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/docling | Hunyuan OCRtencent/hunyuan-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.2 s / page | 1.5 s / page |
| Best for | Structured export for RAG | Chinese documents and photos |
| Inputs | PDF, images, DOCX | PDF, images |
| Languages | Latin scripts, CJK | 100+ languages |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
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
| Docling | Hunyuan OCR | |
|---|---|---|
| What it is | Python library that converts documents into a structured DoclingDocument and plugs in OCR engines and VLMs | Lightweight end-to-end OCR VLM, about 1B parameters |
| Licence | MIT (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 types | PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRL | Images and documents for parsing, spotting, extraction and translation |
| Output formats | Markdown, HTML, JSON, DocTags, plain text | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes |
| Hardware | CPU works; GPU speeds up model stages | NVIDIA GPU with CUDA 13 recommended for the unified vLLM setup; llama.cpp GGUF for CPU, consumer GPU or laptop |
| Benchmark | Not published | ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5, independent) |
| Known failure | Version 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
- Docling GitHub README
- Supported formats
- Issue #5254 OCR regression
- Issue #5132 reading order
- HunyuanOCR model card
- Hunyuan Community License
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsTry 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 vs Qwen-VLDocling vs Nanonets-OCRTesseract vs Hunyuan OCRMinerU vs Hunyuan OCRLlamaParse vs DoclingPaddleOCR-VL vs DoclingMinerU vs DoclingDocling vs Tesseract
Docling alternativesHunyuan OCR alternativesBest OCR models in 2026