Baseten Enters Public Preview on Microsoft Foundry
Start here
Baseten is now in public preview on Microsoft Foundry, letting Azure customers run open models on Baseten's inference infrastructure as a first-party Microsoft service. Baseten says models are available in the Foundry model catalog to all customers, with an admin opting in to enable access for their organization. The launch models are DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3-Flash and Kimi K3, served through Chat Completions and Responses APIs with 99.9% uptime. Usage is billed through Azure as first-party Foundry consumption and counts 100% toward a customer's Microsoft Azure Consumption Commitment (MACC). Baseten describes public preview as the first phase, with general availability expected in early 2027.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- Baseten BlogBaseten Now Available in Public Preview on Microsoft Foundry
Baseten is now in public preview on Microsoft Foundry, letting Azure enterprises run frontier open models on Baseten's optimized inference infrastructure as a first-party Microsoft service. Launch models include DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3-Flash and Kimi K3, served via Chat Completions and Responses APIs with 99.9% uptime and MACC-eligible billing. General availability is expected in early 2027.
Heat for this event
Not enough continuous observations yet to draw a trend.