> ## 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.

# Introduction

> Gatelit is an AI gateway that routes authenticated LLM calls from any client through a single endpoint — with provider routing, org-scoped API keys, structured output, and request logging.

Welcome to Gatelit. Instead of calling OpenAI, Anthropic, Google, or Mistral directly from your app and scattering API keys and provider logic across your codebase, you send every LLM request through one endpoint. Gatelit handles authentication, routes the request to the right provider using your org's API keys, normalizes the response, and logs the request — so your application code stays clean and consistent no matter how many models or providers you use.

## What you get

<CardGroup cols={2}>
  <Card title="Single endpoint" icon="arrow-right-arrow-left">
    One URL, one request format, and one response shape for every provider and model. Switch from `openai/gpt-4o` to `anthropic/claude-3-5-sonnet-20241022` by changing a single string.
  </Card>

  <Card title="Three auth modes" icon="lock">
    Issue short-lived HMAC tokens from your backend (`GatelitSigned`), pass OIDC tokens from Clerk, Supabase Auth, or Auth0 (`Bearer`), or use long-lived service keys for backend-to-backend calls (`GatelitKey`).
  </Card>

  <Card title="Structured output" icon="brackets-curly">
    Request JSON responses from any supported model using `json_object` or `json_schema` mode. Gatelit applies the correct provider-specific adapter automatically.
  </Card>

  <Card title="Request logging" icon="list">
    Every request is logged with token counts, estimated cost, latency, model used, and the auth identity — all visible in the dashboard without any instrumentation in your app.
  </Card>

  <Card title="Bring your own keys" icon="key">
    Each organization can supply its own OpenAI, Anthropic, Google, and Mistral API keys. The gateway uses your org's key for every request, keeping spend and quotas fully scoped to your account.
  </Card>

  <Card title="Saved prompts" icon="file-text">
    Store versioned prompt templates in the dashboard and execute them by reference. Variables are resolved at request time, and every execution is correlated to the prompt in the logs.
  </Card>
</CardGroup>

## Supported providers

Gatelit currently supports four LLM providers. Use any model from these providers by prefixing the model name with the provider identifier:

| Provider  | Prefix      | Example model                          |
| --------- | ----------- | -------------------------------------- |
| OpenAI    | `openai`    | `openai/gpt-4o`                        |
| Anthropic | `anthropic` | `anthropic/claude-3-5-sonnet-20241022` |
| Google    | `google`    | `google/gemini-1.5-pro`                |
| Mistral   | `mistral`   | `mistral/mistral-large-latest`         |

## Auth modes at a glance

| Mode            | Header format                | Best for                                                                                                            |
| --------------- | ---------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| `GatelitSigned` | `GatelitSigned <hmac-token>` | Frontend or mobile clients — your backend issues a short-lived token (60 s TTL) scoped to a specific user and model |
| `Bearer`        | `Bearer <oidc-token>`        | Apps already using Clerk, Supabase Auth, or Auth0 — pass the user's existing token directly                         |
| `GatelitKey`    | `GatelitKey <service-key>`   | Server-to-server calls where a long-lived key is acceptable                                                         |

## Where to go next

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

  <Card title="How it works" icon="workflow" href="/how-it-works">
    Understand the full request lifecycle — auth, provider routing, BYOK, and logging.
  </Card>

  <Card title="Authentication" icon="shield" href="/authentication/overview">
    Choose the right auth mode and learn how to issue tokens.
  </Card>

  <Card title="SDK reference" icon="code" href="/sdk/gatelit-client">
    Full reference for `GatelitClient`, `signToken`, and the `Conversation` helper.
  </Card>
</CardGroup>