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

# Portrix Quickstart: Make Your First AI API Request

> Learn how to send your first AI request through Portrix. Get an API key, install the SDK, and call 400+ models in under 5 minutes.

This page walks you through sending your first AI request via Portrix. By the end, you'll have a working API call that routes through the Portrix gateway to any model in the catalog — all using the same OpenAI SDK you may already have installed.

## Prerequisites

Before you start, make sure you have:

* A Portrix account — sign up for free at [app.portrix.ai](https://app.portrix.ai)
* Basic familiarity with REST APIs or the OpenAI SDK in Python or TypeScript

<Tip>
  Your existing OpenAI code works — just change the base URL and use a Portrix API key.
</Tip>

## Steps

<Steps>
  <Step title="Create your account">
    Go to [app.portrix.ai](https://app.portrix.ai) and sign up for a free account. After you verify your email and complete onboarding, you'll land in the Portrix dashboard. Your API keys are under **Settings → API Keys** in the left sidebar.
  </Step>

  <Step title="Get your API key">
    In the dashboard, navigate to **Settings → API Keys** and click **Create new key**. Give your key a descriptive label (for example, `development` or `my-app-prod`), then click **Create**. Copy the key immediately — it's shown only once. Store it somewhere safe, such as a password manager or secrets vault.
  </Step>

  <Step title="Install the SDK">
    Portrix is OpenAI-compatible, so you use the standard `openai` package. Install it with your preferred package manager:

    <CodeGroup>
      ```bash npm theme={null}
      npm install openai
      ```

      ```bash yarn theme={null}
      yarn add openai
      ```

      ```bash pnpm theme={null}
      pnpm add openai
      ```

      ```bash pip theme={null}
      pip install openai
      ```
    </CodeGroup>
  </Step>

  <Step title="Send your first request">
    Point the OpenAI SDK at the Portrix base URL and use your Portrix API key. Then choose any model from the catalog using the `provider/model-name` format.

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

      client = OpenAI(
          api_key="YOUR_PORTRIX_API_KEY",
          base_url="https://api.portrix.ai/v1",
      )

      response = client.chat.completions.create(
          model="openai/gpt-4o",
          messages=[
              {"role": "user", "content": "Explain what Portrix does in one sentence."}
          ],
      )

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

      ```typescript TypeScript / Node.js theme={null}
      import OpenAI from "openai";

      const client = new OpenAI({
        apiKey: "YOUR_PORTRIX_API_KEY",
        baseURL: "https://api.portrix.ai/v1",
      });

      const response = await client.chat.completions.create({
        model: "openai/gpt-4o",
        messages: [
          { role: "user", content: "Explain what Portrix does in one sentence." },
        ],
      });

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

    Run the code and you should see a response printed to your terminal. That request traveled through the Portrix gateway and was routed to OpenAI's GPT-4o on your behalf.
  </Step>

  <Step title="Explore models">
    Now that your integration is working, try swapping the `model` field to any other model in the Portrix catalog. The rest of your code stays exactly the same.

    ```python Python theme={null}
    # Try any of these models — just change the model field
    model = "anthropic/claude-3-5-sonnet"
    model = "google/gemini-2.0-flash"
    model = "mistral/mistral-large-latest"
    ```

    Browse the full list of available models in the [Supported Models](/help/supported-models) reference.
  </Step>
</Steps>

## Next steps

<CardGroup cols={2}>
  <Card title="Model Selection Guide" icon="layer-group" href="/help/supported-models">
    Browse all 400+ models available through Portrix and learn how to choose the right model for your use case.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Explore the full Portrix API reference, including streaming, tool use, and advanced routing options.
  </Card>
</CardGroup>