OCRRouter

MonkeyOCR vs InternVL3.5

Pick MonkeyOCR for English and Simplified Chinese PDFs such as academic papers with formulas and tables, where you want layout-aware output with block coordinates. Pick InternVL3.5 for commercial or SaaS use, or when you want a general vision language model at many sizes under Apache-2.0. The main split is the licence: MonkeyOCR v1 weights need a written licence for commercial use, InternVL3.5 does not.

MonkeyOCRmonkeyocr/monkeyocrInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forChinese and English PDFsSelf-hosted document understanding
InputsPDF, imagesimages
LanguagesChinese, EnglishMultilingual
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
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 MonkeyOCR if

  • Pro-3B reports the best overall OmniDocBench edit distance among compared models, 0.138 in English and 0.206 in Chinese, and table TEDS of 81.5 in English and 87.5 in Chinese.
  • It outputs Markdown, JSON, LaTeX, HTML and bounding boxes, so you get block coordinates for layout work.
  • It runs on an 8GB RTX 4060 with quantized weights, and pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy.

Choose InternVL3.5 if

  • Apache-2.0 licence, so you can use it commercially without asking the authors for a separate licence.
  • Nine sizes from 1B to 241B let you trade accuracy for cost, and the 20B-A4B and 30B-A3B MoE variants activate few parameters per token.
  • As a general vision language model it suits document question answering and self-hosted multimodal pipelines, and models up to 30B fit on a single A100.

Key differences

MonkeyOCRInternVL3.5
LicenceCode Apache-2.0; v1 weights research and non-commercial only, commercial use needs a written licenceApache-2.0
Model type and sizesDocument parsing model, 3B and 1.2BGeneral vision language model, 1B to 241B-A28B
Output formatsMarkdown, JSON, LaTeX, HTML, bounding boxesPlain text, Markdown, JSON; no bounding boxes or layout output by default
Published OCR benchmarkOmniDocBench pro-3B edit distance 0.138 EN / 0.206 ZH; table TEDS 81.5 EN / 87.5 ZH (reported by the authors)Not published as text values; the model card shows OCR scores only as chart images
HardwareTested on RTX 3090/4090, A6000, H800, A100; RTX 4060 8GB works with quantized modelsUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100s
SpeedPro-3B about 0.49 pages/s on a 3090Not published
Known failureNot fully supported: photographed text, handwriting, Traditional Chinese and multilingual textNot suited to jobs needing word coordinates or CPU-only deployment of larger sizes

Sources

What each one is

MonkeyOCR

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

MonkeyOCR details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": "monkeyocr/monkeyocr","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MonkeyOCR alternativesInternVL3.5 alternativesBest OCR models in 2026