OCRRouter

docTR vs Chunkr

Pick docTR if you want a Python OCR library that returns words and lines with coordinates, runs locally, and carries an Apache-2.0 licence. Pick Chunkr if you need documents turned into HTML or Markdown chunks, for example to feed a RAG pipeline from PDFs and slides. The main split is output: docTR stops at words and lines, while Chunkr does layout parsing and chunking.

docTRmindee/doctrChunkrchunkr/chunkr
TypeOpen sourceOCR API
Price1 credit / page14 credits / page
Per 1,000 pages$1.00$14.00
Typical speed0.9 s / page3.0 s / page
Best forWord-level OCR with positionsLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
LanguagesMainly Latin scriptsMultilingual
Max pages per request5001,000
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
MultilingualNo✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose docTR if

  • You want word-level OCR with a nested page, block, line and word structure and coordinates exported as JSON.
  • You need Apache-2.0 licensing, with no commercial licence needed for closed-source products.
  • You have a Python ML team that wants to choose detection and recognition architectures, with straight or rotated boxes, and train its own models.

Choose Chunkr if

  • You need Markdown or HTML output from PDF, PPT, Word or image files, which docTR does not produce.
  • You are building RAG over PDFs and slides and want layout analysis and semantic chunking.
  • You want a choice between a hosted cloud API and a self-hosted Docker setup with GPU, CPU-only or Mac ARM options.

Key differences

docTRChunkr
LicenceApache-2.0AGPL-3.0 or commercial licence; closed-source use needs the commercial licence
How you run itPython library on PyTorch, with Docker imagesCloud API or self-hosted open-source version via Docker
PriceFree, self-hosted; you pay for computeHosted credit-based plans (prices not verified); open-source version is free, you pay for compute and an LLM endpoint
Output formatsJSON, plain text, bounding boxesHTML, Markdown, JSON, bounding boxes
Tables and MarkdownNo table, formula or Markdown output; words and lines onlyMarkdown and HTML output with layout analysis
Hardware and dependenciesCPU or NVIDIA GPU; GPU Docker images need CUDA 12.2 or newer on the hostSelf-host needs an external OpenAI-compatible LLM endpoint
Known issuesSplit-crop merging can misjoin readings across repeated characters (issue #2229); cropped images give poorer results (issue #2007); ONNX export of MASTER truncates decoding steps (issue #2224)Open-source version uses community models that are less accurate than the cloud's in-house models; Excel is not supported in the open-source version

Sources

What each one is

docTR

Open-source OCR library from Mindee with separate text detection and recognition models.

docTR details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "mindee/doctr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

docTR alternativesChunkr alternativesBest OCR models in 2026