RapidOCR vs Granite Docling
Pick RapidOCR to read plain text from Chinese or English screenshots and receipts on CPU, or to embed OCR in a Java or C# app. Pick Granite Docling to convert English PDFs with tables, code and equations into Markdown, HTML or LaTeX inside Docling. The main split is output: RapidOCR returns text and boxes only, while Granite Docling returns document structure.
RapidOCRrapidai/rapidocr | Granite Doclingibm/granite-docling | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 0.6 s / page | 1.5 s / page |
| Best for | Lightweight OCR on CPU or edge | Small-model document conversion |
| Inputs | images | PDF, images |
| Languages | Chinese, English and more | English, experimental CJK and Arabic |
| Max pages per request | 100 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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 RapidOCR if
- It runs offline on CPU through ONNX Runtime and installs with pip install rapidocr onnxruntime, with no Paddle framework needed.
- It has bindings for Python, C++, Java and C#, so it fits desktop and server apps in many stacks.
- It targets Chinese and English text in screenshots and receipts, where you only need plain text and bounding boxes.
Choose Granite Docling if
- It outputs DocTags, Markdown, HTML, LaTeX and bounding boxes, so tables and layout survive conversion.
- The model card reports table structure TEDS of 0.97 on FinTabNet, code F1 of 0.988 and equation F1 of 0.968.
- At 258M parameters and Apache-2.0, it is a low-cost option on CPU or a small GPU, and it works inside Docling pipelines.
Key differences
| RapidOCR | Granite Docling | |
|---|---|---|
| What it is | OCR toolkit that runs PaddleOCR models converted to ONNX and other runtimes | 258M-parameter document conversion VLM from IBM that outputs DocTags |
| Output formats | Plain text and bounding boxes | DocTags, Markdown, HTML, LaTeX and bounding boxes |
| Licence and price | Apache-2.0, free and self-hosted. Converted models keep their upstream licences. | Apache-2.0, free and self-hosted. You pay for compute. |
| How you run it | Library for Python, C++, Java or C#. CPU by default, with optional GPU, TensorRT, OpenVINO and MNN engines. | Self-hosted model, typically inside Docling. Use float32 on GPUs without bfloat16, such as the T4. |
| Languages | Chinese and English by default. Other languages need extra models. | English is primary. Japanese, Arabic and Chinese are experimental. |
| Benchmarks | Not published | Full-page OCR F1 0.84, table TEDS structure 0.97 on FinTabNet, OCRBench 500, all reported by the authors |
| Known failures | 16-bit grayscale PNG or TIFF give no text or wrong text. Sliced inference crashes on large pages. Arabic recognition crashes. | Repetitive loops on page headings and invoices. Possible exclamation-mark-only output on T4 GPUs. A vLLM wte error needs the untied revision. Ollama on CPU may hallucinate from FP16 overflow. |
Sources
- RapidOCR GitHub README
- Issue #776
- Granite-Docling model card
- HF discussion #24 repetition
- Ollama issue #12355
What each one is
RapidOCR
PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.
RapidOCR detailsGranite Docling
Compact IBM vision model that converts pages to DocTags for the Docling pipeline.
Granite Docling 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": "rapidai/rapidocr","fallbacks": ["ibm/granite-docling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
RapidOCR alternativesGranite Docling alternativesBest OCR models in 2026