OCRRouter

RapidOCR vs Donut

Pick RapidOCR when you need plain text and bounding boxes from Chinese or English images on a CPU, with no training step. Pick Donut when you have a narrow, fixed-layout document type such as receipts or forms and can fine-tune a model to output JSON. The main split is that RapidOCR works out of the box as a text reader, while Donut is a base model that does nothing useful until you train it.

RapidOCRrapidai/rapidocrDonutnaver/donut
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed0.6 s / page1.0 s / page
Best forLightweight OCR on CPU or edgeReceipt and form fields after fine-tuning
Inputsimagesimages
LanguagesChinese, English and moreEnglish, Chinese, Japanese, Korean
Max pages per request100100
TablesNoNo
HandwritingNoNo
MathNoNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
FormsNo✓ Yes
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 RapidOCR if

  • It runs offline on CPU through ONNX Runtime after pip install rapidocr onnxruntime, with no Paddle framework and no fine-tuning.
  • It has bindings for Python, C++, Java and C#, so you can embed it in desktop or server apps in those stacks.
  • It fits Chinese and English screenshots and receipts, and it is an OCR backend option in Docling.

Choose Donut if

  • It maps a document image straight to JSON with no separate OCR step, which suits receipt and form field extraction.
  • It is MIT licensed and available in Hugging Face Transformers, so you can fine-tune it on your own document types.
  • One HN practitioner reports that about 200 fine-tuning documents can reach human-level accuracy on narrow data.

Key differences

RapidOCRDonut
What it isToolkit that converts PaddleOCR models to ONNX and other runtimes for offline inferenceOCR-free document understanding transformer (Swin encoder, BART decoder) from NAVER Clova, ECCV 2022
Out-of-the-box useWorks after install; reads text and returns boxesBase checkpoint is pretrain-only and must be fine-tuned before use
OutputPlain text and bounding boxesJSON and plain text
LicenceApache-2.0; converted models keep their upstream licencesMIT
Hardware and runtimeCPU via ONNX Runtime by default; optional GPU, TensorRT, OpenVINO, MNN, Paddle or PyTorch enginesSelf-hosted; Transformers v5 dropped image-to-text pipeline support, so load the model directly or use v4
LanguagesChinese and English by default; other languages need extra modelsNot published
Known failure16-bit grayscale PNG or TIFF give no text or wrong text (issue #776); Arabic crashes because python-bidi is undeclared (issue #719)Misses tiny text in large images because of input resolution limits; one HN user found results on personal documents did not match the promised scores

Sources

What each one is

RapidOCR

PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.

RapidOCR details

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut 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": "rapidai/rapidocr","fallbacks": ["naver/donut"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

RapidOCR alternativesDonut alternativesBest OCR models in 2026