OCRRouter

Docling vs Hunyuan OCR

Pick Docling to ingest born-digital PDFs, Office files and HTML into structured JSON for RAG. Pick Hunyuan OCR when the input is photos, scene text, or low-resource and historical scripts, or when you need image translation, and you are outside the EU, UK and South Korea. Docling is a pipeline library with pluggable OCR; Hunyuan OCR is a single ~1B OCR model.

Doclingibm/doclingHunyuan OCRtencent/hunyuan-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.2 s / page1.5 s / page
Best forStructured export for RAGChinese documents and photos
InputsPDF, images, DOCXPDF, images
LanguagesLatin scripts, CJK100+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 Docling if

  • It reads PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL through one API.
  • Its lossless JSON export keeps layout, reading order and table structure for downstream tools.
  • It is MIT licensed, with no regional exclusions, and runs on CPU on macOS, Linux and Windows.

Choose Hunyuan OCR if

  • One ~1B model handles document parsing, text spotting, information extraction and image translation.
  • It covers 12 task types, including low-resource and ancient-script OCR, and takes images up to 4K.
  • It can run on a laptop through the llama.cpp GGUF path, and it outputs bounding boxes, LaTeX and Markdown.

Key differences

DoclingHunyuan OCR
What it isPython library that converts documents into a structured DoclingDocument and plugs in OCR engines and VLMsLightweight end-to-end OCR VLM, about 1B parameters
LicenceMIT (individual models have their own licences)Tencent Hunyuan Community License. It excludes the EU, UK and South Korea, and needs a separate licence above 100M monthly active users
Input typesPDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRLImages and documents for parsing, spotting, extraction and translation
Output formatsMarkdown, HTML, JSON, DocTags, plain textMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
HardwareCPU works; GPU speeds up model stagesNVIDIA GPU with CUDA 13 recommended for the unified vLLM setup; llama.cpp GGUF for CPU, consumer GPU or laptop
BenchmarkNot publishedParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5, independent)
Known failureVersion 2.143.1 drops words and numbers with full-page Tesseract OCR (issue #5254); reading order can merge neighbouring columns (issue #5132)Archived 1.0 note said Transformers and vLLM outputs differed in accuracy; the unified environment needs CUDA 13 and vLLM 0.25.1+

Sources

What each one is

Docling

IBM's open-source document converter with a structured document model.

Docling 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": "ibm/docling","fallbacks": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Docling alternativesHunyuan OCR alternativesBest OCR models in 2026