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

# Document processing

> Document processing models available on Tinfoil for file conversion, text extraction, and document parsing.

<Card>
  <div style={{ display: 'flex', alignItems: 'center', gap: '16px', marginBottom: '16px' }}>
    <img src="https://mintcdn.com/tinfoil/QPXTScLceEkhaLM_/images/model-icons/doc-upload-light.png?fit=max&auto=format&n=QPXTScLceEkhaLM_&q=85&s=bbbfe079e7a202ce6232304b273af3f7" alt="Document Processing" style={{ height: '40px', width: '40px', flexShrink: 0 }} className="hidden dark:block" width="256" height="256" data-path="images/model-icons/doc-upload-light.png" />

    <img src="https://mintcdn.com/tinfoil/RB5ba1dQe7Ph1q3f/images/model-icons/doc-upload.png?fit=max&auto=format&n=RB5ba1dQe7Ph1q3f&q=85&s=8fb81824cf6f37defac445624dcbf271" alt="Document Processing" style={{ height: '40px', width: '40px', flexShrink: 0 }} className="dark:hidden block" width="256" height="256" data-path="images/model-icons/doc-upload.png" />

    <div style={{ display: 'flex', alignItems: 'center', gap: '12px' }}>
      <div id="doc-upload" className="model-anchor" style={{ fontSize: '18px', fontWeight: 'bold' }}>Document Processing</div>

      <a href="#doc-upload" className="model-id-link" style={{ textDecoration: 'none' }}>
        <code className="text-xs text-gray-500 bg-gray-100 dark:bg-gray-800 dark:text-gray-300 px-1.5 py-0.5 rounded">doc-upload</code>
      </a>
    </div>
  </div>

  **Capabilities:** Document processing and conversion service

  **Strengths:** PDF processing with sandboxed MuPDF extraction, VLM OCR for scanned pages and images, Word and spreadsheet parsing

  **Best for:** Document upload, processing, conversion, text extraction, and OpenAI-compatible file input workflows

  **Configuration repo:** [tinfoilsh/confidential-doc-upload](https://github.com/tinfoilsh/confidential-doc-upload)

  <Info>
    **File Support:** Supports PDF, DOCX, PPTX, XLSX, HTML, CSV, images, and plain text formats. Born-digital PDFs are parsed with MuPDF; scanned pages and images use VLM OCR. This service powers both direct `/v1/convert/file` requests and base64 `file_data` attachments on `/v1/responses` and `/v1/chat/completions`. See the [Document Processing Guide](/guides/document-processing) for usage examples.
  </Info>
</Card>

## Getting started

See the [Document Processing Guide](/guides/document-processing) for usage examples covering direct conversion, Responses API file inputs, and Chat Completions file inputs.