OCRRouter

Typhoon OCR vs RolmOCR

Pick Typhoon OCR for Thai and English documents such as government forms, financial reports and books, where you need tables as HTML and equations as LaTeX. Pick RolmOCR for plain text transcription of rotated or skewed scans in English-style pipelines on one GPU. The main split is output: Typhoon OCR returns structured Markdown, HTML and LaTeX, while RolmOCR returns plain text only.

Typhoon OCRtyphoon/typhoon-ocrRolmOCRreducto/rolmocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.8 s / page3.0 s / page
Best forThai documentsFast open PDF to text
InputsPDF, imagesPDF, images
LanguagesThai, EnglishNot stated by the authors
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
MathNoNo
Bounding boxesNoNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 Typhoon OCR if

  • It is tuned for Thai: V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model, and V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870).
  • It outputs Markdown, HTML and LaTeX, with tables as HTML including merged cells, equations as LaTeX and checkboxes marked.
  • It is small at 2B parameters yet scores 84.7 on olmOCR-bench, and it can be self-hosted or called through the Typhoon API as typhoon-ocr-v2.

Choose RolmOCR if

  • It is built for rotated and skewed scans, since about 15% of its training data was rotated to handle off-angle pages.
  • It is a straightforward self-hosted plain text transcriber under Apache-2.0, served for example with vLLM on one GPU.
  • Reducto reports faster inference and lower memory use than the original olmOCR, and Needl.ai counted 7 hallucination issues versus 11 for olmocr-2-7b.

Key differences

Typhoon OCRRolmOCR
LicenceApache-2.0, subject to OpenTyphoon Terms and ConditionsApache-2.0, usable commercially
How you run itSelf-host the weights or use the Typhoon API (typhoon-ocr-v2)Self-host only, for example with vLLM
Size2B (V2 and V1.5); 0.8B V2 variant8B (Qwen2.5-VL-7B base)
Output formatsMarkdown, HTML and LaTeX; tables as HTML with merged cellsPlain text only; no layout bounding boxes
BenchmarksolmOCR-bench 84.7, OmniDocBench v1.6 90.97, ThaiOCRBench 59.9 (V2 2B, reported by the authors)Needl.ai PDF extraction overall 0.663, versus 0.770 for olmocr-2-7b (independent)
LanguagesThai and English only evaluatedNot published
Known failureV2 can loop until the token limit, mostly on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBenchCan hallucinate or drop content, such as a table subtitle that olmOCR extracted; quantized versions not evaluated

Sources

What each one is

Typhoon OCR

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

Typhoon OCR details

RolmOCR

Reducto's open PDF-to-text model, built on Qwen2.5-VL-7B with the olmOCR recipe. Needs no PDF metadata and handles rotated pages.

RolmOCR 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": "typhoon/typhoon-ocr","fallbacks": ["reducto/rolmocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Typhoon OCR alternativesRolmOCR alternativesBest OCR models in 2026