> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fallom.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Start tracing your LLM calls in 2 minutes

## Get Your API Key

<Steps>
  <Step title="Sign up">
    Create a free account at [app.fallom.com](https://app.fallom.com)
  </Step>

  <Step title="Copy your API key">
    Go to **Settings → API Keys** and copy your key
  </Step>
</Steps>

## Install the SDK

<Tabs>
  <Tab title="TypeScript">
    ```bash theme={null}
    npm install @fallom/trace
    ```
  </Tab>

  <Tab title="Python">
    ```bash theme={null}
    pip install fallom
    ```
  </Tab>
</Tabs>

## Add 3 Lines of Code

<Tabs>
  <Tab title="TypeScript">
    ```typescript theme={null}
    import fallom from "@fallom/trace";
    import OpenAI from "openai";

    // 1. Initialize once at startup
    await fallom.init({ apiKey: process.env.FALLOM_API_KEY });

    // 2. Create a session (groups related calls)
    const session = fallom.session({
      configKey: "my-app",
      sessionId: "user-123",
    });

    // 3. Wrap your client
    const openai = session.wrapOpenAI(new OpenAI());

    // Done! All calls are now traced
    const response = await openai.chat.completions.create({
      model: "gpt-4o",
      messages: [{ role: "user", content: "Hello!" }],
    });
    ```
  </Tab>

  <Tab title="Python">
    ```python theme={null}
    import os
    import fallom
    from openai import OpenAI

    # 1. Initialize once at startup
    fallom.init(api_key=os.environ["FALLOM_API_KEY"])

    # 2. Create a session (groups related calls)
    session = fallom.session(
        config_key="my-app",
        session_id="user-123",
    )

    # 3. Wrap your client
    openai = session.wrap_openai(OpenAI())

    # Done! All calls are now traced
    response = openai.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    ```
  </Tab>
</Tabs>

## What You Get

Every LLM call is automatically captured:

| Field           | Description                            |
| --------------- | -------------------------------------- |
| **Model**       | Which model was used                   |
| **Tokens**      | Input, output, and cached counts       |
| **Latency**     | Request duration + time to first token |
| **Cost**        | Calculated from token usage            |
| **Prompts**     | Full messages sent                     |
| **Completions** | Model responses                        |
| **Session**     | Grouped by user/conversation           |

<Card title="View Your Traces" icon="gauge" href="https://app.fallom.com">
  Open the dashboard to see your LLM calls in real-time
</Card>

## Next Steps

<CardGroup cols={2}>
  <Card title="Tracing" icon="magnifying-glass" href="/tracing">
    Custom spans, metadata, and advanced tracing
  </Card>

  <Card title="Model A/B Testing" icon="flask" href="/model-testing">
    Test different models in production
  </Card>

  <Card title="Evals" icon="clipboard-check" href="/evals">
    Run evaluations on your outputs
  </Card>

  <Card title="Integrations" icon="plug" href="/integrations/typescript/openai">
    Anthropic, OpenRouter, Vercel AI SDK, and more
  </Card>
</CardGroup>