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

# Quickstart

> Trace your first LLM call in under 2 minutes

<Note>
  Before you begin, make sure you have:

  * A PandaProbe account. Sign up at [app.pandaprobe.com](https://app.pandaprobe.com).
  * A PandaProbe API key + project name.
  * An API key for the LLM provider you want to trace: OpenAI, Gemini, or Anthropic.
</Note>

<Steps>
  <Step title="Install the SDK">
    <Tabs>
      <Tab title="pip">
        ```bash theme={null}
        pip install "pandaprobe[openai,gemini,anthropic]"
        ```
      </Tab>

      <Tab title="uv">
        ```bash theme={null}
        uv add "pandaprobe[openai,gemini,anthropic]"
        ```
      </Tab>
    </Tabs>
  </Step>

  <Step title="Set environment variables">
    ```bash theme={null}
    export PANDAPROBE_API_KEY="your-api-key"
    export PANDAPROBE_PROJECT_NAME="your-project-name"
    ```

    <Note>
      Self-hosting PandaProbe? Set `PANDAPROBE_ENDPOINT="your-endpoint"`.
    </Note>
  </Step>

  <Step title="Wrap your LLM client">
    Choose the provider you want to trace. Make sure the matching provider API key is available in your environment.

    <Tabs>
      <Tab title="OpenAI">
        ```python theme={null}
        from pandaprobe.wrappers import wrap_openai
        from openai import OpenAI

        client = wrap_openai(OpenAI())

        response = client.chat.completions.create(
            model="gpt-5.4",
            messages=[{"role": "user", "content": "What is PandaProbe?"}],
        )

        print(response.choices[0].message.content)
        ```
      </Tab>

      <Tab title="Gemini">
        ```python theme={null}
        from pandaprobe.wrappers import wrap_gemini
        from google import genai

        client = wrap_gemini(genai.Client())

        response = client.models.generate_content(
            model="gemini-3.1-flash-preview",
            contents="What is PandaProbe?",
        )

        print(response.text)
        ```
      </Tab>

      <Tab title="Anthropic">
        ```python theme={null}
        from pandaprobe.wrappers import wrap_anthropic
        from anthropic import Anthropic

        client = wrap_anthropic(Anthropic())

        response = client.messages.create(
            model="claude-sonnet-4-6",
            messages=[{"role": "user", "content": "What is PandaProbe?"}],
        )

        print(response.content[0].text)
        ```
      </Tab>
    </Tabs>
  </Step>

  <Step title="View your trace">
    Open the PandaProbe dashboard. You should see a trace with an LLM span containing the input messages, output, model name, and token usage, all captured automatically.
  </Step>
</Steps>

## What's next?

<CardGroup cols={3}>
  <Card title="LLM Providers" href="/tracing/wrappers/overview">
    Provider wrappers for OpenAI, Anthropic, Gemini, and more
  </Card>

  <Card title="Agent Frameworks" href="/tracing/integrations/overview">
    Framework integrations for LangGraph, CrewAI, and more
  </Card>

  <Card title="Manual Instrumentation" href="/tracing/manual/decorators">
    Full control with decorators and context managers
  </Card>
</CardGroup>

<Note>
  For short-lived scripts, call `pandaprobe.flush()` before the process exits to ensure all traces are sent. Long-running services flush automatically.
</Note>