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/doctr | MonkeyOCRmonkeyocr/monkeyocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 0.9 s / page | 1.5 s / page |
| Best for | Word-level OCR with positions | Chinese and English PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | Mainly Latin scripts | Chinese, English |
| Max pages per request | 500 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | No | No |
| On OCRRouter | Available | Available |
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
| docTR | MonkeyOCR | |
|---|---|---|
| Licence | Apache-2.0 | Code Apache-2.0; v1 weights are research and non-commercial only, commercial use needs a written license |
| How you run it | Python library on PyTorch, with Docker images; GPU images need CUDA 12.2 or newer on the host | Self-hosted via LMDeploy or Docker; 20/30/40-series and V100 need a patched Docker image to avoid a shared-memory error |
| Output formats | JSON, plain text, bounding boxes | Markdown, JSON, LaTeX, HTML, bounding boxes |
| Tables and formulas | No table, formula or Markdown output; words and lines only | Table TEDS 81.5 EN / 87.5 ZH on OmniDocBench (pro-3B, author-reported) |
| Benchmark | Not published | OmniDocBench overall edit distance 0.138 EN / 0.206 ZH (pro-3B, lower is better, author-reported) |
| Hardware and speed | CPU or NVIDIA GPU; speed Not published | Tested on RTX 3090/4090, A6000, H800, A100; pro-3B runs about 0.49 pages/s on a 3090 |
| Known failures | Split-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 detailsMonkeyOCR
Open-source document parser that splits work into structure, recognition and relation steps.
MonkeyOCR detailsTry both on your own file
Run the file once with each model and compare the output.
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