Which document formats can Everything to Markdown convert?

Our local browser AST compiler converts HTML, XHTML, XML, CSV, TSV, JSON, RTF, and Markdown in 0ms without an API key. Authenticated requests to POST /api/convert also process binary PDF, DOCX, XLSX, PPTX, ODS, and Apple iWork documents via Cloudflare Workers AI env.AI.toMarkdown().

Why convert HTML and PDF files to Markdown before feeding them to an LLM?

Raw HTML DOM trees and PDF layout streams contain up to 75% boilerplate markup, inline CSS, and scripts. Converting to GitHub-Flavored Markdown reduces input token billing by 60% to 82% while improving retrieval accuracy in RAG pipelines.

Everything to Markdown Studio — AI Document, HTML & PDF to Markdown

Dual-Engine Compiler Ready — Local Browser AST (0ms) + Cloudflare Workers AI Edge

Drop file here or click to browse (.html, .csv, .json, .pdf, .docx, .xlsx, .pptx)

Markup/text files convert locally in 0ms · Binary Office/PDF files use Workers AI /api/convert

Source HTML, XML, JSON, or text payload Auto-counts BPE tokens

<article>
  <header><nav>Home > Docs > AI Engineering</nav></header>
  <h1>Cloudflare Workers AI Document Pipeline</h1>
  <p>Converting noisy HTML and PDF documents into <strong>structured Markdown</strong> reduces LLM context window token consumption by up to <em>74%</em>.</p>
  <h2>Supported Conversion Modes</h2>
  <ul>
    <li><strong>Local AST Compiler:</strong> Instant 0ms conversion in your browser for HTML, CSV, TSV, and JSON.</li>
    <li><strong>Workers AI Edge Binding:</strong> Server-side extraction via <code>env.AI.toMarkdown()</code> for PDF, DOCX, and XLSX.</li>
  </ul>
  <table>
    <thead><tr><th>Format</th><th>Raw Tokens</th><th>Markdown Tokens</th><th>Savings</th></tr></thead>
    <tbody>
      <tr><td>HTML Web Page</td><td>4,280</td><td>1,120</td><td>73.8%</td></tr>
      <tr><td>PDF Technical Spec</td><td>6,900</td><td>2,450</td><td>64.5%</td></tr>
    </tbody>
  </table>
  <pre><code class="language-typescript">const [doc] = await env.AI.toMarkdown([{ name: "spec.pdf", blob }]);</code></pre>
  <footer>Copyright 2026 Boilerplate Footer</footer>
</article>

Strip <nav>/<footer>/<script> Convert HTML <table> to GFM Preserve [links](url) Prepend YAML frontmatter

Document title metadata

Optional X-API-Token (for PDF/DOCX)

Source BPE tokens

182

Markdown BPE tokens

114

Context reduction

-37.4% saved

Active engine

Local AST (0ms)

Compiled GitHub-Flavored Markdown (GFM) output Ready for LLM / RAG ingestion

Chunk for RAG vector DB

Supported Document Formats & Token Reduction Benchmarks

Feeding raw HTML pages or binary PDFs directly into frontier LLMs wastes context window capacity on layout tags and metadata. The table below compares raw token footprints against structured Markdown across common enterprise document formats:

Supported file extensions, execution engine, and average BPE token reduction
Document category	Extensions	Execution engine	Avg token reduction	Table & code preservation
Web & Markup	`.html`, `.htm`, `.xml`	Local Browser AST + Workers AI	68% – 82%	GFM pipe tables & fenced code
Tabular & Structured Data	`.csv`, `.tsv`, `.json`	Local Table Compiler + Workers AI	35% – 54%	Auto-aligned GFM pipe tables
Portable Document Format	`.pdf`	Workers AI env.AI.toMarkdown	58% – 72%	Multi-page heading & table extraction
Microsoft Office Suite	`.docx`, `.doc`, `.xlsx`, `.xlsm`, `.xls`, `.pptx`, `.ppt`	Workers AI env.AI.toMarkdown	60% – 75%	Sheet-to-table & slide outline
OpenDocument & Apple iWork	`.ods`, `.numbers`, `.pages`, `.key`	Workers AI env.AI.toMarkdown	55% – 70%	Structured section hierarchy
Rich & Plain Text	`.txt`, `.md`, `.rtf`	Local Browser AST (0ms)	15% – 40%	Whitespace normalization & YAML frontmatter

Dual-Engine Architecture: Client-Side AST vs. Cloudflare Workers AI

Everything to Markdown Studio combines two complementary conversion pipelines in a single edge deployment:

Zero-Latency Local Browser Engine: When you paste HTML, XML, CSV, TSV, or JSON—or drop markup files onto the workbench—all parsing and GitHub-Flavored Markdown compilation executes 100% locally in your browser's JavaScript runtime with zero network round-trips.
Authenticated Cloudflare Workers AI Edge API (POST /api/convert): For binary containers such as PDF reports, Word documents, and Excel workbooks, our Hono Worker invokes Cloudflare's native env.AI.toMarkdown() binding at the edge and returns both the extracted Markdown string and exact token count.

Everything to Markdown & LLM Context Compression Workbench

Supported Document Formats & Token Reduction Benchmarks

Dual-Engine Architecture: Client-Side AST vs. Cloudflare Workers AI