Updated

Chunkr

Document intelligence API that parses PDFs, spreadsheets and images into LLM-ready HTML, Markdown or JSON, with OCR, layout detection, reading order, bounding boxes and schema-based extraction; the core is open source. Chunkr is joining Extend, and the hosted API shuts down on 15 November 2026.

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

Open sourceSelf-hostable

Shutting down · Nov 2026: Chunkr is joining Extend. The hosted Chunkr API shuts down on 15 November 2026, with a migration guide to Extend. The AGPL repository stays available for self-hosting. Source ↗

Profile checked

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

How makers use Chunkr

What Chunkr is used for

Document Parsing · Open-source library + hosted API →Turning PDFs, spreadsheets and images into LLM-ready Markdown, HTML or JSON with layout detection and bounding boxes.Trade-off: The hosted API shuts down on 2026-11-15 as Chunkr joins Extend; self-hosting means AGPL terms.
Reducto11Unstructured1Carbon1Docling0MarkItDown0Chunkr0Makers' products on each, for document parsing

Chunkr vs the alternatives makers chose

OptionMakers' productsOpen source
Reducto11 85%No
Carbon1 8%No
Unstructured1 8%Yes
Chunkr0 0%Yes

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

When to use Chunkr, and when not

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.
  • Layout and tables matter and documents must stay on your own machines: Docling or Marker.
  • 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.

Who uses it

No maker's live product on record yet, and 4 open-source projects that declare it in their code.

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

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

Alternatives to Chunkr

All alternatives by situation →

Questions makers ask about Chunkr

What are the alternatives to Chunkr?

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 Chunkr alternatives page.

Is Chunkr open source or self-hostable?

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

Can AI coding agents work with Chunkr?

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

Who uses Chunkr?

No maker's live product we track yet; 4 open-source projects declare it in their code. source ↗