Announcing Foundry Managed Compute: Run open models in Microsoft Foundry
Microsoft launches Foundry Managed Compute to run and customize open-source AI models on managed elastic GPU capacity.
“Managed Compute is built to lift that work off your team so the model, not the infrastructure, is what you spend your time on.”
Microsoft announced Foundry Managed Compute, a managed platform for serving and customizing open-source AI models on dedicated GPU capacity without operating VMs, Kubernetes, or inference runtimes. It rounds out Foundry as a single platform spanning frontier, open-source, and custom models through one endpoint and bill, signaling Microsoft's push to capture enterprise demand for controllable, lower-cost open models alongside frontier APIs.