OCRRouter

OpenOCR vs Chunkr

Pick OpenOCR for self-hosted Chinese and English document parsing, especially academic PDFs with formulas, where a 0.1B model is enough. Pick Chunkr for RAG pipelines that need HTML, Markdown or JSON chunks from PDFs, slides, Word files and images, with the option of a hosted API.

OpenOCRfudan/openocrChunkrchunkr/chunkr
TypeOpen sourceOCR API
Price1 credit / page14 credits / page
Per 1,000 pages$1.00$14.00
Typical speed0.5 s / page3.0 s / page
Best forLightweight OCR pipeline on CPULayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
LanguagesChinese and EnglishMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 OpenOCR if

  • It is Apache-2.0 licensed and free to self-host, with no copyleft terms to worry about in closed products.
  • OpenDoc-0.1B reports 90.57 on OmniDocBench v1.5 with only 0.1B parameters, and UniRec-0.1B handles plain text and formulas in one model.
  • It exports to ONNX and outputs LaTeX, which suits Chinese and English academic PDFs with formulas.

Choose Chunkr if

  • It accepts PDF, PPT, Word and images and outputs HTML, Markdown, JSON and bounding boxes, which fits RAG chunking.
  • It offers both a cloud API and a self-host version, so you can start hosted and move to Docker later.
  • Self-host runs on GPU, CPU-only or Mac ARM, and works with any OpenAI-compatible LLM endpoint.

Key differences

OpenOCRChunkr
LicenceApache-2.0AGPL-3.0 or commercial licence; closed-source use needs the commercial licence
How you run itSelf-host only, as a Python libraryCloud API or self-host with Docker (GPU, CPU-only, Mac ARM)
PriceFree, you pay for computeHosted credit-based plans (prices not published); open-source version is free but you pay for compute and an LLM endpoint
Output formatsPlain text, LaTeX, bounding boxesHTML, Markdown, JSON, bounding boxes
Input formatsNot publishedPDF, PPT, Word and images; no Excel in the open-source version
Benchmark90.57 on OmniDocBench v1.5 (OpenDoc-0.1B), self-reported by the authorsNot published
Known limitsChinese and English only; document parsing needs the separate PP-DocLayoutV2 layout model; no hardware or throughput figuresOpen-source version uses community models that are less accurate than the cloud's; self-host needs an external LLM endpoint

Sources

What each one is

OpenOCR

Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.

OpenOCR details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr 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": "fudan/openocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OpenOCR alternativesChunkr alternativesBest OCR models in 2026