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

# Gatelit Documentation

> Route authenticated LLM calls from any client through a single endpoint — with provider routing, org-scoped API keys, structured output, and request logging.

Gatelit is an AI gateway that sits between your applications and LLM providers. Any client — frontend, backend, or AI agent — makes authenticated LLM calls through a single endpoint. Provider routing, org-scoped keys, structured output, and request logging live in the gateway, not scattered across your codebase.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Make your first authenticated LLM request in minutes.
  </Card>

  <Card title="Authentication" icon="lock" href="/authentication/overview">
    Choose the right auth mode for your use case.
  </Card>

  <Card title="JavaScript SDK" icon="js" href="/sdk/installation">
    Install and use the GatelitClient in any JS/TS project.
  </Card>

  <Card title="Vue SDK" icon="vuejs" href="/sdk-vue/installation">
    Add reactive AI streaming to your Vue app with one composable.
  </Card>
</CardGroup>

## How Gatelit works

<Steps>
  <Step title="Authenticate">
    Your backend issues a short-lived signed token (or use an OIDC token or a long-lived service key) that authorizes a specific model and user.
  </Step>

  <Step title="Send a request">
    Call `POST /v1/chat/completions` with the model in `provider/model-name` format. Gatelit routes to the right provider automatically.
  </Step>

  <Step title="Receive the response">
    Get back a standard OpenAI-compatible response — or stream it chunk by chunk. Token usage and cost are logged automatically.
  </Step>

  <Step title="Inspect in the dashboard">
    View request logs, manage provider keys, configure models, and edit saved prompts — all from the Gatelit dashboard.
  </Step>
</Steps>

## Explore

<CardGroup cols={2}>
  <Card title="Guides" icon="book-open" href="/guides/first-request">
    Step-by-step walkthroughs for streaming, structured output, prompt management, and more.
  </Card>

  <Card title="Gateway API" icon="server" href="/api/chat-completions">
    Full reference for `POST /v1/chat/completions` and `POST /v1/prompts/:id/run`.
  </Card>

  <Card title="Dashboard" icon="chart-bar" href="/dashboard/overview">
    Manage keys, view logs, and control which models your org can use.
  </Card>

  <Card title="Bring Your Own Key" icon="key" href="/guides/byok">
    Use your own provider API keys scoped to your organization.
  </Card>
</CardGroup>