Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

Microsoft DirectML

Free#22 of 39 in GPU Computing SDKs

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.

7.1/10Editor score
Microsoft DirectML7.1 Visit DirectML

At a glance

  • Editor score
    7.1 / 10
  • Pricing
    Free plan
  • Best for
    Windows GPU machine learning
  • Free plan
    Yes
  • Paid from
    Free
  • Facts checked
    22 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

Plans Free planFree Free to use — no paid tier required for the core job.
See plans on learn.microsoft.com

Microsoft DirectML fact sheet

Free planYes
Paid fromFree
Compiler toolchainNo
GPU backendsNot verified
Supported platformsWindows
Accelerator APIsDirectML C++/COM API; DirectX 12
Supported languagesC++ (native); Python via PyDirectML samples
Architecture targetsDirectX 12-compatible AMD, Intel, NVIDIA, and Qualcomm hardware
Parallel librariesYes
DeploymentSelf-hosted
PlatformsWindows
SupportDocs, Community
Built forSmall business, Mid-market, Enterprise (editorial estimate)
Integrations4 integrations: ONNX Runtime, Windows ML, TensorFlow, PyTorch
PricingFree plan
Websitelearn.microsoft.com
Facts checked22 Nov 2026

Microsoft DirectML integrations

Microsoft DirectML lists 4 integrations on its own site.

  • ONNX Runtime
  • Windows ML
  • TensorFlow
  • PyTorch

Alternatives to Microsoft DirectML

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

Reviews come only from verified accounts. Sign in or create an account first — your e-mail is never shown.

Your rating

0 characters · at least 80, up to 3,000

Posted from your verified account. Reviews appear after an editor reads them, usually within two working days.

Featured on iTechGuides

Featured on iTechGuides — Microsoft DirectML 7.1/10

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