OpenRouter

Route OpenRouter model calls through Keywords AI Gateway using your own OpenRouter credits.

This section is for Keywords AI LLM gateway users.

Use Keywords AI Gateway to call OpenRouter models while keeping unified observability (logs, cost, latency, and reliability metrics) in Keywords AI — and optionally charge usage to your own OpenRouter credits.

Prerequisites

• A Keywords AI API key
• An OpenRouter API key (BYOK credits)

Get OpenRouter API key

Retrieve your API key from OpenRouter to begin integration.

Supported SDKs / integrations

✅ Supported Frameworks

• OpenAI SDK
• LangChain SDK
• Vercel/OpenAI
• Vercel/Google
• LlamaIndex SDK
• Google GenAI
• Keywords native (Otel)

❌ Unsupported Frameworks

• Anthropic SDK
• Vercel/Anthropic

Configuration

There are 2 ways to add your OpenRouter credentials to your requests:

Via UI (Global)

1. Navigate to Providers

   Go to the Providers page. This page allows you to manage credentials for over 20+ supported providers.

   
2. Add your OpenRouter API Key

   Select OpenRouter and paste your API key.

   
3. Configure Load Balancing (Optional)

   You can add multiple OpenRouter API keys for redundancy. Use the Load balancing weight field to determine how traffic is distributed between keys.

Via code (Per-Request)

You can pass credentials dynamically in the request body. This is useful if you need to use your users’ own API keys (BYOK credits).

Add the customer_credentials parameter to your Gateway request:

{
  // Rest of the request body
  "customer_credentials": {
    "openrouter": {
      "api_key": "YOUR_OPENROUTER_API_KEY"
    }
  }
}

Log OpenRouter requests

If you are not using the Gateway to proxy requests, you can still log your OpenRouter requests to Keywords AI asynchronously. This allows you to track cost, latency, and performance metrics for external calls.

OpenRouter Python SDK

import requests

url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
    "model": "openai/gpt-4o",
    "prompt_messages": [
        {
            "role": "user",
            "content": "Explain quantum computing"
        }
    ],
    "completion_message": {
        "role": "assistant",
        "content": "Quantum computing is a computing paradigm that uses quantum mechanics to process information..."
    },
    "cost": 0.002,
    "generation_time": 3.1,
    "customer_params": {
        "customer_identifier": "user_789"
    }
}
headers = {
    "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, json=payload)

Get Started with Logging

Learn how to set up comprehensive logging for all your LLM requests