🔄 OpenAI Gemini API Key Rotator

A robust Node.js proxy server that automatically rotates API keys for Gemini and OpenAI APIs when rate limits (429 errors) are encountered. Built with zero dependencies and comprehensive logging.

✨ Features

🔄 Automatic Key Rotation: Seamlessly switches to the next API key on 429 errors
🎯 Multi-API Support: Works with both Gemini and OpenAI APIs simultaneously
🔧 Flexible Base URLs: Use custom endpoints or default API servers
📝 Detailed Logging: Track every request, rotation, and error with masked API keys
🚀 Zero Dependencies: Pure Node.js with no external packages
📁 File Upload Support: Handles multipart/form-data and binary uploads
🛡️ Error Handling: Proper error responses and graceful failures

🚀 Quick Start

1. Installation

git clone https://github.com/p32929/openai-gemini-api-key-rotator.git
cd openai-gemini-api-key-rotator

2. Configuration

Copy the example environment file and add your API keys:

cp .env.example .env

Edit .env:

# Required
PORT=3000

# At least one of these is required
GEMINI_API_KEYS=AIzaSyABC123...,AIzaSyDEF456...,AIzaSyGHI789...
OPENAI_API_KEYS=sk-proj-abc123...,sk-proj-def456...,sk-proj-ghi789...

# Optional - Custom base URL for all API calls
# BASE_URL=https://your-custom-server.com

3. Start the Server

npm start

You'll see output like:

[CONFIG] Port: 3000
[CONFIG] Using default API endpoints
[CONFIG] Found 3 Gemini API keys
[CONFIG] Found 2 OpenAI API keys
[GEMINI-ROTATOR] Initialized with 3 API keys
[OPENAI-ROTATOR] Initialized with 2 API keys
Multi-API proxy server running on port 3000
Available Gemini API keys: 3
Gemini endpoints: /gemini/v1/* and /gemini/v1beta/*
Available OpenAI API keys: 2
OpenAI endpoints: /openai/v1/*

🔗 API Endpoints

API	Endpoint Pattern	Example
Gemini	`/gemini/v1/*`	`/gemini/v1/models/gemini-pro:generateContent`
Gemini Beta	`/gemini/v1beta/*`	`/gemini/v1beta/models/gemini-pro:generateContent`
OpenAI	`/openai/v1/*`	`/openai/v1/chat/completions`

📋 Copy-Paste Examples

Gemini API Examples

1. Generate Content (Text)

curl -X POST "http://localhost:3000/gemini/v1/models/gemini-2.5-pro:generateContent" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{
        "text": "Write a short poem about API key rotation"
      }]
    }]
  }'

2. Generate Content with System Instructions

curl -X POST "http://localhost:3000/gemini/v1/models/gemini-2.5-pro:generateContent" \
  -H "Content-Type: application/json" \
  -d '{
    "system_instruction": {
      "parts": [{
        "text": "You are a helpful coding assistant."
      }]
    },
    "contents": [{
      "parts": [{
        "text": "Explain what API rate limiting is"
      }]
    }],
    "generationConfig": {
      "temperature": 0.7,
      "maxOutputTokens": 100
    }
  }'

3. List Models

curl -X GET "http://localhost:3000/gemini/v1/models"

4. Get Model Info

curl -X GET "http://localhost:3000/gemini/v1/models/gemini-2.5-pro"

5. Generate Content with Image (Base64)

curl -X POST "http://localhost:3000/gemini/v1/models/gemini-2.5-pro:generateContent" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {
          "text": "What do you see in this image?"
        },
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "base64_encoded_image_data_here"
          }
        }
      ]
    }]
  }'

6. Generate Content with Image (File Upload)

# First, encode your image to base64
IMAGE_DATA=$(base64 -i path/to/your/image.jpg)

curl -X POST "http://localhost:3000/gemini/v1/models/gemini-2.5-pro:generateContent" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {
          "text": "Describe this image in detail"
        },
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "'$IMAGE_DATA'"
          }
        }
      ]
    }]
  }'

