

Start Service

docker-compose up -d for one-click startup with automatic database initialization

03

Get Started

Add upstream platforms and API Keys in the admin panel, modify base_url in your SDK to connect