OCRRouter

dots.ocr vs DeepSeek-VL2

Pick dots.ocr to turn multilingual PDFs into structured output: it returns layout boxes, Markdown, HTML tables and LaTeX formulas from a 3B model on a single GPU. Pick DeepSeek-VL2 to answer questions about single pages and charts, where it scores 93.3 on DocVQA. The main split is full-document parsing versus document question answering.

dots.ocrrednote/dots-ocrDeepSeek-VL2deepseek/deepseek-vl2
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 forMultilingual document parsingCharts and tables
InputsPDF, imagesimages
Languages100+ languagesMainly English and Chinese
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
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 dots.ocr if

  • You need layout-aware parsing: one pass returns boxes, categories and text, with tables as HTML and formulas as LaTeX.
  • You want a small model: 3B parameters, with a documented path on a single CUDA GPU using vLLM.
  • You want structured outputs beyond text: JSON, Markdown, HTML, LaTeX, bounding boxes and SVG for charts through the dots.mocr-svg variant.

Choose DeepSeek-VL2 if

  • You ask questions about a single page or a chart: DocVQA is 93.3 and ChartQA is 86.0 per the paper.
  • You want a size choice: Tiny (1.0B active) runs under 40GB, and Small scores 834 on OCRBench.
  • You need commercial use of weights under the DeepSeek Model License, with MIT-licensed code.

Key differences

dots.ocrDeepSeek-VL2
Main jobDocument parsing with layout, tables and formulasDocument and chart question answering, single page understanding
Size3B (1.7B LLM backbone)Tiny 3.37B total (1.0B active), Small 16.1B, full 27.5B total (4.5B active)
HardwareSingle CUDA GPU with vLLM is the documented path. No VRAM figure stated.Small may need 80GB GPU memory, or 40GB with incremental prefilling. Tiny runs under 40GB.
Output formatsJSON, Markdown, HTML, LaTeX, bounding boxes, SVGPlain text, Markdown
LicenceMIT, plus a separate dots.ocr license agreement file in the repositoryMIT for code, DeepSeek Model License for weights (commercial use allowed)
BenchmarksolmOCR-bench 79.1 (83.9 for dots.mocr); DocVQA 91.85 and OCRBench 82.16 for dots.mocr, per the authorsDocVQA 93.3 (full model), OCRBench 834 (Small), ChartQA 86.0, per the authors
Known failureRuns of ellipses or underscores can make output repeat endlessly. Complex tables and formulas stay difficult. A table above 1000 grid cells drops the whole page in Docling.Only a few images per session, and dynamic tiling turns off above two images. Struggles with blurry images.

Sources

What each one is

dots.ocr

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

dots.ocr details

DeepSeek-VL2

DeepSeek's mixture-of-experts vision models (December 2024) with OCR and table and chart understanding.

DeepSeek-VL2 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": ["deepseek/deepseek-vl2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

dots.ocr alternativesDeepSeek-VL2 alternativesBest OCR models in 2026