onnxruntime

ONNX Runtime is a runtime accelerator for Machine Learning models

onnxruntime Permissive license MIT License Active ★ 21,369 v1.28.0 released 2026-07-25

Install

onnxruntime on PyPI

pip

pip install onnxruntime

uv

uv add onnxruntime

poetry

poetry add onnxruntime

Package facts

License	MIT License (permissive)
Python support	supports the current Python release (>=3.11)
Install friction	medium — platform-specific wheel
Runtime dependencies	4 — flatbuffers, numpy, packaging, protobuf
Maintenance	actively maintained — 19 days since the last release
Last repo commit	2026-08-13
First released	2018-09-21
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: onnxruntime-1.28.0-cp311-cp311-macosx_14_0_arm64.whl; onnxruntime-1.28.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; onnxruntime-1.28.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; onnxruntime-1.28.0-cp311-cp311-win_amd64.whl; onnxruntime-1.28.0-cp311-cp311-win_arm64.whl; onnxruntime-1.28.0-cp312-cp312-macosx_14_0_arm64.whl; onnxruntime-1.28.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; onnxruntime-1.28.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; onnxruntime-1.28.0-cp312-cp312-win_amd64.whl; onnxruntime-1.28.0-cp312-cp312-win_arm64.whl; onnxruntime-1.28.0-cp313-cp313-macosx_14_0_arm64.whl; onnxruntime-1.28.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; onnxruntime-1.28.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; onnxruntime-1.28.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; onnxruntime-1.28.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; onnxruntime-1.28.0-cp313-cp313-win_amd64.whl; onnxruntime-1.28.0-cp313-cp313-win_arm64.whl; onnxruntime-1.28.0-cp314-cp314-macosx_14_0_arm64.whl; onnxruntime-1.28.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; onnxruntime-1.28.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Keywords: onnx, machine, learning

Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: PythonProgramming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules

About onnxruntime

from the package's own PyPI description — quoted content, verbatim

ONNX Runtime

ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models. For more information on ONNX Runtime, please see aka.ms/onnxruntime <https://aka.ms/onnxruntime/> or the Github project <https://github.com/microsoft/onnxruntime/>.

Changes

1.28.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.28.0

1.27.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.27.0

1.26.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.26.0

1.25.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.25.0

1.24.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.24.0

1.23.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.23.0

1.22.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.22.0

1.21.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.21.0

1.20.0 ^^^^^^

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.20.0

1.19.0 ^^^^^^

Release Notes :...

Read as markdown · JSON record · Source repository · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

ONNX Runtime is a performance-focused inference engine that executes Open Neural Network Exchange (ONNX) models across Windows, macOS, and Linux.

Medium install friction due to platform-specific prebuilt wheels for Python 3.11–3.14 across Windows, macOS, and Linux architectures. Four runtime dependencies (flatbuffers, numpy, packaging, protobuf) are stable and widely available. Active maintenance with release 19 days old signals strong ongoing support.

MIT License (permissive) imposes no significant restrictions on use, modification, or distribution in commercial or proprietary projects.

Usage

pip install onnxruntime
import onnxruntime as rt
sess = rt.InferenceSession('model.onnx')
output = sess.run(None, {'input': input_data})

Requires Python ≥3.11; ONNX model file must be available at runtime.

Verdict: onnxruntime is a production-grade, actively maintained inference engine with no known vulnerabilities, permissive licensing, and broad platform coverage. Medium install friction is typical for compiled ML runtimes. Suitable for deploying ONNX models in production environments.

Needs verification

Whether prebuilt wheels include GPU acceleration (CUDA/TensorRT) or are CPU-only by default.
Performance characteristics on specific hardware configurations.
Whether the four runtime dependencies have known vulnerabilities.

onnx model inferenceneural network runtimemachine learning model executiononnx scoring enginedeep learning inferencemodel deployment runtimeonnx accelerator