Skip to main content
POST
Tear down a cluster
See Tear down the cluster and confirm for how to verify completion. CLI equivalent, after ornn login:

Authorizations

Authorization
string
header
required

Create an organization API key in Account Settings > Developer. Do not send this key to the Kubernetes API server.

Path Parameters

controller_id
string<uuid>
required

Cluster id returned by create or list; not a reservation ID.

Response

Teardown accepted, or already in progress. Poll for completion. Reservation billing continues.

id
string<uuid>
required
state
string
required
kind
string
organization_id
string<uuid> | null
access_mode
string
network_mode
string
endpoint
string | null
credential_state
string
namespace
string | null

The namespace Ornn configures for your workloads.

node_count
integer

Workers attached when this response was built; usually 0 right after a launch.

gpu_count
integer

GPUs on the workers counted in node_count.

progress
object | null

Stages of the latest launch or teardown. Launch stages are create_plane, prepare_hosts, join_workers, apply_plane, and issue_access. Teardown stages include workers and the control-plane stage (namespace for Kubernetes, stack for Slurm), plus nodes or storage when those steps fail.

created_at
string<date-time>
updated_at
string<date-time>