PaddleOCR (PP-OCR) vs Chunkr
Pick PaddleOCR (PP-OCR) when you need fast, free, local text detection and recognition on printed Chinese, English or other Latin-script text, including on CPU, edge or in the browser. Pick Chunkr when you need whole PDFs, slides or Word files turned into HTML or Markdown chunks for RAG. The main split is output: PaddleOCR returns text lines and boxes only, while Chunkr does layout analysis and semantic chunking.
PaddleOCR (PP-OCR)paddle/paddleocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 1 credit / page | 14 credits / page |
| Per 1,000 pages | $1.00 | $14.00 |
| Typical speed | 0.7 s / page | 3.0 s / page |
| Best for | Fast printed text, Chinese and English | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 80+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| 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 PaddleOCR (PP-OCR) if
- Apache-2.0 licence with no cost beyond compute, so you can ship it in closed-source products without a commercial licence.
- It runs on CPU, NVIDIA GPU and other accelerators, and in the browser through the PaddleOCR.js SDK, with no external LLM endpoint needed.
- One PP-OCRv6 model covers 50 languages, including Chinese, English, Japanese and 46 Latin-script languages, at 34.5M parameters for the medium size.
Choose Chunkr if
- It returns HTML, Markdown, JSON and bounding boxes, so you get structured document output instead of bare text lines.
- It accepts PDF, PPT, Word and images, and it is built for RAG chunking of PDFs and slides.
- You can use the hosted cloud API, or self-host with Docker on GPU, CPU-only or Mac ARM, and connect any OpenAI-compatible LLM endpoint.
Key differences
| PaddleOCR (PP-OCR) | Chunkr | |
|---|---|---|
| Licence | Apache-2.0 | AGPL-3.0, or a commercial licence. Closed-source use needs the commercial licence. |
| How you run it | Local library: Python package, C++ or the PaddleOCR.js browser SDK | Hosted cloud API, or open-source self-host via Docker |
| Price | Free, self-hosted (you pay for compute) | Hosted credit-based plans, official prices not verified. Open-source version is free, but you pay for compute and an LLM endpoint. |
| Output formats | Plain text, bounding boxes, JSON | HTML, Markdown, JSON, bounding boxes |
| Tables and layout | Text lines and boxes only. Tables and formulas need the separate PP-Structure or VL pipelines. | Layout analysis and semantic chunking built in |
| Input files | Not published | PDF, PPT, Word and images. Excel is not supported in the open-source version. |
| Known failure | PP-OCRv6 weights contain denormals that make CPU inference 4 to 11x slower in RapidOCR. A NotImplementedError was reported with PaddleOCR 3.7.0 on PaddlePaddle 3.3.1. | The open-source version uses community models that are less accurate than the cloud's in-house models. |
Sources
- PaddleOCR GitHub README
- PP-OCRv6 on Hugging Face
- RapidOCR issue #743 denormal weights
- Issue #18162
- Chunkr GitHub README
- Chunkr site
What each one is
PaddleOCR (PP-OCR)
Baidu's classic open-source text detection and recognition pipeline. Light enough to run on CPU.
PaddleOCR (PP-OCR) detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr 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": "paddle/paddleocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
PaddleOCR (PP-OCR) alternativesChunkr alternativesBest OCR models in 2026