From the source
Baseten is now in public preview on
Microsoft Foundry, letting Azure customers run frontier open models through Baseten's 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, with new models becoming available the day they are released.
- Baseten says the infrastructure is built for 99.9% uptime, and Microsoft Foundry supplies the enterprise security, observability and billing Azure teams already use.
- Customers can pick Global Standard or Data Zone Standard (US) deployments billed per token, or Global Provisioned or Data Zone Provisioned (US) deployments with provisioned throughput units for reserved capacity.
- Usage is billed through Azure as first-party Foundry consumption and counts 100% toward a Microsoft Azure Consumption Commitment.
- Models are available in the Foundry model catalog today; an admin opts in, developers choose a deployment type, and deployments are ready in seconds.
- Models are served through the Chat Completions API and the Responses API, requests are stateless, and Baseten stores no prompts or responses.
- General availability is expected in early 2027.





