Updated

Marker

Open-source PDF and document converter from Datalab that uses layout and OCR models to produce Markdown, JSON or HTML, with a hosted API.

2 open-source projects declare Marker in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostable

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Marker

What Marker is used for

Document Parsing · Open-source library + hosted API →Accurate PDF-to-Markdown with layout, tables, equations and OCR from local models, or the same through Datalab's hosted API.Trade-off: The model weights are free only for research, personal use and startups under $5M in funding or revenue; slow without a GPU.
Reducto11Unstructured1Carbon1Docling0MarkItDown0Marker0Makers' products on each, for document parsing

Marker vs the alternatives makers chose

OptionMakers' productsOpen source
Reducto11 85%No
Carbon1 8%No
Unstructured1 8%Yes
Marker0 0%Yes

For document parsing: how many of the 13 makers' products we know the document parsing of chose each option.

When to use Marker, and when not

Pick Marker if

Something else fits better if

  • You only need the text out of born-digital PDFs, fast and free: pypdf or pdf-parse or PyMuPDF.
  • You want Markdown from many file types with one local tool: MarkItDown or Docling.
  • Your inputs mix PDFs, emails, HTML and office files and you may move to a hosted API later: Unstructured.
  • Scans, dense tables or forms where a parsing error means a wrong answer: Reducto or LlamaParse or Mistral AI.
From each decision's guide, written from what makers' products chose and why.

How Marker itself is built

9 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet, and 2 open-source projects that declare it in their code.

We haven't found a maker's live product that uses Marker yet — only the open-source projects below, which declare it in their code.

Open source: a project that declares Marker as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to Marker

All alternatives by situation →

Questions makers ask about Marker

What are the alternatives to Marker?

For document parsing, the other options makers' products we track chose most are Reducto (11), Carbon (1), Unstructured (1). Open source or self-hostable among them: Unstructured. Each alternative, with the situation it fits, is on the Marker alternatives page.

When should you use Marker?

Layout and tables matter and documents must stay on your own machines (document parsing). Something else fits better if: you only need the text out of born-digital PDFs, fast and free, pick pypdf or pdf-parse or PyMuPDF; you want Markdown from many file types with one local tool, pick MarkItDown or Docling.

Is Marker open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Marker?

No llms.txt, official MCP server or CLI found yet.

Who uses Marker?

No maker's live product we track yet; 2 open-source projects declare it in their code. source ↗