OCRRouter

Qianfan OCR vs RapidOCR

Pick Qianfan OCR when you need full document parsing on a GPU: tables, formulas, handwriting, 192 languages and Markdown, JSON, HTML or LaTeX output. Pick RapidOCR when you need fast offline text and box extraction on CPU, mostly for Chinese and English, or want to embed OCR in a Java, C# or C++ app. The main split is a 4B end-to-end parsing model against a lightweight ONNX text recognition toolkit.

Qianfan OCRbaidu/qianfan-ocrRapidOCRrapidai/rapidocr
TypeOCR APIOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page0.6 s / page
Best forChinese documentsLightweight OCR on CPU or edge
InputsPDF, imagesimages
LanguagesChinese, English and moreChinese, English and more
Max pages per request200100
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNo✓ Yes
ConfidenceNo✓ Yes
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 Qianfan OCR if

  • It scores 93.12 on OmniDocBench v1.5, the top end-to-end score in Baidu's table.
  • It covers 192 languages, handwriting and scene text, and is listed as good for tables, formulas and key information extraction.
  • It outputs Markdown, JSON, HTML, LaTeX and bounding boxes, so you get structure and not just text.

Choose RapidOCR if

  • It runs on CPU through ONNX Runtime by default, with pip install rapidocr onnxruntime and no Paddle framework.
  • It has bindings for Python, C++, Java and C#, so it embeds in many stacks.
  • It suits offline OCR of Chinese and English screenshots and receipts in desktop or server apps.

Key differences

Qianfan OCRRapidOCR
LicenceApache-2.0, commercial use allowedApache-2.0; converted models keep their upstream licences
How you run it4B model, benchmarked on one NVIDIA A100 with vLLM; also hosted on the Baidu Qianfan platformLocal library in Python, C++, Java or C#; CPU by default, optional GPU, TensorRT, OpenVINO or MNN engines
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesPlain text and bounding boxes
Languages192 languages, plus handwriting and scene textChinese and English by default; other languages need extra models
BenchmarksOmniDocBench v1.5 93.12, olmOCR-Bench 79.8, OCRBench 880 (reported by the authors)Not published
Speed and latency1.024 pages per second on an A100 even with W8A8; thinking mode can emit up to 16,384 tokensNot published
Known failureNot suited to CPU-only deployment16-bit grayscale PNG or TIFF give no text or wrong text; Arabic recognition crashes; sliced inference crashes on large pages

Sources

What each one is

Qianfan OCR

Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.

Qianfan OCR details

RapidOCR

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

RapidOCR 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/qianfan-ocr","fallbacks": ["rapidai/rapidocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesRapidOCR alternativesBest OCR models in 2026