OCRRouter

GOT-OCR 2.0 vs RolmOCR

Pick GOT-OCR 2.0 for formulas, sheet music, chemical structures and region-specific OCR on English and Chinese documents, where you need LaTeX, Markdown or other structured output. Pick RolmOCR for plain text transcription of scanned pages, especially rotated or skewed ones, under an Apache-2.0 licence for the weights. The main split is output type: GOT-OCR 2.0 reads many content types, while RolmOCR only returns plain text.

GOT-OCR 2.0stepfun/got-ocr-2RolmOCRreducto/rolmocr
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forFormatted text, formulas and chartsFast open PDF to text
InputsimagesPDF, images
LanguagesChinese, EnglishNot stated by the authors
Max pages per request100500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
MultilingualNoNo
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 GOT-OCR 2.0 if

  • You need formulas, sheet music or chemical structures, with output as LaTeX, TikZ, SMILES or kern.
  • You want to OCR one region of a page, guided by box coordinates or color.
  • You have limited GPU memory: it has 580M parameters, and a llama.cpp port exists for CPU users.

Choose RolmOCR if

  • You are transcribing scanned pages to plain text, including rotated or skewed ones, since about 15% of its training data was rotated.
  • You need Apache-2.0 weights that are usable commercially, with no non-commercial data licence attached.
  • You have an independent benchmark to check against: Needl.ai scored it 0.663 overall and counted 7 hallucination issues versus 11 for olmocr-2-7b.

Key differences

GOT-OCR 2.0RolmOCR
Model size and base580M parameters, unified end-to-end OCR model from StepFun and UCAS8B (Qwen2.5-VL-7B base), fine-tuned by Reducto on olmOCR-mix-0225
LicenceCode Apache-2.0; training data CC BY-NC 4.0Apache-2.0
How you run itSelf-hosted. Needs CUDA 11.8 and PyTorch 2.0.1 per the README; available in Hugging Face Transformers; llama.cpp port for CPUSelf-hosted, for example with vLLM; suited to one GPU
Output formatsPlain text, Markdown, LaTeX, TikZ, SMILES, kernPlain text only
Layout and regionsRegion OCR by box coordinates or color; multi-page OCRCannot output layout bounding boxes
BenchmarkNot published (README lists no benchmark scores)0.663 overall on Needl.ai (independent), versus 0.770 for olmocr-2-7b
Known failureOutput can loop characters midway (issue #226); returns wrong text on blank images (issue #235); format mode is much worse than plain mode (issue #317)Can hallucinate or drop content; omitted a table subtitle that olmOCR extracted; quantized versions not evaluated

Sources

What each one is

GOT-OCR 2.0

Unified OCR model that reads plain text, tables, formulas, sheet music and charts.

GOT-OCR 2.0 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": "stepfun/got-ocr-2","fallbacks": ["reducto/rolmocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GOT-OCR 2.0 alternativesRolmOCR alternativesBest OCR models in 2026