What it does
ONNX, the Open Neural Network Exchange, is an open standard for saving AI models. It defines a common way to describe a model and the operations it uses.
Because many frameworks, tools and hardware makers support it, developers can build a model in one tool and run it somewhere else. The current focus is on running trained models to get answers, known as inference.
The project provides a Python package, documentation, tutorials and a collection of pre-trained models.
Who it's for
AI developers and engineers who move models between tools or deploy them on different hardware.
Can I use it without coding?
Developers only. It's a format and Python library used by programmers. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Show HN: Open-source Deep Research across workplace applicationsHacker News · Mar 2025
- ONNX: The Open Standard for Seamless Machine Learning InteroperabilityHacker News · Aug 2024