OCRRouter

dots.ocr vs OCR.space

Pick dots.ocr if you can run a CUDA GPU and want layout, tables and formulas out of PDFs in one pass under an MIT licence. Pick OCR.space if you want a hosted API with a free tier of 25,000 requests a month for quick prototypes or searchable PDFs. The main split is self-hosted layout parsing versus a hosted, rate-limited API.

dots.ocrrednote/dots-ocrOCR.spaceocrspace/ocr-space
TypeOpen sourceOCR API
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.5 s / page1.5 s / page
Best forMultilingual document parsingCheap simple OCR
InputsPDF, imagesPDF, images
Languages100+ languages20+ languages
Max pages per request500100
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
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 dots.ocr if

  • You need Markdown, JSON, HTML tables and LaTeX formulas with layout boxes from academic or business PDFs in a single model call.
  • You want MIT-licensed code you can run yourself, with no per-request fees and no file size or page caps from a vendor.
  • You need chart or diagram conversion to SVG, which the dots.mocr-svg variant offers.

Choose OCR.space if

  • You have no GPU and want to call a hosted API, with a free tier of 25,000 requests a month for hobby projects and prototypes.
  • You need to turn scanned PDFs into searchable PDFs, or want per-word overlay coordinates.
  • You need Engine 3 for 200+ languages, handwriting and checkboxes, with a paid PRO plan that has a 100% uptime or money back SLA.

Key differences

dots.ocrOCR.space
How you run itSelf-hosted with vLLM or Hugging Face Transformers. A single CUDA GPU with vLLM is the documented path.Hosted API. An on-premise version is sold separately.
LicenceMIT, with a separate dots.ocr licence agreement file in the repository.Proprietary.
PriceFree, you pay for compute.Free: 25,000 requests/month. PRO $30/month for 300,000 requests. PRO PDF $60/month. Enterprise from $999/month.
Size limitsNo vendor limits stated. Very large tables can fail: a table above 1000 grid cells raised an error and dropped the page in Docling.Free tier: 1 MB files and 3 PDF pages. PRO: 5 MB. PRO PDF: 100 MB+, 999+ pages.
Output formatsJSON, Markdown, HTML, LaTeX, bounding boxes, SVG.JSON, plain text, bounding boxes, searchable PDF, Markdown.
BenchmarksolmOCR-bench 79.1 for dots.ocr and 83.9 for dots.mocr, as reported by the authors.Not published
Known failure modesRuns of ellipses or underscores can make output repeat endlessly. Complex tables and formulas remain difficult.Free searchable PDFs carry a watermark. Engine 3 is slower on large files with less precise coordinates. Engine 2 does not support Greek.

Sources

What each one is

dots.ocr

Single vision model from rednote that does layout detection and content recognition together.

dots.ocr details

OCR.space

Low-cost OCR API with a large free tier. Returns text, word boxes and searchable PDFs.

OCR.space 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": "rednote/dots-ocr","fallbacks": ["ocrspace/ocr-space"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

dots.ocr alternativesOCR.space alternativesBest OCR models in 2026