Hunyuan OCR vs OpenOCR
Pick OpenOCR for Chinese and English academic PDFs with formulas when you want an Apache-2.0 licence and a 0.1B model. Pick Hunyuan OCR for photo and scene text, image translation, and low-resource or historical scripts, as long as you are outside the EU, UK and South Korea. The main split is scope: Hunyuan OCR is a ~1B all-in-one model with many output formats, while OpenOCR is a small toolkit limited to two languages.
Hunyuan OCRtencent/hunyuan-ocr | OpenOCRfudan/openocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 1.5 s / page | 0.5 s / page |
| Best for | Chinese documents and photos | Lightweight OCR pipeline on CPU |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | Chinese and English |
| 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 | ✓ Yes | No |
| 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 Hunyuan OCR if
- One ~1B model covers document parsing, text spotting, information extraction and image translation.
- It supports low-resource and ancient-script OCR, which OpenOCR does not, since OpenDoc and UniRec handle only Chinese and English.
- It outputs Markdown, HTML, LaTeX, JSON, plain text and bounding boxes, and v1.5 accepts images up to 4K with a 128K context window.
Choose OpenOCR if
- It uses the Apache-2.0 licence, with no region exclusions and no MAU cap.
- OpenDoc-0.1B reports 90.57 on OmniDocBench v1.5 at only 0.1B parameters, though the authors self-report this score.
- UniRec-0.1B reads plain text and single or multi-line formulas in one model, and the toolkit supports ONNX export.
Key differences
| Hunyuan OCR | OpenOCR | |
|---|---|---|
| Licence | Tencent Hunyuan Community License. Excludes EU, UK and South Korea. Separate licence needed above 100M monthly active users. | Apache-2.0 |
| Model size | ~1B parameters | 0.1B (OpenDoc-0.1B and UniRec-0.1B) |
| How you run it | Self-host via vLLM, Transformers or llama.cpp. CUDA 13 recommended for the unified vLLM environment. llama.cpp GGUF path for CPU, consumer GPU or laptop. | Self-host as a Python library, with ONNX export. Hardware requirements not published. |
| Languages | Includes low-resource and ancient-script OCR. | Chinese and English only for OpenDoc and UniRec. |
| Output formats | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes | Plain text, LaTeX, bounding boxes |
| Benchmark | ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5), independent | OmniDocBench v1.5 overall 90.57 (OpenDoc-0.1B), self-reported by the authors. Different benchmark, so scores are not comparable. |
| Known limits | Archived 1.0 note said Transformers and vLLM outputs differed in accuracy. Unified environment needs vLLM 0.25.1+. | Document parsing depends on a separate layout model, PP-DocLayoutV2 from PaddlePaddle. No independent replication of benchmarks found. |
Sources
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsOpenOCR
Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.
OpenOCR detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "tencent/hunyuan-ocr","fallbacks": ["fudan/openocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Hunyuan OCR alternativesOpenOCR alternativesBest OCR models in 2026