Gemini API Tutorial via OpenRouter

This tutorial will guide you through using the Gemini API through OpenRouter's free endpoint. We'll cover setting up the request, making a simple completion call, and interpreting the response.

Prerequisites

• An OpenRouter API key (obtainable from https://openrouter.ai)
• Python 3.x
• requests library (pip install requests)

Installation

pip install requests

Example Code

import requests

API_KEY = "your_openrouter_api_key"
ENDPOINT = "https://api.openrouter.ai/v1/chat/completions"

def get_gemini_response(user_message):
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    payload = {
        "model": "google/gemini-2.0-flash-exp",
        "messages": [{"role": "user", "content": user_message}]
    }
    response = requests.post(ENDPOINT, json=payload, headers=headers)
    response.raise_for_status()
    return response.json()["choices"][0]["message"]["content"]

if __name__ == "__main__":
    user_input = input("Ask Gemini: ")
    print("Gemini says:", get_gemini_response(user_input))

Explanation

• Endpoint: https://api.openrouter.ai/v1/chat/completions is the unified endpoint used by OpenRouter to reach various LLM providers.
• Model: We use google/gemini-2.0-flash-exp as an example; replace with any compatible model.
• Headers: Authorization with Bearer token and Content-Type JSON.
• Payload: The model field specifies which LLM to use, and messages contains the conversation history.

Running the Script

Save the script as gemini_tutorial.py and run:

python gemini_tutorial.py

Enter your message when prompted, and the script will display Gemini's response.

Tips

• Use the free tier of OpenRouter to test without spending credits.
• Adjust the model parameter to try different Gemini variants.
• Handle rate limits by checking the response status code.

By following this tutorial, you'll be able to integrate Gemini into your applications using OpenRouter's API gateway.