PDF to Markdown guides
Answer-first, practical guides to turning PDFs into clean, LLM-ready Markdown – pick the one that matches your job.
Choose a guide
Each guide answers the question first, then walks through the steps and the edge cases.
Get started & use cases
Scanned PDF to Markdown (OCR)
Turn image-only and scanned PDFs into selectable Markdown with built-in OCR across many languages. Real tables, formulas kept.
PDF to Markdown for RAG
Prepare PDFs as clean, chunk-friendly Markdown for RAG and LLM ingestion, with a copyable REST + hosted-MCP recipe.
Extract tables from PDF to Markdown
Get real, aligned Markdown tables out of a PDF, keep formulas, and OCR scanned tables. Not screenshots.
PDF to Markdown for Obsidian & Notion
Convert a PDF to clean Markdown and import it into an Obsidian vault or Notion, with headings, tables and links intact.
PDF Formulas & LaTeX to Markdown
Convert a PDF with equations to Markdown and keep the math - inline and block formulas preserved as LaTeX-style notation, not garbled.
Extract images from PDF to Markdown
Keep figures when converting a PDF: images embedded inline or as light placeholders, with OCR for any text on the page.
Convert arXiv PDF to Markdown
Turn a research paper into clean Markdown straight from its PDF link - equations, tables and references kept, ready for LLMs.
Convert invoice PDF to Markdown
Convert invoices and receipts to Markdown: line-item tables rebuilt, scanned receipts OCR'd, ready to parse or feed to an LLM.
For AI assistants
PDF to Markdown for ChatGPT
Convert a PDF to clean Markdown for ChatGPT - tables and formulas kept, fewer tokens, more in context - or wire a Custom GPT Action.
PDF to Markdown for Claude
Feed PDFs to Claude as clean Markdown: token-efficient context, reliable tables, or let Claude convert them itself via the hosted MCP.
PDF to Markdown for Gemini
Prepare PDFs for Gemini as clean Markdown: compact, table-safe context for long and multi-document analysis, or convert via the API.
Developers & API
Convert PDF to Markdown in Python
A step-by-step Python tutorial for the REST API: create a job, poll, and download clean Markdown, with error handling.
Convert PDF to Markdown in Node.js
A Node 18+ tutorial for the REST API: create, poll and download with the global fetch and no dependencies, plus error handling and file upload.
Convert PDF to Markdown in Go
A Go tutorial for the REST API using net/http and typed structs: create, poll and download, plus a concurrent worker-pool pattern and context timeouts.
Convert PDF to Markdown with cURL
A command-line recipe with curl and jq: create, poll and download from the shell, ready to drop into a CI step or a cron job.
Batch convert PDFs to Markdown
Convert many PDFs at once with the REST API: loop, poll each job, and download, with idempotency-safe retries and concurrency.
Compare converters
PDF to Markdown vs Marker
Marker is a self-hosted GPU library; pdf2md.dev is hosted and free with OCR, tables, a REST API and a hosted MCP. An honest side-by-side.
PDF to Markdown vs LlamaParse
LlamaParse is a credit-metered cloud API needing an account; pdf2md.dev is free and anonymous with OCR, a REST API and a hosted MCP.
PDF to Markdown vs MarkItDown
MarkItDown is a local MIT library with no built-in OCR; pdf2md.dev is hosted with OCR, real table reconstruction, a REST API and a hosted MCP.
PDF to Markdown vs Adobe PDF Extract
Adobe PDF Extract is enterprise SaaS with quote-only pricing; pdf2md.dev is free, instant and public with OCR, a REST API and a hosted MCP.
PDF to Markdown vs Mistral OCR
Mistral OCR is a pay-per-page API needing a key; pdf2md.dev is free and anonymous with OCR, real tables, a REST API and a hosted MCP.
Best PDF to Markdown Converters (2026)
A ranked, honest roundup of the top PDF to Markdown tools - hosted, open-source and enterprise - with a side-by-side table and who each is best for.
Reference
PDF to Markdown Glossary
Short, plain-language definitions of the PDF to Markdown, OCR, RAG and Markdown terms used across these guides, each linking to a deeper guide.
Changelog
What's new in pdf2md.dev - a dated log of product and content updates, newest first, with an Atom feed.
PDF to Markdown Benchmark
Speed and reliability on real production traffic: ~2,940 conversions, 99.8% success, with median time by document size.
Building an integration or agent?
Beyond the guides, the converter is a REST API and a hosted MCP endpoint, with machine-readable discovery so scripts and agents can find and use it.