Quickstart#

See your first LLM trace in Lens Loop in under 5 minutes.

What you'll accomplish

By the end of this guide, you'll capture your first LLM API call as a trace in Lens Loop — complete with prompts, responses, latency, and token usage.

Prerequisites

Lens Loop installed — Download here or use the link from your beta invite email
Lens ID — You'll create one when you first launch Loop (takes < 1 minute)
An LLM API key — OpenAI, Anthropic, or any supported provider
An application that makes LLM API calls — Any language or framework

Download Lens Loop for your platform from your beta invite email or lenshq.io
Run the installer and launch Lens Loop
Sign in with your Lens ID (or create one — it takes less than a minute)

Need detailed instructions?

See Install Lens Loop for platform-specific guidance.

Step 2: Connect Your Application#

Route your LLM API calls through Loop's local proxy. This typically involves two configuration changes:

Set your API base URL to http://localhost:31300/openai/v1
Add the X-Loop-Project header with a project name

The project is created automatically if it doesn't exist.

PythonNode.js

import os
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:31300/openai/v1",  # (1)!
    api_key=os.environ.get("OPENAI_API_KEY"),
    default_headers={
        "X-Loop-Project": "hello-loop",  # (2)!
    }
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello!"}]
)
print(response.choices[0].message.content)

Routes traffic through Lens Loop's local gateway
Tags this trace with your project name

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://localhost:31300/openai/v1", // (1)!
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: {
    "X-Loop-Project": "hello-loop", // (2)!
  },
});

const response = await openai.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Say hello!" }],
});
console.log(response.choices[0].message.content);

Routes traffic through Lens Loop's local gateway
Tags this trace with your project name

Using a different provider?

See Capture Traffic for Anthropic, Azure, Gemini, and local models like Ollama.

Step 3: See Your Trace#

Your trace is now visible in Lens Loop:

Open Lens Loop (if not already open)
In the Navigator, select your project
Click Traces to see your captured requests
Click on a trace to inspect:
- Full prompt and response content
- Token usage and estimated cost
- Latency breakdown
- Model and parameters used

You did it!

You've captured your first LLM trace. Every request routed through Loop will now be observable, searchable, and analyzable.

Next Steps#

Organize with Labels

Add custom labels to group and filter traces by feature, user, or experiment.

Learn about headers
Team Environments

Share traces across your team with a remote Loop Server.

Set up remote capture
Explore the UI

Learn about the Navigator, Traces view, and Details panel.

Using Lens Loop

Troubleshooting

Trace not appearing?

Ensure Lens Loop is running (check your system tray or menu bar)
Verify the X-Loop-Project header matches your project name exactly (case-sensitive)
Check that port 31300 is available and not blocked by a firewall

Connection refused error?

Make sure Lens Loop is running before you run your script
Try restarting Lens Loop

API key issues?

Your actual API key is still sent to the LLM provider — Loop just proxies the request
Ensure OPENAI_API_KEY (or equivalent) is set in your environment

Need more help?

Visit the Lens Loop Forum

Quickstart#

Step 1: Install & Sign In#

Step 2: Connect Your Application#

Step 3: See Your Trace#

Next Steps#