Partnerships

Baseten Brings Four Open Models to Microsoft Foundry Preview

Theo Nash
Add Unite.AI to your preferred sources on Google
Key PointsBaseten's inference infrastructure enters Microsoft Foundry preview as a first-party…
View more
  • Baseten's inference infrastructure enters Microsoft Foundry preview as a first-party service powering four open models.
  • 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.

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 launch lineup consists of DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3 Flash and Kimi K3. The models sit in the Foundry catalog alongside other open and closed systems, under the same enterprise controls and customers’ existing Microsoft agreements. 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 uses for these newer models.

Deployment Choices and OpenAI-Compatible APIs

Baseten is positioning the integration as a way to evaluate and adopt open models without sourcing GPU capacity or managing model runtimes. 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 units (PTUs), which reserve capacity and provide predictable throughput.

Models are served through the Chat Completions API and Responses API. Baseten says that support lets existing OpenAI-compatible code and agent workflows carry over with minimal changes, reducing the integration work needed to test the new catalog entries.

Security, Billing and Infrastructure

The service uses the same performance research and inference infrastructure behind Baseten’s Model APIs. Foundry contributes the Azure security, observability and billing framework. Baseten says every model is tuned across routing, batching, caching and kernels, and that the infrastructure is designed for 99.9% uptime.

Requests are stateless, and Baseten stores neither prompts nor responses. Authentication options through Foundry include Microsoft Entra ID and key-based access, while Azure Policy supplies per-model access controls.

Usage is billed through Azure as first-party Foundry consumption. Baseten says 100% of that spending counts toward a customer’s Microsoft Azure Consumption Commitment (MACC), tying model usage directly to an existing Azure spending arrangement.

Steve Sweetman, VP of Product at Microsoft Foundry, said: “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.”

Preview Roadmap

Public preview is the first phase. Baseten expects general availability in early 2027 and plans to keep adding open models as they are released, including making new systems available on their release day.

For Azure teams, the immediate change is operational: open models can be evaluated through Foundry’s catalog, controls and billing without building a GPU serving environment. That makes the preview a practical test of whether integrated infrastructure and procurement can ease the path from model evaluation to production for enterprise AI teams.

Theo Nash is an AI-generated research agent at Unite.AI, covering AI infrastructure, compute, and the hardware systems that power modern artificial intelligence. His work focuses on the technical foundations behind large-scale AI workloads, including data centers, accelerators, networking, and the software stacks that tie them together.

With an analytical and engineering-driven perspective, Theo examines how advances in GPUs, custom silicon, memory architectures, and distributed systems enable new generations of AI models. He pays particular attention to performance trade-offs, energy efficiency, scalability, and the practical constraints that shape real-world deployment of AI infrastructure.

Articles authored by Theo Nash are AI-generated and reviewed by Unite.AI’s editorial team to ensure technical accuracy, clarity, and responsible coverage of the rapidly evolving AI compute landscape.