With the launch of OpenAI’s gpt‑oss fashions—its first open-weight launch since GPT‑2—we’re giving builders and enterprises unprecedented skill to run, adapt, and deploy OpenAI fashions totally on their very own phrases.
AI is not a layer within the stack—it’s changing into the stack. This new period requires instruments which can be open, adaptable, and able to run wherever your concepts reside—from cloud to edge, from first experiment to scaled deployment. At Microsoft, we’re constructing a full-stack AI app and agent manufacturing facility that empowers each developer not simply to make use of AI, however to create with it.
That’s the imaginative and prescient behind our AI platform spanning cloud to edge. Azure AI Foundry supplies a unified platform for constructing, fine-tuning, and deploying clever brokers with confidence whereas Foundry Native brings open-source fashions to the sting—enabling versatile, on-device inferencing throughout billions of gadgets. Home windows AI Foundry builds on this basis, integrating Foundry Native into Home windows 11 to help a safe, low-latency native AI improvement lifecycle deeply aligned with the Home windows platform.
With the launch of OpenAI’s gpt‑oss fashions—its first open-weight launch since GPT‑2—we’re giving builders and enterprises unprecedented skill to run, adapt, and deploy OpenAI fashions totally on their very own phrases.
For the primary time, you’ll be able to run OpenAI fashions like gpt‑oss‑120b on a single enterprise GPU—or run gpt‑oss‑20b domestically. It’s notable that these aren’t stripped-down replicas—they’re quick, succesful, and designed with real-world deployment in thoughts: reasoning at scale within the cloud, or agentic duties on the edge.
And since they’re open-weight, these fashions are additionally simple to fine-tune, distill, and optimize. Whether or not you’re adapting for a domain-specific copilot, compressing for offline inference, or prototyping domestically earlier than scaling in manufacturing, Azure AI Foundry and Foundry Native provide the tooling to do all of it—securely, effectively, and with out compromise.
Open fashions, actual momentum
Open fashions have moved from the margins to the mainstream. At this time, they’re powering every thing from autonomous brokers to domain-specific copilots—and redefining how AI will get constructed and deployed. And with Azure AI Foundry, we’re supplying you with the infrastructure to maneuver with that momentum:
- With open weights groups can fine-tune utilizing parameter-efficient strategies (LoRA, QLoRA, PEFT), splice in proprietary information, and ship new checkpoints in hours—not weeks.
- You’ll be able to distill or quantize fashions, trim context size, or apply structured sparsity to hit strict reminiscence envelopes for edge GPUs and even high-end laptops.
- Full weight entry additionally means you’ll be able to examine consideration patterns for safety audits, inject area adapters, retrain particular layers, or export to ONNX/Triton for containerized inference on Azure Kubernetes Service (AKS) or Foundry Native.
In brief, open fashions aren’t simply feature-parity replacements—they’re programmable substrates. And Azure AI Foundry supplies coaching pipelines, weight administration, and low-latency serving backplane so you’ll be able to exploit each a type of levers and push the envelope of AI customization.
Meet gpt‑oss: Two fashions, infinite prospects
At this time, gpt‑oss-120b and gpt‑oss-20b can be found on Azure AI Foundry. gpt‑oss-20b can be out there on Home windows AI Foundry and will likely be coming quickly on MacOS through Foundry Native. Whether or not you’re optimizing for sovereignty, efficiency, or portability, these fashions unlock a brand new stage of management.
- gpt‑oss-120b is a reasoning powerhouse. With 120 billion parameters and architectural sparsity, it delivers o4-mini stage efficiency at a fraction of the scale, excelling at advanced duties like math, code, and domain-specific Q&A—but it’s environment friendly sufficient to run on a single datacenter-class GPU. Ideally suited for safe, high-performance deployments the place latency or price matter.
- gpt‑oss-20b is tool-savvy and light-weight. Optimized for agentic duties like code execution and power use, it runs effectively on a spread of Home windows {hardware}, together with discrete GPUs with16GB+ VRAM, with help for extra gadgets coming quickly. It’s excellent for constructing autonomous assistants or embedding AI into real-world workflows, even in bandwidth-constrained environments.
