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

# Introduction

> Toolken is a managed LLM gateway. Change one base URL to get cost per agent, feature, and customer, with rate limits, and nothing to host.

**Point your client at one URL. Every call comes back tagged with its cost.**

<Frame caption="Your account overview: spend, requests, and errors in one place">
  <img src="https://mintcdn.com/toolken/B9FQGhQVN-q79Dqo/images/dashboard-overview.png?fit=max&auto=format&n=B9FQGhQVN-q79Dqo&q=85&s=6cea8a13b610ff1cddcc6ecc04c04cef" alt="Toolken dashboard overview" width="1440" height="900" data-path="images/dashboard-overview.png" />
</Frame>

## What you get

<CardGroup cols={2}>
  <Card title="Observability" icon="chart-bar">See cost, usage, and performance by agent, feature, and customer.</Card>
  <Card title="Rate limits" icon="gauge-high">Request-rate and concurrent-stream limits enforced at the edge.</Card>
  <Card title="Any provider, your keys" icon="plug">Works with any OpenAI-compatible app. Bring your own provider keys. They are forwarded untouched and never stored.</Card>
  <Card title="Zero infra" icon="server">No servers, no databases. Toolken runs at the edge. You change a URL and you are done.</Card>
</CardGroup>

## Who it's for

Teams running AI agents (OpenClaw, Hermes, or any framework) and SaaS products that need cost per customer.

## Start here

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/get-started/quickstart">Make your first attributed request in under two minutes.</Card>
  <Card title="How Toolken works" icon="diagram-project" href="/get-started/how-toolken-works">See the request flow and what is possible.</Card>
</CardGroup>