v1

latestOpenAPI 3.1.02026-07-26101317.6 KB

Endpoints

Scale Endpoint Replicas

Scale the number of replicas for an active endpoint. Autoscaling must be disabled.

post/endpoints/{endpoint_id}/scale

Path parameters

endpoint_idstring required

Unique endpoint ID.

Request body

num_replicasinteger required

Desired number of replicas (1-100).

Example request

{
  "num_replicas": 3
}

Response

Scale result.

endpoint_idstring

Unique endpoint ID.

previous_replicasinteger

Replica count before scaling.

current_replicasinteger

Replica count after scaling.

messagestring

Result message.

Example response

{
  "endpoint_id": "51c910f7-ecde-4c6c-88f8-d8e37ca9d598",
  "previous_replicas": 1,
  "current_replicas": 3,
  "message": "Successfully scaled from 1 to 3 replicas"
}