7. Generate Content with Multiple Images

curl -X POST "http://localhost:3000/gemini/v1/models/gemini-2.5-pro:generateContent" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {
          "text": "Compare these two images and tell me the differences"
        },
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "base64_image1_data_here"
          }
        },
        {
          "inline_data": {
            "mime_type": "image/png",
            "data": "base64_image2_data_here"
          }
        }
      ]
    }]
  }'

OpenAI API Examples

1. Chat Completions

curl -X POST "http://localhost:3000/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Explain API key rotation in simple terms"
      }
    ],
    "max_tokens": 150,
    "temperature": 0.7
  }'

2. Chat Completions with Streaming

curl -X POST "http://localhost:3000/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about programming"
      }
    ],
    "stream": true
  }'

3. List Models

curl -X GET "http://localhost:3000/openai/v1/models"

4. Text Completions (Legacy)

curl -X POST "http://localhost:3000/openai/v1/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "prompt": "The benefits of API key rotation are:",
    "max_tokens": 100,
    "temperature": 0.5
  }'

5. Create Embeddings

curl -X POST "http://localhost:3000/openai/v1/embeddings" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": "API key rotation helps maintain service availability"
  }'

6. Vision API - Analyze Image with GPT-4o-mini

curl -X POST "http://localhost:3000/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What do you see in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/image.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }'

7. Vision API - Analyze Local Image (Base64)

# First, encode your image to base64
IMAGE_DATA=$(base64 -i path/to/your/image.jpg)

curl -X POST "http://localhost:3000/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Describe this image in detail"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,'$IMAGE_DATA'"
            }
          }
        ]
      }
    ],
    "max_tokens": 500
  }'

8. File Upload - Create Assistant File

curl -X POST "http://localhost:3000/openai/v1/files" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@path/to/your/document.pdf" \
  -F "purpose=assistants"

9. Audio Transcription - Upload Audio File

curl -X POST "http://localhost:3000/openai/v1/audio/transcriptions" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@path/to/your/audio.mp3" \
  -F "model=whisper-1"

10. Audio Translation - Upload Audio File

curl -X POST "http://localhost:3000/openai/v1/audio/translations" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@path/to/your/audio.mp3" \
  -F "model=whisper-1"

11. Text-to-Speech - Generate Audio

curl -X POST "http://localhost:3000/openai/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello, this is a test of the text-to-speech API",
    "voice": "alloy"
  }' \
  --output speech.mp3

🔧 Configuration Options

Environment Variables

Variable	Required	Description	Example
`PORT`	✅ Yes	Server port	`3000`
`GEMINI_API_KEYS`	🔶 Optional*	Comma-separated Gemini API keys	`AIza...,AIza...`
`OPENAI_API_KEYS`	🔶 Optional*	Comma-separated OpenAI API keys	`sk-proj-...,sk-proj-...`
`BASE_URL`	❌ No	Custom base URL for all APIs	`https://api.example.com`

*At least one API key type is required

Popular API Provider Examples

# OpenRouter (supports 100+ models including Claude, GPT-4, Llama, etc.)
OPENAI_BASE_URL=https://openrouter.ai/api
OPENAI_API_KEYS=sk-or-v1-your-key-here

# Groq (ultra-fast inference for Llama, Mixtral, Gemma models)
OPENAI_BASE_URL=https://api.groq.com/openai
OPENAI_API_KEYS=gsk_your-groq-key-here

# Together AI (open source models)
OPENAI_BASE_URL=https://api.together.xyz
OPENAI_API_KEYS=your-together-key-here

# Anthropic Claude (direct)
OPENAI_BASE_URL=https://api.anthropic.com
OPENAI_API_KEYS=sk-ant-your-key-here

# Use custom proxy or local server
OPENAI_BASE_URL=https://your-proxy-server.com
# OPENAI_BASE_URL=http://localhost:8080

# Use default endpoints (OpenAI official)
# OPENAI_BASE_URL=

📊 Logging Output

The server provides detailed logging for monitoring and debugging:

