Hunyuan OCR vs Unstructured
Pick Unstructured if you ingest mixed files (PDF, Word, PowerPoint, email, HTML) into a RAG pipeline and want a hosted API or an Apache-2.0 library. Pick Hunyuan OCR if you need a self-hosted ~1B model for photo and scene text, image translation, or low-resource and historical scripts, and you are outside the EU, UK and South Korea. The main split is scope: Hunyuan OCR reads images, Unstructured routes many file types into typed elements.
Hunyuan OCRtencent/hunyuan-ocr | Unstructuredunstructured/unstructured | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 20 credits / page |
| Per 1,000 pages | $2.00 | $20.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Chinese documents and photos | Mixed file types into RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ 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 Hunyuan OCR if
- It is one ~1B model that covers document parsing, text spotting, information extraction and image translation.
- It supports low-resource and ancient-script OCR, among 12 task types exposed through the vLLM client.
- It can run on a laptop, consumer GPU or CPU through the llama.cpp GGUF path, and it costs nothing beyond your own compute.
Choose Unstructured if
- It handles PDFs, HTML, Word, PowerPoint, emails and images in one library, with many connectors.
- The library is Apache-2.0, and the hosted platform gives you the first 10,000 pages free, then $0.015 per page.
- Its Auto, Fast, High-Res and VLM strategies let you trade speed for quality, and Fast suits born-digital PDFs.
Key differences
| Hunyuan OCR | Unstructured | |
|---|---|---|
| Licence | Tencent Hunyuan Community License; excludes EU, UK and South Korea; separate license above 100M monthly active users | Apache-2.0 for the open-source library; proprietary for the hosted platform |
| How you run it | Self-host only, via vLLM, Transformers or llama.cpp | Self-host the library or call the hosted API |
| Price | Free; you pay for compute | Library free; hosted is free for 10,000 pages, then $0.015 per page; Business is custom |
| Hardware | NVIDIA GPU with CUDA 13 for the unified vLLM setup; GGUF path for CPU or laptop | Not published |
| Output formats | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes | JSON, HTML, plain text, bounding boxes |
| Benchmark | ParseBench-2 overall 67.11; ParseBench mean 63.86 (v1.5) | Table cell content 0.426 open-source vs 0.866 hosted (vendor's own benchmark) |
| Known failure | Archived 1.0 note said Transformers and vLLM outputs differed in accuracy | hi_res tables cut off at edges and drop first letters; table OCR ignores language settings; library sends usage telemetry by default |
Sources
- HunyuanOCR model card
- Hunyuan Community License
- Unstructured pricing
- Unstructured GitHub README
- Issue #3262
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsUnstructured
Document ETL for RAG. Partitions many file types into typed elements; open-source library too.
Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Hunyuan OCR alternativesUnstructured alternativesBest OCR models in 2026