Baseten Brings High-Performance Inference for Open Models to Microsoft Foundry
Enterprises can now run open models with Baseten’s speed and reliability and Foundry’s security and governance, under
Press Release Disclaimer: This is a press release distributed through the XPR Media network. It has not been independently verified by our newsroom.

![]()
SAN FRANCISCO, Nov. 17, 2026 (GLOBE NEWSWIRE) — Baseten, the inference operating system for owned intelligence, today announced a partnership with Microsoft Corp. (NASDAQ: MSFT) bringing Baseten’s high-performance inference to Microsoft Foundry. Now in public preview, Baseten on Microsoft Foundry lets enterprises on Azure run frontier open models on Baseten’s fast, reliable inference with Foundry’s built-in security and governance, billed through their existing Microsoft agreement. Together, Baseten and Microsoft Foundry provide the performance, control, and ownership needed to securely scale AI on open models.
As production workloads become more complex, enterprises are turning to open models for control over cost, speed, customization, and compliance. Baseten on Microsoft Foundry gives them a frictionless path to the open frontier — without having to secure GPU capacity, manage deployments, or onboard another vendor — all from the Foundry platform where they already build and govern AI apps and agents.
“The next wave of AI innovation will come from what developers build when powerful open models meet high-performance infrastructure,” said Steve Sweetman, VP of Product at Microsoft Foundry. “Bringing Baseten to Microsoft Foundry gives enterprises more choice and pairs Baseten’s optimized and reliable inference with the governance, controls, and observability within the Foundry platform, so developers can turn their most ambitious ideas into production applications. Together, we’re helping customers create value faster.”
Baseten on Microsoft Foundry offers a choice of frontier open models, including DeepSeek V4.1 Flash 1017, GLM 5.3, GLM 5.3 Flash, and Kimi K3. Each model runs on Baseten’s full inference stack, bringing Baseten’s research-backed performance and reliability to Azure. For enterprise control, Baseten on Microsoft Foundry offers global and U.S. data zones for customers with residency requirements. It also includes zero data retention and Azure Policy controls that let administrators restrict specific models.
Customers are billed through Azure as first-party Foundry consumption and can apply their existing Microsoft Azure Consumption Commitment. Teams can choose pay-as-you-go for usage-based access or Provisioned Throughput Units (PTUs) for SLA-backed performance.
“It’s easy to forget how early broad adoption of AI is. Many enterprises are just now seeing how open models can deliver better efficiency, reliability, and ownership,” said Amir Haghighat, co-founder and CTO at Baseten. “Microsoft is one of the most trusted and respected names for enterprises, and we’re eager to help its customers move faster in building durable, owned intelligence.”
Baseten on Microsoft Foundry is available today in public preview, with general availability expected in early 2027. After an enterprise opts in, developers can find Baseten models in Microsoft Foundry’s model catalog, then choose a model and select a deployment type. Deployments are ready in seconds, and no prompts or responses are stored.
About Baseten
Baseten provides the building blocks for the open frontier, bringing inference, training, and execution together so companies can build, run, and scale AI in production. Founded in 2019 and based in San Francisco, Baseten is valued at $13 billion and has raised more than $2 billion from leading investors.
Contacts
Media Contact
press@baseten.co

Media gallery


