OCRRouter

dots.ocr vs Hunyuan OCR

Pick dots.ocr for multilingual PDFs, academic and business documents with mixed tables and text, where you want layout boxes, HTML tables and LaTeX formulas from one pass and an MIT-licensed codebase. Pick Hunyuan OCR for photo and scene text, image translation, or low-resource scripts, especially on a laptop or small GPU, as long as you are outside the EU, UK and South Korea. The main split is document parsing focus at 3B versus a ~1B all-purpose model with a restrictive licence.

dots.ocrrednote/dots-ocrHunyuan OCRtencent/hunyuan-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page1.5 s / page
Best forMultilingual document parsingChinese documents and photos
InputsPDF, imagesPDF, images
Languages100+ languages100+ languages
Max pages per request500500
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 dots.ocr if

  • You parse multilingual PDFs into Markdown with layout, and want tables as HTML and formulas as LaTeX from one model.
  • You need an MIT-licensed codebase, with no region exclusions and no monthly-active-user cap.
  • You want chart-to-SVG conversion through the dots.mocr-svg variant, or the dots.mocr (v1.5) score of 83.9 on olmOCR-bench.

Choose Hunyuan OCR if

  • You work with photo and scene text, text-image translation, or low-resource and ancient scripts.
  • You need a ~1B model that runs on a laptop or consumer GPU through llama.cpp GGUF, including on CPU.
  • You want one model for parsing, text spotting, information extraction and translation, with 4K images and a 128K context window in v1.5.

Key differences

dots.ocrHunyuan OCR
LicenceMIT for the repository, plus a separate dots.ocr license agreement fileTencent Hunyuan Community License. Excludes the EU, UK and South Korea. Separate licence needed above 100M monthly active users
Model size3B (1.7B LLM backbone)About 1B
How you run itSelf-hosted with vLLM or Hugging Face Transformers. Single CUDA GPU with vLLM is the documented path. No VRAM figure statedSelf-hosted with vLLM, Transformers or llama.cpp. Unified vLLM environment recommends CUDA 13 and vLLM 0.25.1+. GGUF path for CPU, consumer GPU or laptop
Output formatsJSON, Markdown, HTML, LaTeX, bounding boxes, SVGMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
BenchmarksolmOCR-bench 79.1 (dots.ocr) and 83.9 (dots.mocr / 1.5), both reported by the authorsParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5), independent. Not published on olmOCR-bench
ScopeDocument parsing: layout, text, tables and formulas in one passDocument parsing, text spotting, information extraction and image translation, with 12 task types via the vLLM client
Known failureRuns of ellipses or underscores can make output repeat endlessly. Complex tables and formulas remain difficult. A table above 1000 grid cells raised an error and dropped the page in a Docling issueArchived 1.0 note says Transformers and vLLM outputs differed in accuracy. Text score of 62.88 in the ParseBench-2 public CI replay

Sources

What each one is

dots.ocr

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

dots.ocr details

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan 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": "rednote/dots-ocr","fallbacks": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

dots.ocr alternativesHunyuan OCR alternativesBest OCR models in 2026