OCRRouter

docTR vs MonkeyOCR

Pick docTR if you need word-level text with coordinates from a Python library under Apache-2.0, for example invoices and receipts that feed your own extraction. Pick MonkeyOCR if you need Markdown, tables and formulas from English or Simplified Chinese PDFs, and your use is research or you hold a written license. The main split is output: docTR returns words and lines only, while MonkeyOCR parses full document structure but its v1 weights block commercial use without a license.

docTRmindee/doctrMonkeyOCRmonkeyocr/monkeyocr
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed0.9 s / page1.5 s / page
Best forWord-level OCR with positionsChinese and English PDFs
InputsPDF, imagesPDF, images
LanguagesMainly Latin scriptsChinese, English
Max pages per request500500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
MultilingualNoNo
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

  • The whole library is Apache-2.0, so you can ship it in a commercial product without asking anyone.
  • It exports a nested page, block, line and word structure with coordinates as JSON, which suits custom extraction on invoices and receipts.
  • You can choose detection and recognition architectures, use straight or rotated boxes, and train your own models in Python.

Choose MonkeyOCR if

  • It outputs Markdown, JSON, LaTeX, HTML and bounding boxes, so tables and formulas in academic papers come out as structure.
  • Pro-3B scores 0.138 English and 0.206 Chinese overall edit distance on OmniDocBench, with table TEDS of 81.5 and 87.5 (author-reported).
  • It runs on an 8GB RTX 4060 with quantized weights, and the 1.2B model is about 36% faster than 3B for about 1.6% lower accuracy.

Key differences

docTRMonkeyOCR
LicenceApache-2.0Code Apache-2.0; v1 weights are research and non-commercial only, commercial use needs a written license
How you run itPython library on PyTorch, with Docker images; GPU images need CUDA 12.2 or newer on the hostSelf-hosted via LMDeploy or Docker; 20/30/40-series and V100 need a patched Docker image to avoid a shared-memory error
Output formatsJSON, plain text, bounding boxesMarkdown, JSON, LaTeX, HTML, bounding boxes
Tables and formulasNo table, formula or Markdown output; words and lines onlyTable TEDS 81.5 EN / 87.5 ZH on OmniDocBench (pro-3B, author-reported)
BenchmarkNot publishedOmniDocBench overall edit distance 0.138 EN / 0.206 ZH (pro-3B, lower is better, author-reported)
Hardware and speedCPU or NVIDIA GPU; speed Not publishedTested on RTX 3090/4090, A6000, H800, A100; pro-3B runs about 0.49 pages/s on a 3090
Known failuresSplit-crop merging misjoins readings across repeated characters (issue #2229); cropped images give poorer results (issue #2007); ONNX export of MASTER truncates decoding steps (issue #2224)Photographed text, handwriting, Traditional Chinese and multilingual text are not fully supported

Sources

What each one is

docTR

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

docTR details

MonkeyOCR

Open-source document parser that splits work into structure, recognition and relation steps.

MonkeyOCR 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": ["monkeyocr/monkeyocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

docTR alternativesMonkeyOCR alternativesBest OCR models in 2026