OCRRouter

Nanonets-OCR vs Hunyuan OCR

Pick Nanonets-OCR for printed business documents where you need signatures, watermarks and checkboxes tagged, or flowcharts turned into Mermaid. Pick Hunyuan OCR for photo and scene text, translation of text in images, or low-resource and historical scripts, and when you want a ~1B model that runs on a laptop. Check the licence first: Hunyuan's does not apply in the EU, UK or South Korea, and Nanonets-OCR2-3B's model card states no licence.

Nanonets-OCRnanonets/nanonets-ocrHunyuan OCRtencent/hunyuan-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.8 s / page1.5 s / page
Best forMarkdown with semantic tagsChinese documents and photos
InputsPDF, imagesPDF, images
LanguagesMultilingual100+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
Forms✓ YesNo
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 Nanonets-OCR if

  • It tags signatures, watermarks and image descriptions, and turns checkboxes into unicode symbols, which suits forms and business documents.
  • It extracts flowcharts and org charts as Mermaid code, and separates inline from display LaTeX equations.
  • The 3B model scores 89.43 on DocVQA and 78.56 on ChartQA per its model card, with Markdown, HTML, LaTeX and Mermaid output.

Choose Hunyuan OCR if

  • One ~1B model covers document parsing, text spotting, information extraction and image translation.
  • It supports images up to 4K and a 128K context window in v1.5, and offers 12 task types including low-resource and ancient-script OCR.
  • It runs on CPU, consumer GPUs or laptops through the llama.cpp GGUF path, and outputs JSON and bounding boxes as well as Markdown, HTML and LaTeX.

Key differences

Nanonets-OCRHunyuan OCR
Size3B (Hugging Face lists ~4B params), fine-tuned from Qwen2.5-VL-3B~1B
LicenceNot stated on the Nanonets-OCR2-3B model card (no licence tag); base model is Qwen2.5-VL-3BTencent Hunyuan Community License. Excludes the EU, UK and South Korea. A separate licence is needed above 100M monthly active users
How you run itSelf-host the weights from Hugging Face. Free, you pay for computeSelf-host via vLLM, Transformers or llama.cpp. Free, you pay for compute. CUDA 13 and vLLM 0.25.1+ for the unified vLLM environment
Output formatsMarkdown, HTML, LaTeX, MermaidMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
BenchmarksolmOCR-bench overall 69.5, DocVQA 89.43, ChartQA 78.56 (all from the authors, OCR2-3B)ParseBench-2 overall 67.11 and ParseBench mean 63.86 (independent, v1.5)
PromptsTrained on a fixed prompt. The team says hallucination with other prompts is expected12 task types exposed through the vLLM client
Known failureNot trained on handwriting and can hallucinate. In a handwriting test it showed generation loops, with CER up to 2100% and 69.1s per image on an L4Transformers and vLLM outputs differed in accuracy in the archived 1.0 note. ParseBench-2 text score is 62.88 in public CI replay

Sources

What each one is

Nanonets-OCR

Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.

Nanonets-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": "nanonets/nanonets-ocr","fallbacks": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Nanonets-OCR alternativesHunyuan OCR alternativesBest OCR models in 2026