onnxruntime
ONNX Runtime is a runtime accelerator for Machine Learning models
Decision gist · record as of 2026-08-14
Yes. onnxruntime is a mature, actively maintained library with no known vulnerabilities, permissive MIT licensing, and broad platform support. Install it if you have ONNX models to run in production or development. Medium install friction is typical for compiled inference engines and poses no barrier for standard environments.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an ONNX model file (.onnx) and input data compatible with the model's expected input shape and type.
- Medium install friction due to platform-specific wheels (x86_64, ARM, Windows, macOS, Linux variants) and compiled dependencies.
- Active maintenance with a release 20 days ago and ongoing repository activity.
License · maintenance · safety
MIT License (permissive) — MIT License permits commercial and private use with minimal restrictions, making it suitable for most production and research deployments.
last release 2026-07-25 (20 days) · last repo commit 2026-08-14 · 21,370 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 89,348,090 downloads/mo, #376 on PyPI
Alternatives
Verify before relying
pip install onnxruntime
import onnxruntime as rt
sess = rt.InferenceSession('model.onnx')
results = sess.run(None, {'input': input_data})- Whether the package includes GPU acceleration support or requires separate installation
- Performance characteristics compared to other ONNX runtime implementations
- Specific ONNX opset versions supported in 1.28.0
What it is and what it does
onnxruntime is a scoring engine that executes ONNX models—a standardized format for representing trained neural networks and machine learning models. It takes a serialized ONNX model file and input data, runs inference, and returns predictions. The package is designed for performance, offering optimized execution paths across different hardware platforms (x86, ARM, Windows, Linux, macOS) and supporting modern Python versions (3.11–3.14).
The package depends on flatbuffers, numpy, packaging, and protobuf for serialization, numerical computation, and dependency resolution. It is actively maintained and widely used in production for model deployment, batch inference, and real-time serving scenarios where model latency and throughput matter.
Use it for
- Load a trained ONNX model and run inference on new data in a Python application
- Deploy machine learning models to edge devices or embedded systems with ARM processors
- Batch-score large datasets using optimized inference on multi-core CPUs
- Integrate model serving into microservices or REST APIs for real-time predictions
- Benchmark and compare inference performance of different ONNX models across platforms
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
onnxruntime is a mature, actively maintained library with no known vulnerabilities, permissive MIT licensing, and broad platform support. Install it if you have ONNX models to run in production or development. Medium install friction is typical for compiled inference engines and poses no barrier for standard environments.
Install
onnxruntime on PyPI
Before you install
Medium install friction due to platform-specific wheels (x86_64, ARM, Windows, macOS, Linux variants) and compiled dependencies. Active maintenance with a release 20 days ago and ongoing repository activity.
Requires an ONNX model file (.onnx) and input data compatible with the model's expected input shape and type.
License in practice
MIT License permits commercial and private use with minimal restrictions, making it suitable for most production and research deployments.
Quickstart
pip install onnxruntime
import onnxruntime as rt
sess = rt.InferenceSession('model.onnx')
results = sess.run(None, {'input': input_data})Verify before relying
- Whether the package includes GPU acceleration support or requires separate installation
- Performance characteristics compared to other ONNX runtime implementations
- Specific ONNX opset versions supported in 1.28.0
Package facts
| License | MIT License permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 4 packagesflatbuffersnumpypackagingprotobuf |
| Maintenance | Actively maintained 20 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 89,348,090 / month, #376 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | 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 |
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
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “onnx model loader”
- onnxruntimeonnxruntime loads and executes Open Neural Network Exchange (ONNX)…
- sod4onnxsod4onnx removes specified output operations from ONNX model files,…
- onnxslimOnnxSlim reduces the size and operator count of ONNX models while…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also onnxruntime-gpu · onnx-weekly · onnxruntime-openvino · onnxruntime_extensions · onnx · optimum-onnx · sit4onnx · skl2onnx · onnxslim