Replace bare metal GPU cluster server
Delete a server from the cluster and provision a new one in its place, maintaining the cluster size. Uses the current cluster configuration (image, SSH key, network settings) for the new server.
By default the replacement keeps the original Public/Private IPs (ethernet only).
Set keep_ip_addresses=false for fresh IPs.
Authorizations
API key for authentication. Make sure to include the word apikey, followed by a single space and then your token.
Example: apikey 1234$abcdef
Path Parameters
Project ID
1
Region ID
7
Cluster unique identifier
"1aaaab48-10d0-46d9-80cc-85209284ceb4"
Server unique identifier
"f1c1eeb6-1834-48c9-a7b0-daafce64872b"
Body
Retain the original Public/Private IPs on the replacement node (ethernet only). When false, new IPs are assigned. No effect on InfiniBand interfaces.
true
Response
OK
List of task IDs representing asynchronous operations. Use these IDs to monitor operation progress:
GET /v1/tasks/{task_id}- Check individual task status and details Poll task status until completion (FINISHED/ERROR) before proceeding with dependent operations.
["d478ae29-dedc-4869-82f0-96104425f565"]