Baseten Brings Four Open Models to Microsoft Foundry Preview

What happened
Baseten announced on November 17, 2026, that its inference infrastructure is available in public preview through Microsoft Foundry, initially powering four open models for Azure customers as a first-party Microsoft service. The models sit in the Foundry catalog alongside other open and closed systems, under the same enterprise controls and customers’ existing Microsoft agreements. Microsoft is a software and software development company based in Redmond, and its products and services include Azure.
Deployment Choices and OpenAI-Compatible APIs Baseten is positioning the integration as a way to evaluate and adopt open models without sourcing GPU (a chip built for many calculations at once, used for graphics and AI) capacity or managing model runtimes. The launch lineup consists of DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3 Flash and Kimi K3.
Administrators must opt in before their organizations can access the previewed models through Foundry. Baseten expects general availability in early 2027 and plans to add new open models on release day.
All Foundry customers can use the preview, but an administrator must opt in for their organization.
The announcement names coding agents, research workflows and customer support applications among the operates with for these newer models. It handles the serving infrastructure, while developers choose between Standard and Provisioned deployments; the company says those deployments are ready in seconds.
Global Standard and Data Zone Standard deployments in the US use pay-per-token billing. Global Provisioned and Data Zone Provisioned deployments in the US instead use provisioned throughput (how much work a system gets through in a given time) units (PTUs), which reserve capacity and provide predictable throughput.