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

# Overview

> One API key for every visual model, and the call returns JSON.

* [Read a document](/gateway/guides/document-ocr) — OCR a PDF. One call, one page block per page.
* [Call a model](/gateway/quickstart) — The gateway quickstart: install, set a key, then visual Q\&A, video Q\&A, and document OCR.
* [Run an agent](/agents/introduction) — Hand Orion a file and a question.

## After the first call

<CardGroup cols={2}>
  <Card title="Authentication" icon="key" href="/gateway/authentication">
    Where the key goes, and what a missing key returns.
  </Card>

  <Card title="Models" icon="table-list" href="/gateway/models">
    The catalog, and which model fits the job.
  </Card>

  <Card title="Pricing" icon="dollar-sign" href="/gateway/pricing">
    Per-token rates, and `usage.cost` on the response.
  </Card>

  <Card title="Errors" icon="triangle-exclamation" href="/gateway/error-codes">
    The status codes the gateway returns.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.