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…
Baseten Brings Four Open Models to Microsoft Foundry Preview
Event trace
Timeline
Time Slices
- T0 6 篇 2026-11-18 06:56 Haoyuan Li on Alluxio The server-side rendering equivalent for LLM inference workloads You’re probably underutilizing your GPUs Breaking your AI storage bottlenecks Exclusive | Affordablity Is Key To AI Success In India: Peak XV's Rajan Anandan Baseten Brings Four Open Models to Microsoft Foundry Preview
- T+2h 6 篇 2026-11-18 08:56 Haoyuan Li on Alluxio The server-side rendering equivalent for LLM inference workloads You’re probably underutilizing your GPUs Breaking your AI storage bottlenecks Exclusive | Affordablity Is Key To AI Success In India: Peak XV's Rajan Anandan Baseten Brings Four Open Models to Microsoft Foundry Preview
- T+12h 6 篇 2026-11-18 18:56 Haoyuan Li on Alluxio The server-side rendering equivalent for LLM inference workloads You’re probably underutilizing your GPUs Breaking your AI storage bottlenecks Exclusive | Affordablity Is Key To AI Success In India: Peak XV's Rajan Anandan Baseten Brings Four Open Models to Microsoft Foundry Preview
- T+24h 6 篇 2026-11-19 06:56 Haoyuan Li on Alluxio The server-side rendering equivalent for LLM inference workloads You’re probably underutilizing your GPUs Breaking your AI storage bottlenecks Exclusive | Affordablity Is Key To AI Success In India: Peak XV's Rajan Anandan Baseten Brings Four Open Models to Microsoft Foundry Preview
Conclusion
该事件汇聚 6 个来源,平均可信度 37%
Confidence: medium
Find Your Interest
- The Roundup by ByteByteGo
- v1.27.0
- v1.27.0-pre
- Dan Maher from Datadog Says AI Agent Reliability Is an Engineering Problem, Not a Model Choice
- v1.28.0-pre
- The Guardrail Is Now Part of the Attack
- v1.28.1
- The First AI Model That Scared Me Can’t Write a Sentence
- How LinkedIn Uses AI to Review 40,000 Pull Requests a Week
- EP231: AI Terms You Need to Know





