ONNX Runtime

ONNX Runtime is ranked #1 of 35 in deep learning software on The Geeks Club. It runs on Android, iOS, Linux, macOS, Self-hosted, Web, Windows. There is a free plan.

ONNX Runtime plans and pricing

All plans

Open source Free MIT license · cross-platform runtime github.com · 1 Oct 2026

Compared on deep learning software

Free plan: Yes
Training mode: local
Deployment targets: multiple
GPU acceleration: Yes
Supported languages: Python, C, C++, C#, Java, JavaScript, TypeScript, Kotlin, Objective-C
Model formats: ONNX, ORT

Best ONNX Runtime alternatives

See all 12

7.5 Amazon SageMaker Autopilot Free trial

7.5 Paperspace Gradient Free plan

7.4 Apache TVM Free plan

7.4 MATLAB Grader Free plan

7.2 TensorFlow Free plan

7.2 Trackio Free plan

ONNX Runtime

Purpose: ONNX Runtime is a production-grade engine for accelerating machine-learning training and inference in existing technology stacks.
Model frameworks: Inference supports models from PyTorch, Hugging Face, and TensorFlow across different software and hardware stacks.
Performance: It provides optimizations for inference latency, throughput, memory utilization, and binary size.
Hardware acceleration: Its extensible Execution Providers framework lets ONNX models use hardware-specific acceleration libraries across CPUs, GPUs, FPGAs, and specialized NPUs.
Provider integrations: Listed providers include NVIDIA CUDA and TensorRT, Intel OpenVINO, Windows DirectML, Qualcomm QNN, Android NNAPI, Apple CoreML, Azure, and WebGPU.
Languages: The site lists support for Python, C#, C++, Java, JavaScript, and Rust, among other languages.
Platforms: The site says ONNX Runtime runs on Linux, Windows, Mac, iOS, Android, and web browsers.
Deployment: Inference is described for cloud servers, edge and mobile devices, and web browsers.
Generative AI: The generative AI page describes deploying text, image, and audio models, including Llama, Mistral, Phi, Stable Diffusion, and Whisper.
On-device privacy: The generative AI page says on-device models can run inference privately and save costs.
Training: ONNX Runtime supports on-device training and says it can reduce costs for large-model training.
Package sizing: If a prebuilt web or mobile package is too large, developers can make a custom build containing only the operators and opsets their models need.
Nightly build support: The install page warns that nightly builds have limited support and advises against deploying them to production workloads.
Windows guidance: The install page says DirectML is in sustained engineering and recommends WinML for new Windows projects.
Price from: Free

Visit site Alternatives

Where it ranks on The Geeks Club

Best Deep Learning Software in 2026#1 of 35

Is ONNX Runtime yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote ONNX Runtime

Sources

onnxruntime.ai· checked 1 Oct 2026
onnxruntime.ai/inference· checked 1 Oct 2026
onnxruntime.ai/docs/execution-providers/· checked 1 Oct 2026
onnxruntime.ai/generative-ai· checked 1 Oct 2026
onnxruntime.ai/docs/install/· checked 1 Oct 2026
onnxruntime.ai/docs/· checked 1 Oct 2026
onnxruntime.ai/docs/ecosystem/· checked 1 Oct 2026
github.com/microsoft/onnxruntime/blob/main/SECURIT· checked 1 Oct 2026
onnxruntime.ai/getting-started· checked 1 Oct 2026
github.com/microsoft/onnxruntime· checked 1 Oct 2026