OCRRouter

RapidOCR vs InternVL3.5

Pick RapidOCR for offline CPU OCR of Chinese and English screenshots and receipts, or for embedding OCR in Java or C# apps. Pick InternVL3.5 for document question answering and Markdown or JSON output, if you have GPUs. The main split is a small text-and-box OCR library versus a self-hosted vision language model family.

RapidOCRrapidai/rapidocrInternVL3.5opengvlab/internvl
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 edgeSelf-hosted document understanding
Inputsimagesimages
LanguagesChinese, English and moreMultilingual
Max pages per request100500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
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 on CPU through ONNX Runtime by default, so you need no GPU.
  • It has bindings for Python, C++, Java and C#, so it embeds in many stacks.
  • It returns plain text and bounding boxes, which you need when a job wants word positions.

Choose InternVL3.5 if

  • It outputs Markdown and JSON as well as plain text, and suits document question answering.
  • It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost.
  • Models up to 30B fit on a single A100, and the MoE variants 20B-A4B and 30B-A3B activate few parameters per token.

Key differences

RapidOCRInternVL3.5
What it isOCR toolkit that converts PaddleOCR models to ONNX and other runtimesOpen-weight vision language model family from OpenGVLab, 1B to 241B-A28B parameters
LicenceApache-2.0; converted models keep their upstream licencesApache-2.0
How you run itLibrary for Python, C++, Java or C#; pip install rapidocr onnxruntimeSelf-host with Transformers, LMDeploy or vLLM
HardwareCPU via ONNX Runtime by default; optional GPU, TensorRT, OpenVINO, MNN, Paddle or PyTorch enginesUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100s
OutputPlain text and bounding boxesPlain text, Markdown and JSON; no bounding boxes or layout output by default
LanguagesChinese and English by default; other languages need extra modelsNot published
Known failure16-bit grayscale PNG or TIFF give no text or wrong text; Arabic recognition crashes; sliced inference crashes on large pagesOCR scores are published only as chart images, not text values

Sources

What each one is

RapidOCR

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

RapidOCR details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 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": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

RapidOCR alternativesInternVL3.5 alternativesBest OCR models in 2026