Baseten launches in Microsoft Foundry public preview
Understand this story
Baseten is now available in Microsoft Foundry public preview, allowing Azure enterprise customers to call frontier open-source models powered by Baseten's inference infrastructure directly from the Foundry model catalog, with the first batch including DeepSeek V4.1 Flash, GLM-5.3, and Kimi K3. Baseten says an administrator must enable access for the organization; this is the first phase of Baseten's entry into Foundry, with general availability expected in early 2027. On pricing, customers can choose pay-per-token Global Standard or Data Zone Standard (US) deployments, or Global Provisioned or Data Zone Provisioned (US) deployments that reserve capacity in provisioned throughput units (PTUs). Usage is billed through Azure as first-party Foundry consumption and counts 100% toward the Microsoft Azure Consumption Commitment (MACC).
AI overview based on source reports · Updated 2 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Baseten BlogBaseten is now available on Microsoft Foundry
Baseten is now in public preview on Microsoft Foundry, letting Azure customers test, deploy and scale frontier open models through Baseten's inference infrastructure directly from the Foundry model catalog. Launch models include DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3-Flash and Kimi K3, offered with Standard or Provisioned deployments, zero data retention, Entra ID and key-based authentication, and MACC-eligible billing. General availability is expected in early 2027.
Activity for this story
- Current comparable activity
- 9
- Peak comparable activity
- 10Nov 18 07:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.