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-ocr | RapidOCRrapidai/rapidocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 0.6 s / page |
| Best for | Chinese documents | Lightweight OCR on CPU or edge |
| Inputs | PDF, images | images |
| Languages | Chinese, English and more | Chinese, English and more |
| Max pages per request | 200 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | No |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | ✓ Yes |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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 OCR | RapidOCR | |
|---|---|---|
| Licence | Apache-2.0, commercial use allowed | Apache-2.0; converted models keep their upstream licences |
| How you run it | 4B model, benchmarked on one NVIDIA A100 with vLLM; also hosted on the Baidu Qianfan platform | Local library in Python, C++, Java or C#; CPU by default, optional GPU, TensorRT, OpenVINO or MNN engines |
| Output formats | Markdown, JSON, HTML, LaTeX, bounding boxes | Plain text and bounding boxes |
| Languages | 192 languages, plus handwriting and scene text | Chinese and English by default; other languages need extra models |
| Benchmarks | OmniDocBench v1.5 93.12, olmOCR-Bench 79.8, OCRBench 880 (reported by the authors) | Not published |
| Speed and latency | 1.024 pages per second on an A100 even with W8A8; thinking mode can emit up to 16,384 tokens | Not published |
| Known failure | Not suited to CPU-only deployment | 16-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 detailsRapidOCR
PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.
RapidOCR detailsTry both on your own file
Run the file once with each model and compare the output.
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