OCRRouter

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-ocrTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page1.8 s / page
Best forBooks and very long documentsThai documents
InputsPDF, imagesPDF, images
Languages30+ languagesThai, English
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 OCRTyphoon OCR
Language focusNot publishedThai and English only; no other language was evaluated
LicenceMITApache-2.0, subject to OpenTyphoon Terms and Conditions
Model size3B total, about 500M active per token; Unlimited OCR 2 is 3.34B2B (V2 and V1.5); 0.8B V2 variant
How you run itSelf-host with vLLM, SGLang or transformers on an NVIDIA GPU (CUDA 12.9 or 13.0); also hosted in Baidu CloudSelf-host the weights, or use the Typhoon API as typhoon-ocr-v2; API pricing not listed
Output formatsMarkdown, plain text, bounding boxesMarkdown, HTML, LaTeX
Multi-page input40+ pages in one pass; context capped at 32,768 tokens; multi-page works only in base modeNot published
Known failureText repetition and looping (issue #55), hallucinated text (issue #58), bold and italic mostly lostV2 can loop until the token limit on dense multi-column pages; key-information extraction scores only 21.0 on ThaiOCRBench

Sources

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 details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

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