← All projects
Developer building blocks

ONNX

A shared file format for AI models, so a model built with one tool can run in many others.

Widely used

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