[CONFIG] Loading configuration from /path/to/.env
[CONFIG] Port: 3000
[CONFIG] Using default API endpoints
[CONFIG] Found 2 Gemini API keys
[CONFIG] Found 3 OpenAI API keys
[CONFIG] Gemini Key 1: [AIza...1234]
[CONFIG] Gemini Key 2: [AIza...5678]
[CONFIG] OpenAI Key 1: [sk-p...9012]
[CONFIG] OpenAI Key 2: [sk-p...3456]
[CONFIG] OpenAI Key 3: [sk-p...7890]
[GEMINI-ROTATOR] Initialized with 2 API keys
[OPENAI-ROTATOR] Initialized with 3 API keys
[INIT] Gemini client initialized
[INIT] OpenAI client initialized

[REQ-abc123def] POST /openai/v1/chat/completions from 127.0.0.1
[REQ-abc123def] Proxying to OPENAI: /v1/chat/completions
[OPENAI::sk-p...9012] Currently active API key (1/3)
[OPENAI::sk-p...9012] Attempting POST /v1/chat/completions (attempt 1)
[OPENAI::sk-p...9012] Rate limited (429) - rotating to next key
[OPENAI::sk-p...9012] Key marked as failed (1/3 failed)
[OPENAI-ROTATOR] Rotated from index 0 to 1 -> [OPENAI::sk-p...3456]
[OPENAI::sk-p...3456] Currently active API key (2/3)
[OPENAI::sk-p...3456] Attempting POST /v1/chat/completions (attempt 2)
[OPENAI::sk-p...3456] Success (200)
[REQ-abc123def] Response: 200

🛠️ How It Works

Request Routing: Incoming requests are routed based on URL patterns
Key Selection: The first available API key is selected
API Call: Request is forwarded to the appropriate API endpoint
Error Handling:
- 429 (Rate Limited): Automatically rotates to next key and retries
- Other Errors: Returns the original error response
Exhaustion: When all keys are rate-limited, returns 429 with descriptive error

📁 Project Structure

openai-gemini-api-key-rotator/
├── src/
│   ├── config.js          # Environment configuration
│   ├── keyRotator.js      # API key rotation logic
│   ├── geminiClient.js    # Gemini API client
│   ├── openaiClient.js    # OpenAI API client
│   └── server.js          # HTTP proxy server
├── index.js               # Main entry point
├── package.json           # Node.js dependencies
├── .env.example          # Environment template
└── README.md             # This file

Made with ❤️ for developers who hate rate limits

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
src		src
tests		tests
.env.example		.env.example
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
index.js		index.js
package.json		package.json

License

p32929/openai-gemini-api-key-rotator

Folders and files

Latest commit

History

Repository files navigation

🔄 OpenAI Gemini API Key Rotator

✨ Features

🚀 Quick Start

1. Installation

2. Configuration

3. Start the Server

🔗 API Endpoints

📋 Copy-Paste Examples

Gemini API Examples

1. Generate Content (Text)

2. Generate Content with System Instructions

3. List Models

4. Get Model Info

5. Generate Content with Image (Base64)

6. Generate Content with Image (File Upload)

7. Generate Content with Multiple Images

OpenAI API Examples

1. Chat Completions

2. Chat Completions with Streaming

3. List Models

4. Text Completions (Legacy)

5. Create Embeddings

6. Vision API - Analyze Image with GPT-4o-mini

7. Vision API - Analyze Local Image (Base64)

8. File Upload - Create Assistant File

9. Audio Transcription - Upload Audio File

10. Audio Translation - Upload Audio File

11. Text-to-Speech - Generate Audio

🔧 Configuration Options

Environment Variables

Popular API Provider Examples

📊 Logging Output

🛠️ How It Works

📁 Project Structure

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages