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

# Quickstart

> Start observing and managing your LLMs with Traceport in under 5 minutes.

## Get Up and Running

<Steps>
  <Step title="Create an Account">
    Navigate to [app.traceport.ai](https://app.traceport.ai) and sign up for a free account.
  </Step>

  <Step title="Connect Your Providers">
    Traceport routes your LLM requests to the appropriate model providers. Connect your preferred providers first.

    1. Go to **Integrations** in the left sidebar.
    2. Select your provider under the "Available" section.
    3. Input your provider's API key — it is securely stored and used to forward your prompts.

    <Tip>Start with one provider (e.g., OpenAI) and add more later.</Tip>
  </Step>

  <Step title="Generate a Traceport API Key">
    1. Navigate to **API Keys** in the sidebar.
    2. Click **Create New Key**.
    3. Name your key (e.g., "Production API").
    4. Copy the generated key.

    <Warning>Store your API key securely — it won't be shown again after creation.</Warning>
  </Step>

  <Step title="Update Your Codebase">
    Integrating Traceport requires minimal changes. Simply point your SDK to Traceport's gateway URL and use your Traceport API Key.

    <CodeGroup>
      ```python Python (OpenAI SDK) theme={null}
      from openai import OpenAI

      client = OpenAI(
          api_key="<YOUR_TRACEPORT_API_KEY>",
          base_url="https://api.traceport.ai/v1"
      )

      response = client.chat.completions.create(
          model="gpt-4o",
          messages=[
              {"role": "user", "content": "What is observability?"}
          ]
      )

      print(response.choices[0].message.content)
      ```

      ```javascript Node.js (OpenAI SDK) theme={null}
      import OpenAI from "openai";

      const client = new OpenAI({
        apiKey: "<YOUR_TRACEPORT_API_KEY>",
        baseURL: "https://api.traceport.ai/v1"
      });

      const response = await client.chat.completions.create({
        model: "gpt-4o",
        messages: [
          { role: "user", content: "What is observability?" }
        ]
      });

      console.log(response.choices[0].message.content);
      ```
    </CodeGroup>

    <Info>
      Traceport provides an **OpenAI-compatible Gateway API**, so you can use standard OpenAI SDKs (Python, Node.js) or any framework like **LangChain** or **LlamaIndex** that supports custom base URLs.
    </Info>
  </Step>

  <Step title="View Your Logs">
    Run your code, then return to your [Traceport Dashboard](https://app.traceport.ai) and navigate to **Logs**. You'll instantly see your captured completions, latency, and cost in real-time.
  </Step>
</Steps>

## What's Next?

<CardGroup cols={2}>
  <Card title="API Logs" icon="list" href="/observability/api-logs">
    Deep-dive into individual request details, tokens, and costs.
  </Card>

  <Card title="Workflow Traces" icon="diagram-project" href="/observability/workflow-runs">
    Monitor complex multi-step AI workflows end-to-end.
  </Card>

  <Card title="Model Playground" icon="flask" href="/ai-tools/playground">
    Test and compare models interactively before writing code.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Explore the full Traceport Gateway API documentation.
  </Card>
</CardGroup>