OCRRouter

RapidOCR vs Pixtral

Pick RapidOCR for offline CPU text extraction from Chinese and English screenshots and receipts, especially inside Java or C# apps. Pick Pixtral only if you already run on the Mistral API and need question answering over charts and documents, since the model is deprecated and not suited to verbatim transcription.

RapidOCRrapidai/rapidocrPixtralmistral/pixtral
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed0.6 s / page3.0 s / page
Best forLightweight OCR on CPU or edgeQuestions about document images
Inputsimagesimages
LanguagesChinese, English and moreMultilingual
Max pages per request100500
TablesNoNo
HandwritingNoNo
MathNoNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
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 RapidOCR if

  • It runs fully offline on CPU through ONNX Runtime, installed with pip install rapidocr onnxruntime.
  • It has bindings for Python, C++, Java and C#, so it embeds in many stacks.
  • It returns plain text with bounding boxes, which suits screenshots and receipts in Chinese and English.

Choose Pixtral if

  • It scores 90.7 ANLS on DocVQA per Mistral, which fits question answering over documents.
  • It outputs plain text, Markdown or JSON, and a 128K token context allows many images per request.
  • It is available on the Mistral API at a launch price of $0.15 per million input and output tokens, so existing Mistral integrations can keep using it.

Key differences

RapidOCRPixtral
What it isOCR toolkit that runs PaddleOCR models through ONNX and other runtimes12.4B general vision language model (12B decoder plus 400M vision encoder)
How you run itLocal library from Python, C++, Java or C#Mistral API as pixtral-12b-2409, or open weights you host yourself
LicenceApache-2.0; converted models keep their upstream licencesApache-2.0
PriceFree, self-hosted; you pay for compute$0.15 per million input and output tokens at API launch; free to self-host
Output formatsPlain text and bounding boxes; no layout, tables or MarkdownPlain text, Markdown and JSON
Languages and scriptsChinese and English by default; other languages need extra models, and Arabic crashes without manual setup (issue #719)Reported accuracy drop on non-Latin scripts, handwriting and small fonts
Known failure16-bit grayscale PNG or TIFF give no text or wrong text (issue #776); sliced inference crashes on large pages (issue #764)Mistral marks it deprecated and no longer maintained; a launch thread user said it does not always get OCR near correct; Q4 quantization degrades small text OCR

Sources

What each one is

RapidOCR

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

RapidOCR details

Pixtral

Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.

Pixtral 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": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

RapidOCR alternativesPixtral alternativesBest OCR models in 2026