Getting a Dedicated AI Cluster's Details
Get the details for a dedicated AI cluster in OCI Generative AI.
Hosting Cluster Details
For a hosting dedicated AI cluster, review these fields to understand its compute and endpoint capacity:
- Unit size
- The dedicated AI unit shape selected for the model hosted on the cluster. The unit shape identifies the compute resources used by the model.
- Number of units
- The dedicated AI units provisioned for the cluster's model replicas. Adding model replicas increases the cluster's inference throughput and requires additional units.
- Remaining endpoint capacity
- The number of additional model endpoints that the cluster can support under its current endpoint limit. By default, a hosting cluster supports up to 50 model endpoints. For example, if a cluster has one endpoint, the remaining endpoint capacity is 49. This value counts model endpoint resources, not model replicas or inference requests.
Creating additional model endpoints doesn't increase the cluster's inference throughput. See Endpoint Capacity.
On the Dedicated AI clusters list page, select the dedicated AI cluster that you want to work with. If you need help finding the list page for dedicated AI clusters, see Listing Dedicated AI Clusters. On the dedicated AI cluster's details page, access various resources associated with the dedicated AI cluster by selecting their links or tabs.
Use the dedicated-ai-cluster get command and required parameters to get a dedicated cluster's details:
oci generative-ai dedicated-ai-cluster get --dedicated-ai-cluster-id <dedicated-ai-cluster-OCID> [OPTIONS]For a complete list of parameters and values for CLI commands, see the CLI Command Reference.
Run the GetDedicatedAiCluster operation to get a dedicated cluster's details.