Microsoft DirectML
Microsoft DirectML: A free, open-source Windows API for DirectX 12 GPU and NPU machine-learning execution. Ranked #22 of 39 in GPU Computing SDKs by our editors (7.1/10); pricing: Free plan; best for windows GPU machine learning.
At a glance
- Editor score7.1 / 10
- PricingFree plan
- Best forWindows GPU machine learning
- Free planYes
- Paid fromFree
- Facts checked22 Nov 2026
Where it wins
- DirectX 12 hardware abstraction across AMD, Intel, NVIDIA, and Qualcomm GPUs
- Integrates with ONNX Runtime, Windows ML, TensorFlow, and PyTorch
- Supports both layer-by-layer and graph execution workflows
Where it doesn't
- Windows-only platform support
- Requires DirectX 12-compatible GPUs or AI acceleration hardware
- New feature development has moved to Windows ML
Our verdict on Microsoft DirectML
Microsoft DirectML is a low-level, hardware-accelerated machine-learning API for Windows applications, games, engines, middleware, and custom frameworks. Its DirectX 12-style C++/COM interface executes neural-network operators and graphs on DirectX 12-compatible GPUs and AI acceleration hardware. It suits teams building Windows inference or graphics workloads that need direct control over execution, as well as developers integrating through ONNX Runtime or Windows ML.
The SDK is open source with a free plan and supports self-hosted deployment. Teams can use its native C++ and nano-COM API, a standalone redistributable package, or framework connections including ONNX Runtime, Windows ML, TensorFlow, and PyTorch. The ONNX Runtime DirectML execution provider and Windows ML backend integration make it practical for applications that already use those ecosystems. Python access appears through PyDirectML samples, while the core interface remains native C++/COM.
DirectML includes a hardware-accelerated operator library, layer-by-layer and graph execution workflows, and samples covering super-resolution, object detection, and NPU inference. Microsoft documents the project as being in sustained engineering: security and compliance fixes remain supported, while new feature development has moved to Windows ML. Choose DirectML when a Windows application needs DirectX 12-based execution across compatible hardware; teams seeking ongoing new DirectML features should look to Windows ML instead.
Your product? Our editors can test Microsoft DirectML in depth and publish a review, labelled as paid · from $149/mo →
Microsoft DirectML pricing
Microsoft DirectML fact sheet
| Free plan | Yes |
|---|---|
| Paid from | Free |
| Compiler toolchain | No |
| GPU backends | Not verified |
| Supported platforms | Windows |
| Accelerator APIs | DirectML C++/COM API; DirectX 12 |
| Supported languages | C++ (native); Python via PyDirectML samples |
| Architecture targets | DirectX 12-compatible AMD, Intel, NVIDIA, and Qualcomm hardware |
| Parallel libraries | Yes |
| Deployment | Self-hosted |
| Platforms | Windows |
| Support | Docs, Community |
| Built for | Small business, Mid-market, Enterprise (editorial estimate) |
| Integrations | 4 integrations: ONNX Runtime, Windows ML, TensorFlow, PyTorch |
| Pricing | Free plan |
| Website | learn.microsoft.com |
| Facts checked | 22 Nov 2026 |
Microsoft DirectML integrations
Microsoft DirectML lists 4 integrations on its own site.
- ONNX Runtime
- Windows ML
- TensorFlow
- PyTorch
Alternatives to Microsoft DirectML
- NVIDIA CUDA ToolkitA free, full CUDA development toolkit for C/C++ and Python on Linux and Windows.9.4
- AMD ROCmA broad, open-source toolkit for AMD GPU compute, AI frameworks, and HPC workloads.9.2
- Intel oneAPI ToolkitA free, broad Intel toolkit for C++, SYCL, Fortran, profiling and accelerator analysis.9.0
See all Microsoft DirectML alternatives →
Used Microsoft DirectML? Be the first to review it
The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used Microsoft DirectML for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.
Write a reviewTwo minutes · verified accounts only · read by an editor before it appears
Featured on iTechGuides
Microsoft DirectML is listed in our GPU Computing SDKs directory. Add the badge to your site — it links back to this page.
<a href="https://www.itechguides.com/products/microsoft-directml/"><img src="https://www.itechguides.com/best/badge/microsoft-directml.svg" alt="Featured on iTechGuides" width="230" height="46"></a>
Reviewed by iTechGuides Editors · Editorial team · Updated Nov 2026
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update
