RapidOCR vs Hunyuan OCR
Pick RapidOCR for offline CPU text extraction from Chinese and English screenshots and receipts, or when you need to embed OCR in a Java or C# app. Pick Hunyuan OCR when you need structured output such as Markdown, HTML, LaTeX or JSON, or tasks like scene text spotting and image translation, and you can run a GPU or the llama.cpp GGUF path. The main split is that RapidOCR returns text and boxes only, while Hunyuan OCR is a ~1B VLM that parses documents.
RapidOCRrapidai/rapidocr | Hunyuan OCRtencent/hunyuan-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 0.6 s / page | 1.5 s / page |
| Best for | Lightweight OCR on CPU or edge | Chinese documents and photos |
| Inputs | images | PDF, images |
| Languages | Chinese, English and more | 100+ languages |
| 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 | ✓ 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 RapidOCR if
- It runs on CPU through ONNX Runtime by default, and pip install rapidocr onnxruntime needs no Paddle framework.
- It has bindings for Python, C++, Java and C#, so it fits into desktop and server apps in many stacks.
- It is Apache-2.0 licensed with no regional exclusions, though converted models keep their upstream licenses.
Choose Hunyuan OCR if
- One ~1B model covers document parsing, text spotting, information extraction and image translation, with Markdown, HTML, LaTeX and JSON output.
- It accepts images up to 4K and a 128K context window in v1.5, and it covers low-resource and ancient-script OCR.
- It can run on a laptop or consumer GPU through the llama.cpp GGUF conversion, so a datacenter GPU is not required.
Key differences
| RapidOCR | Hunyuan OCR | |
|---|---|---|
| What it is | Toolkit that converts PaddleOCR models to ONNX and other runtimes | ~1B end-to-end OCR vision-language model from Tencent Hunyuan |
| Licence | Apache-2.0 (converted models keep their upstream licenses) | Tencent Hunyuan Community License. Excludes EU, UK and South Korea. Separate license needed above 100M monthly active users |
| How you run it | Python, C++, Java or C# library. CPU via ONNX Runtime by default, optional GPU, TensorRT, OpenVINO, MNN engines | Self-hosted via vLLM, Transformers or llama.cpp. NVIDIA GPU with CUDA 13 recommended for the unified vLLM environment. llama.cpp GGUF path for CPU, consumer GPU or laptop |
| Output formats | Plain text and bounding boxes | Markdown, HTML, LaTeX, JSON, plain text and bounding boxes |
| Languages | Chinese and English only by default. Other languages need extra models | Includes low-resource and ancient-script OCR |
| Benchmark | Not published | ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5) |
| Known failure | 16-bit grayscale PNG or TIFF give no text or wrong text. Sliced inference crashes on large pages. Arabic recognition crashes because python-bidi is undeclared | Archived 1.0 note said Transformers and vLLM outputs differed in accuracy. Unified vLLM setup needs CUDA 13 and vLLM 0.25.1+ |
Sources
What each one is
RapidOCR
PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.
RapidOCR detailsHunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
RapidOCR alternativesHunyuan OCR alternativesBest OCR models in 2026