Skip to main content
This section is for Keywords AI LLM gateway users.
Use Keywords AI Gateway to call OpenAI models while keeping unified observability (logs, cost, latency, and reliability metrics) in Keywords AI.

​
Prerequisites

  • A Keywords AI API key
  • An OpenAI API key (BYOK)

Get OpenAI API key

Retrieve your API key from the OpenAI platform to begin integration.

​
Supported SDKs / integrations

​
Configuration

There are 2 ways to add your OpenAI 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.
Keywords AI Providers Page
2

Add your OpenAI API Key

Select OpenAI and paste your API key.Add OpenAI Credentials
3

Configure Load Balancing (Optional)

You can add multiple OpenAI 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). Add the customer_credentials parameter to your Gateway request: 
{
  // Rest of the request body
  "customer_credentials": {
    "openai": {
      "api_key": "YOUR_OPENAI_API_KEY",
    }
  }
}

​
Log OpenAI requests

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

url = "https://api.keywordsai.co/api/request-logs/create/"
payload = {
    "model": "gpt-4o",
    "prompt_messages": [
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ],
    "completion_message": {
        "role": "assistant",
        "content": "I'm doing well, thank you for asking!"
    },
    "cost": 0.0015,
    "generation_time": 2.3,
    "customer_params": {
        "customer_identifier": "user_123"
    }
}
headers = {
    "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
    "Content-Type": "application/json"
}

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

Get Started with Logging

View the full guide on setting up comprehensive logging for your LLM stack.