Typhoon OCR vs Unstructured
Pick Typhoon OCR for Thai and English documents such as government forms, financial reports and books, where it is built to read the page itself. Pick Unstructured for ingesting many file types (PDF, HTML, Word, PowerPoint, email, images) into a RAG pipeline. The main split is scope: Typhoon OCR is a 2B-parameter OCR model for two languages, while Unstructured is a document ETL tool that partitions many formats into typed elements.
Typhoon OCRtyphoon/typhoon-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 | 1.8 s / page | 3.0 s / page |
| Best for | Thai documents | Mixed file types into RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | Thai, English | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | ✓ 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 Typhoon OCR if
- Its V1.5 model beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870), and V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model.
- It outputs tables as HTML with merged cells, equations as LaTeX, and marks checkboxes, and V2 2B scores 84.7 on olmOCR-bench.
- The Apache-2.0 weights are free to self-host (subject to OpenTyphoon Terms and Conditions), or you can call typhoon-ocr-v2 on the Typhoon API.
Choose Unstructured if
- It reads PDFs, HTML, Word, PowerPoint, emails and images in one library, with many connectors.
- The hosted platform gives the first 10,000 pages free, then $0.015 per page, and the open-source library is free under Apache-2.0.
- Its Auto, Fast, High-Res and VLM strategies let you trade speed for quality, and the fast strategy suits born-digital PDFs.
Key differences
| Typhoon OCR | Unstructured | |
|---|---|---|
| What it is | Open Thai and English document OCR model, 2B parameters (0.8B V2 variant also exists) | Document ETL library and hosted platform that partitions files into typed elements |
| Licence | Apache-2.0, subject to OpenTyphoon Terms and Conditions | Apache-2.0 for the open-source library; proprietary for the hosted platform |
| How you run it | Self-host the weights, or use the Typhoon API as typhoon-ocr-v2 | Self-host the Python library, or use the hosted API |
| Price | Free self-hosted (you pay for compute). API pricing not published on the model card | Hosted: first 10,000 pages free, then $0.015 per page; Business is custom. Open-source library is free |
| Output formats | Markdown, HTML, LaTeX | JSON, HTML, plain text, bounding boxes |
| Languages | Only Thai and English evaluated | Table OCR ignores language settings (GitHub issue #1694), so non-English tables are a weak spot |
| Known failure | V2 can loop until the token limit, mostly on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBench | Open-source table cell content scores 0.426 versus 0.866 hosted; hi_res tables can cut off at the edges and drop first letters (issue #3262) |
Sources
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
- Unstructured pricing
- Unstructured GitHub README
- Unstructured issue #3262
- Unstructured issue #1694
What each one is
Typhoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon 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": "typhoon/typhoon-ocr","fallbacks": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Typhoon OCR alternativesUnstructured alternativesBest OCR models in 2026