Endpoints
Create Cluster
Create an auto-scaling cluster for the specified model.
PUT
Authorizations
Provide your API key as Key your-key-here
in the Authorization
header.
Path Parameters
The specific model to create a cluster for (e.g., gpt2
).
Body
application/json
Specify the desired capacity and timeout for the cluster.
Timeout value for the cluster.
Response
200
Cluster created successfully.