OCRRouter

Marker vs Unlimited OCR

Pick Marker for self-hosted PDF to Markdown on books and papers with equations, or when you need to run on CPU or Apple Silicon, as long as your company is under $5M or you buy a license. Pick Unlimited OCR for long reports and books parsed in one request on an NVIDIA GPU, or when you need MIT-licensed commercial use. The main split is licence and hardware: Marker's model weights restrict larger companies and Unlimited OCR needs CUDA.

Markerdatalab/markerUnlimited OCRbaidu/unlimited-ocr
TypeOCR APIOpen source
Price14 credits / page2 credits / page
Per 1,000 pages$14.00$2.00
Typical speed2.5 s / page1.2 s / page
Best forBooks and research papersBooks and very long documents
InputsPDF, images, DOCXPDF, images
Languages90+ languages30+ languages
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ 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 Marker if

  • You have no NVIDIA GPU: Marker runs on CPU or Apple Silicon (MPS), and its fast mode uses about 18 MB of ONNX weights at 23.6 pages per second.
  • You need more output formats: Markdown, HTML, JSON block trees, RAG chunks, LaTeX and images.
  • You work with books and papers with equations, and you want a score you can check against a benchmark: 83.7 on olmOCR-bench in vllm mode (Datalab's own number).

Choose Unlimited OCR if

  • You are a company above $5M and want free commercial use: the licence is MIT, with no copyleft.
  • You parse long reports and books in one request: it handles 40+ pages in a single forward pass with roughly constant memory.
  • You need layout-aware extraction: it returns block types and bounding boxes alongside the text.

Key differences

MarkerUnlimited OCR
LicenceCode Apache-2.0; weights under a modified AI Pubs Open Rail-M license, free for research, personal use and startups under $5MMIT
HardwareGPU, CPU or Apple Silicon (MPS); vllm mode needs an NVIDIA GPUNVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs; not for CPU-only machines
Hosted optionDatalab API with about 5,000 free pages per month, paid plans after thatHosted endpoint in Baidu Cloud's OCR product
Output formatsMarkdown, HTML, JSON, chunks, LaTeX, imagesMarkdown, plain text, bounding boxes
BenchmarkolmOCR-bench 83.7 and OmniParseBench 85.9 in vllm mode, both reported by Datalab; CPU fast mode drops to 66.6 on olmOCR-benchParseBench mean 46.17 (independent); Unlimited OCR 2 scores 84.6 on MPDocBench and 77.1 on MarathonDocBench, reported by Baidu
Long documentsNot published40+ pages in one pass; context capped at 32,768 tokens, and multi-page input only works in base mode
Known failureWeight licence blocks free commercial use above $5MText repetition and looping (issue #55), hallucinated text (issue #58), bbox coordinate loops on GB10 GPUs under SGLang (issue #114), and mostly lost bold and italic styling (ParseBench text formatting 0.97)

Sources

What each one is

Marker

Hosted version of the open-source Marker and Surya models. Strong on books and papers.

Marker details

Unlimited OCR

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

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

Questions

More comparisons

Marker alternativesUnlimited OCR alternativesBest OCR models in 2026