Together AI· Inference platformCapability change

New in Together GPU Clusters: Autoscaling, observability, and self-healing

Together AI announces major enterprise enhancements to Together GPU Clusters, including autoscaling, RBAC, full-stack observability, self-serve node repair, and active health checks.

From the source

Today, we’re introducing major enterprise enhancements to Together GPU Clusters (formerly Instant Clusters). We are integrating autoscaling, Role-Based Access Control (RBAC), full-stack observability, self-serve node repair, and active health checks directly into the core cluster experience — giving teams the elasticity of a virtualized stack with the performance profile of bare metal.

together.ai

Announced

10 Mar 2026 00:00 UTC

Detected