OCRRouter

Unlimited OCR vs MonkeyOCR

Pick Unlimited OCR for long documents such as reports and books, bulk PDF to text for RAG, and any commercial use, since it is MIT licensed and parses 40+ pages in one pass. Pick MonkeyOCR for English and Simplified Chinese papers with formulas and tables, or for research on smaller GPUs, as long as you do not need commercial rights without a separate licence. The main split is licence and scope: Unlimited OCR is free for commercial work and built for long input, while MonkeyOCR v1 weights need a written licence for commercial use.

Unlimited OCRbaidu/unlimited-ocrMonkeyOCRmonkeyocr/monkeyocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page1.5 s / page
Best forBooks and very long documentsChinese and English PDFs
InputsPDF, imagesPDF, images
Languages30+ languagesChinese, English
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 Unlimited OCR if

  • It is MIT licensed, so you can use it commercially with no copyleft.
  • It parses 40+ pages in a single forward pass with roughly constant memory, which suits long reports and books.
  • It also has a hosted option in Baidu Cloud's OCR product, so you can skip running your own GPU.

Choose MonkeyOCR if

  • It reports the best overall OmniDocBench edit distance among compared models in English and Chinese, with pro-3B at 0.138 / 0.206.
  • It runs on an 8GB RTX 4060 with quantized weights, while Unlimited OCR 2 runs out of memory on 12 GB GPUs under SGLang.
  • It outputs JSON, LaTeX and HTML as well as Markdown and bounding boxes, which helps with formulas and tables in academic papers.

Key differences

Unlimited OCRMonkeyOCR
LicenceMIT, commercial use allowedCode Apache-2.0; v1 weights are research and non-commercial only, commercial use needs a written licence
How you run itSelf-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu CloudSelf-host only, via LMDeploy or Docker
Model size3B total, about 500M active per token; Unlimited OCR 2 is 3.34B3B and 1.2B; pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; Unlimited OCR 2 under SGLang runs out of memory on 12 GB GPUsTested on RTX 3090/4090, A6000, H800 and A100; RTX 4060 8GB works with quantized models
Output formatsMarkdown, plain text, bounding boxesMarkdown, JSON, LaTeX, HTML, bounding boxes
BenchmarksParseBench mean 46.17; Unlimited OCR 2 scores 77.1 on MarathonDocBench and 84.6 on MPDocBench, both reported by the authorsOmniDocBench table TEDS 81.5 EN / 87.5 ZH for pro-3B, reported by the authors
Known failureText repetition and looping on some pages, reported hallucinated text, and formatting such as bold and italic is mostly lost; context is capped at 32,768 tokensPhotographed text, handwriting, Traditional Chinese and multilingual text are not fully supported; pro-3B runs at about 0.49 pages/s on a 3090

Sources

What each one is

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR 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": "baidu/unlimited-ocr","fallbacks": ["monkeyocr/monkeyocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesMonkeyOCR alternativesBest OCR models in 2026