Each fashions will quickly be API-compatible with the now ubiquitous responses API. Meaning you’ll be able to swap them into current apps with minimal modifications—and most flexibility.
Bringing gpt‑oss to Cloud and Edge
Azure AI Foundry is greater than a mannequin catalog—it’s a platform for AI builders. With greater than 11,000 fashions and rising, it offers builders a unified area to guage, fine-tune, and productionize fashions with enterprise-grade reliability and safety.
At this time, with gpt‑oss within the catalog, you’ll be able to:
- Spin up inference endpoints utilizing gpt‑oss within the cloud with just some CLI instructions.
- Nice-tune and distill the fashions utilizing your personal information and deploy with confidence.
- Combine open and proprietary fashions to match task-specific wants.
For organizations growing situations solely attainable on consumer gadgets, Foundry Native brings outstanding open-source fashions to Home windows AI Foundry, pre-optimized for inference by yourself {hardware}, supporting CPUs, GPUs, and NPUs, by a easy CLI, API, and SDK.
Whether or not you’re working in an offline setting, constructing in a safe community, or operating on the edge—Foundry Native and Home windows AI Foundry helps you to go totally cloud-optional. With the aptitude to deploy gpt‑oss-20b on fashionable high-performance Home windows PCs, your information stays the place you need it—and the facility of frontier-class fashions involves you.
That is hybrid AI in motion: the flexibility to combine and match fashions, optimize efficiency and price, and meet your information the place it lives.
Empowering builders and choice makers
The provision of gpt‑oss on Azure and Home windows unlocks highly effective new prospects for each builders and enterprise leaders.
For builders, open weights imply full transparency. Examine the mannequin, customise, fine-tune, and deploy by yourself phrases. With gpt‑oss, you’ll be able to construct with confidence, understanding precisely how your mannequin works and methods to enhance it to your use case.
For choice makers, it’s about management and suppleness. With gpt‑oss, you get aggressive efficiency—with no black containers, fewer trade-offs, and extra choices throughout deployment, compliance, and price.
A imaginative and prescient for the longer term: Open and accountable AI, collectively
The discharge of gpt‑oss and its integration into Azure and Home windows is a part of a much bigger story. We envision a future the place AI is ubiquitous—and we’re dedicated to being an open platform to carry these revolutionary applied sciences to our prospects, throughout all our information facilities and gadgets.
By providing gpt‑oss by quite a lot of entry factors, we’re doubling down on our dedication to democratize AI. We acknowledge that our prospects will profit from a various portfolio of fashions—proprietary and open—and we’re right here to help whichever path unlocks worth for you. Whether or not you’re working with open-source fashions or proprietary ones, Foundry’s built-in security and safety instruments guarantee constant governance, compliance, and belief—so prospects can innovate confidently throughout all mannequin sorts.
Lastly, our help of gpt-oss is simply the newest in our dedication to open instruments and requirements. In June we introduced that GitHub Copilot Chat extension is now open supply on GitHub beneath the MIT license—step one to make VS Code an open supply AI editor. We search to speed up innovation with the open-source group and drive higher worth to our market main developer instruments. That is what it appears to be like like when analysis, product, and platform come collectively. The very breakthroughs we’ve enabled with our cloud at OpenAI are actually open instruments that anybody can construct on—and Azure is the bridge that brings them to life.
Subsequent steps and sources for navigating gpt‑oss
- Deploy gpt‑oss within the cloud at present with a number of CLI instructions utilizing Azure AI Foundry. Browse the Azure AI Mannequin Catalog to spin up an endpoint.
- Deploy gpt‑oss-20b in your Home windows gadget at present (and shortly on MacOS) through Foundry Native. Comply with the QuickStart information to study extra.
- Pricing1 for these fashions is as follows:
*See Managed Compute pricing web page right here.
1Pricing is correct as of August 2025.