This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
A unified, reliable and secure platform supporting the AI developer lifecycle from model selection, fine-tuning, optimizing and deployment across CPU, GPU, NPU and cloud.
Windows AI APIs
APIs that unlock the power of models shipping with Windows.
Learn more
Foundry Local
Pull in your favorite open-source models and make your app smarter with Foundry Local
Learn more
Windows ML
Bring your own model and let Windows ML run it on the NPU, GPU or CPU.
Learn more
Tools and samples
Tools and samples get you started with Windows AI Foundry.
Learn moreReady-to-use AI APIs powered by on-device models. Optimized for efficiency and performance on Copilot+ PCs devices with minimal setup required.
Learn more about Windows AI APIs
Small yet powerful language model to generate text
Recognize text in images.
Upscale your images using local AI models
Identify specific objects in an image
Generate various types of text descriptions for an image
Retouch your images and remove unwanted objects
Use LoRA for Phi Silica to customize the on-device small language model with your own data.
Build your vector store and bring semantic and lexical search in your apps using Semantic Search and Knowledge Retrieval.
Learn more
Find and integrate popular open-source language models with the Foundry Local CLI shipping on every Windows device.
Get started with Foundry Local
Windows AI Foundry integrates Foundry Local, offering developers quick access to ready-to-use open-source models on Windows Silicon. This offers the ability for developers to browse, test, interact and deploy models in their local apps. With the Foundry Local model catalog, we have done the heavy-lifting of optimizing these models across CPUs, GPUs and NPUs, making them ready-to-use.
Windows ML serves as the core of our AI platform and the integrated AI inferencing runtime on Windows. It allows developers to use their own models and deploy them efficiently across a broad silicon partner ecosystem, including AMD, Intel, NVIDIA, and Qualcomm, supporting CPU, GPU, and NPU architectures.
Learn more about Windows ML
Check out these developers tools, samples and tutorials to get started with Windows AI Foundry.
Check out samples and tools
AI Dev Gallery
Get started with local AI by exploring samples, testing APIs, and viewing source code! AI Dev Gallery is a great place to begin your AI journey.
Learn more
AI Toolkit
The AI Toolkit for Visual Studio Code provides tools and a model catalog to help jump-start local AI development and deployment.
Learn moreSee how developers are using Windows AI Foundry to build amazing experiences
Hear why devs are excited about Windows ML
Hear from app developers how Windows ML empowers them to efficiently create AI-driven Windows applications, maximizing the potential of on-device AI.
Learn more
Learn why hardware partners support Windows ML
Microsoft has partnered with independent hardware vendors to bring Windows ML to Windows app developers. Discover why these leading industry players recognize the potential of Windows ML and how they believe it will empower developers working on Windows applications.
Learn more
Inside look: Developers on the power of Windows AI APIs
Developers are using Windows AI APIs to integrate AI into their applications. These custom-built APIs, designed to work with Copilot+ PC hardware, enable a variety of AI-driven features. Learn how partners are incorporating AI seamlessly and enhancing their app capabilities.
Learn more
Follow us