Hunyuan OCR vs GOT-OCR 2.0
Pick Hunyuan OCR for photo and scene text spotting, image translation, and low-resource or historical scripts, and only if you are outside the EU, UK and South Korea. Pick GOT-OCR 2.0 for formulas, sheet music, chemical structures and region-guided OCR on English and Chinese documents. The main split is scope and licence: Hunyuan OCR is a ~1B model with a regional licence, and GOT-OCR 2.0 is a 580M model with Apache-2.0 code.
Hunyuan OCRtencent/hunyuan-ocr | GOT-OCR 2.0stepfun/got-ocr-2 | |
|---|---|---|
| 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 | 1.5 s / page |
| Best for | Chinese documents and photos | Formatted text, formulas and charts |
| Inputs | PDF, images | images |
| Languages | 100+ languages | Chinese, English |
| Max pages per request | 500 | 100 |
| 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 handles document parsing, text spotting, information extraction and image translation.
- It takes images up to 4K and a 128K context window in v1.5, and covers low-resource and ancient-script OCR.
- It runs on a laptop through the llama.cpp GGUF path, and it has a public ParseBench-2 overall score of 67.11.
Choose GOT-OCR 2.0 if
- It reads formulas, tables, charts, sheet music and geometry, and outputs LaTeX, TikZ, SMILES and kern.
- Region OCR can be guided by box coordinates or color, and it supports multi-page OCR and dynamic resolution.
- The code is Apache-2.0 with no regional exclusions, and it is in Hugging Face Transformers with batched inference.
Key differences
| Hunyuan OCR | GOT-OCR 2.0 | |
|---|---|---|
| Size | ~1B parameters | 580M parameters |
| Licence | Tencent Hunyuan Community License. Excludes the EU, UK and South Korea. A separate license is needed above 100M monthly active users. | Code Apache-2.0. Training data CC BY-NC 4.0. |
| How you run it | Self-hosted via vLLM, Transformers or llama.cpp. CUDA 13 recommended for the unified vLLM environment. | Self-hosted via Hugging Face Transformers. README lists CUDA 11.8 and PyTorch 2.0.1. CPU users are pointed to a llama.cpp port. |
| Output formats | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes | Plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Benchmarks | ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5, independent) | Not published |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute) |
| Known failure | A 1.0 note said Transformers and vLLM outputs differed in accuracy. ParseBench-2 text score is 62.88 in public CI replay. | Issues report looping characters mid-recognition, wrong text instead of an empty string on images with no text, and much worse results in format mode than in plain OCR mode. |
Sources
- HunyuanOCR GitHub
- HunyuanOCR model card
- Hunyuan Community License
- GOT-OCR2.0 GitHub
- GOT-OCR 2.0 paper
- GitHub issue index
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsGOT-OCR 2.0
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
GOT-OCR 2.0 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": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Hunyuan OCR alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026