Compare software

PaddleOCRMarker
Free

Free and open source under the Apache licence.

 Free

The code is free under Apache 2.0; model weights have a separate licence, and Datalab…

Windows, macOS, Linux, Command line Self-hosted, Command line
  • Parses layout, tables and formulas, not just lines of text
  • Outputs JSON and Markdown ready for downstream processing
  • Handles tables, equations and code blocks
  • Accepts many input formats besides PDF
  • Built on the PaddlePaddle framework, which is a large dependency
  • Much of the documentation and community is in Chinese
  • Model weights are under a separate licence from the code
  • Needs a Python environment and benefits from a GPU
Downloadable app Downloadable app, Self-hosted
Open source Open source
License: Apache-2.0 License: Apache-2.0
Not stated if an account is needed No account needed
Not stated if it works offline Not stated if it works offline

Checked September 22, 2026

Checked September 23, 2026

Catalog facts only. Anything “not stated” is unconfirmed. Check full listings for details.