This guide will help you start logging your LLM requests with Muxx in just a few minutes.
Prerequisites
- A Muxx account (sign up here)
- An API key from your LLM provider (OpenAI, Anthropic, or Google)
Step 1: Create a Project
- Log in to the Muxx dashboard
- Create or select an organization
- Click New Project and give it a name
- Add your LLM provider API key in the project settings
Step 2: Create Your Muxx API Key
- In your project, go to Settings → API Keys
- Click Create Key
- Choose Live for production or Test for development
- Click Create and copy the key immediately
muxx_sk_live_xxxxxxxxxxxxxxxxxxxx
The full key is only shown once. Store it securely—you’ll need it to authenticate requests.
See API Keys for more details on key management and security best practices.
Step 3: Choose Your Integration
Gateway Only
Python SDK
TypeScript SDK
The simplest option—just change your base URL.from openai import OpenAI
client = OpenAI(
api_key="your-openai-key", # Or use OPENAI_API_KEY env var
base_url="https://gateway.muxx.dev/v1",
default_headers={
"X-Muxx-Api-Key": "muxx_sk_live_xxxxxxxxxxxx"
}
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
For deeper tracing with spans and decorators.from muxx import Muxx
from openai import OpenAI
muxx = Muxx(api_key="muxx_sk_live_xxxxxxxxxxxx")
client = muxx.wrap(OpenAI())
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
For Node.js and TypeScript applications.import { Muxx } from 'muxx';
import OpenAI from 'openai';
const muxx = new Muxx({ apiKey: 'muxx_sk_live_xxxxxxxxxxxx' });
const client = muxx.wrap(new OpenAI());
const response = await client.chat.completions.create({
model: 'gpt-4o',
messages: [{ role: 'user', content: 'Hello!' }],
});
Step 4: View Your Logs
After making a request, head to the Muxx dashboard. You’ll see:
- Request logs with full payloads
- Token usage and cost breakdown
- Latency measurements
- Model and provider information
Next Steps
Gateway Setup
Configure caching, rate limiting, and more
Python SDK
Add tracing and observability decorators
TypeScript SDK
Integrate with your Node.js application
Dashboard Guide
Explore analytics and team features