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

# Quickstart

> Go from zero to a working LLM request through your own Guardway gateway in about ten minutes.

From zero to your first request through a Guardway gateway in roughly **10 minutes**.

## Before you start

* A machine or VM with Docker installed (see [Requirements](/guardway-gateway/requirements))
* An API key from at least one LLM provider (OpenAI, Anthropic, Groq, etc.)
* Network egress on port 443 to `api.guardway.ai` and your provider's API

## The six steps

<Steps>
  <Step title="Sign up for Guardway">
    Create your account at [app.guardway.ai](https://app.guardway.ai). You'll receive an invite email, set a password, and land on the dashboard.

    [Full walkthrough →](/getting-started/sign-up)
  </Step>

  <Step title="Deploy a gateway">
    In the dashboard, open **Gateways** and click **Register New Gateway** to generate a one-time registration token. Paste it into the `docker run` command the dialog gives you and start the container on any host in your network.

    [Full walkthrough →](/guardway-gateway/deploy)
  </Step>

  <Step title="Activate the gateway">
    Within a minute the gateway sends a heartbeat and appears as **Online** in the Gateways list. Click **Connect** to point the dashboard at its local URL.

    [Full walkthrough →](/guardway-gateway/activate)
  </Step>

  <Step title="Connect a provider">
    Open **Configuration → Providers**, pick a preset (OpenAI, Anthropic, Groq, etc.), paste your API key, and attach it to your gateway.

    [Full walkthrough →](/platform/configuration/providers)
  </Step>

  <Step title="Sync models">
    Open **Configuration → Models** and click **Sync Models** on the provider. The gateway discovers what's available and enables them for inference.

    [Full walkthrough →](/platform/configuration/models)
  </Step>

  <Step title="Test in the Playground, then check logs">
    Open the **Playground**, pick a model, send a message. Then open **Monitoring → Logs** to see the request and **Monitoring → Traces** to see how it flowed through guardrails, routing, and the provider.

    [Playground →](/platform/playground) · [Logs & Traces →](/platform/logs)
  </Step>
</Steps>

## What's next

<CardGroup cols={2}>
  <Card icon="shield-check" title="Configure guardrails" href="/platform/configuration/security#guardrails">
    Turn on PII detection, prompt-injection protection, and content moderation.
  </Card>

  <Card icon="users" title="Invite your team" href="/platform/settings/members">
    Add teammates, set roles, and assign teams to budgets.
  </Card>

  <Card icon="key" title="Issue API keys" href="/platform/configuration/api-keys">
    Create scoped API keys for your applications.
  </Card>

  <Card icon="chart-line" title="Watch usage and spend" href="/platform/dashboard/usage">
    Track tokens, cost, and latency per model, team, and key.
  </Card>
</CardGroup>