Convert PDF to Markdown
Convert PDF documents to clean Mathpix Markdown with math notation, tables, and document structure preserved. Perfect compatibility with Snip web app and VS Code.
- Equations as LaTeX inside the Markdown, ready to render
- Tables as Markdown tables, images extracted alongside
- Plain text you can diff, review and put in version control
- Compatible with Snip web app and VS Code
Markdown that keeps the mathematics
Mathpix Markdown is ordinary Markdown plus the structures scientific documents need: equations, tables, theorem environments, figure captions and page breaks.
Math inside Markdown
Equations are written as LaTeX between delimiters, which is what every Markdown renderer with math support expects.
Tables as Markdown tables
Not as pre-formatted blocks or screenshots. Where a table is too structured for Markdown, the HTML form is available instead.
A format you can review
Markdown is text, so a converted document goes into git, shows up in a diff, and can be corrected by anyone without a licence.
What Mathpix recognizes in PDF files
Reading order on multi-column pages
Resolved during recognition, so the Markdown reads top to bottom rather than column by column.
Algorithms keep their line structure
Recognized as their own blocks, so an algorithm keeps its line structure instead of becoming a paragraph.
Captions stay with their figures
Annotated structures rather than stray lines, so they stay attached to the figure or the page they belong to.
How to convert PDF to Markdown
1
Upload your PDF
Drag it into the Mathpix Snip web editor, or pick it from your files.
2
Convert it to Markdown
Recognition runs on the whole document: math, tables, figures and layout together.
3
Export or copy the Markdown
Download the Markdown, or copy it straight to the clipboard and paste it where you need it.
What Mathpix accepts, and the limits that apply
Which files you can send
PDF, EPUB, Word (DOCX, DOC), PowerPoint (PPTX), OpenDocument Text (ODT), DjVu, WordPerfect (WPD), Mobipocket (MOBI) and Amazon Kindle (AZW3)
What you get back
Mathpix Markdown (.mmd) and standard Markdown (.md), or a zip that carries the extracted images.
The size limits that apply
One PDF, uploaded: 1 GB
Files API, per file: 15 GB
Files API, files per job: 200,000
Our PDF to Markdown conversion tools
On-premise PDF Cloud
Use all PDF processing features with a self-hosted, fully contained solution.
Learn more
Converting PDF to Markdown: common questions
What is the difference between Mathpix Markdown and Markdown?
Mathpix Markdown is a superset: everything valid in Markdown plus equations, tables, theorem environments and page breaks. Standard Markdown is also available as an output if you need the lowest common denominator.
Where do the images go?
Export as a zip and they come out as files, referenced from the Markdown. Export as plain .mmd and they are referenced by URL instead.
Can I feed this to an LLM?
That is one of the main reasons people convert to Markdown. It is the format that survives a context window without losing the mathematics.
Other formats you can convert PDF to
Mathpix Markdown
Learn about our STEM-enhanced Markdown format.
PDF to LaTeX
Convert PDFs to clean LaTeX source code.
PDF to Word
Convert PDFs to editable Word documents.