Unlimited OCR vs Typhoon OCR
Pick Unlimited OCR for long reports and books that you want parsed in one request, with bounding boxes, on a CUDA GPU. Pick Typhoon OCR for Thai or Thai-English documents such as government forms and financial reports, where it is built to do well. The main split is scope: Unlimited OCR handles 40+ pages per pass but loses bold and italic, while Typhoon OCR is evaluated only on Thai and English.
Unlimited OCRbaidu/unlimited-ocr | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 1.8 s / page |
| Best for | Books and very long documents | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | Thai, English |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| 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 Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
- It returns block types and bounding boxes with the text, which suits layout-aware extraction and bulk PDF to text for RAG.
- It is MIT licensed, which allows commercial use with no copyleft.
Choose Typhoon OCR if
- It is built for Thai and English: V1.5 scored BLEU 0.870 on Thai government forms, ahead of GPT-5 and Gemini 2.5 Pro, 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.
- At 2B parameters it scores 84.7 on olmOCR-bench, and a 0.8B V2 variant exists.
Key differences
| Unlimited OCR | Typhoon OCR | |
|---|---|---|
| Language focus | Not published | Thai and English only; no other language was evaluated |
| Licence | MIT | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| Model size | 3B total, about 500M active per token; Unlimited OCR 2 is 3.34B | 2B (V2 and V1.5); 0.8B V2 variant |
| How you run it | Self-host with vLLM, SGLang or transformers on an NVIDIA GPU (CUDA 12.9 or 13.0); also hosted in Baidu Cloud | Self-host the weights, or use the Typhoon API as typhoon-ocr-v2; API pricing not listed |
| Output formats | Markdown, plain text, bounding boxes | Markdown, HTML, LaTeX |
| Multi-page input | 40+ pages in one pass; context capped at 32,768 tokens; multi-page works only in base mode | Not published |
| Known failure | Text repetition and looping (issue #55), hallucinated text (issue #58), bold and italic mostly lost | V2 can loop until the token limit on dense multi-column pages; key-information extraction scores only 21.0 on ThaiOCRBench |
Sources
- Hugging Face model card
- GitHub repo
- Issue #55 repetition
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon OCR 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": "baidu/unlimited-ocr","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesTyphoon OCR alternativesBest OCR models in 2026