CREATE cluster
Create an auto-scaling cluster to run an open-source model. This call sets up concurrency, scaling behavior, and shutdown logic based on usage.
PUT
Authorizations
Set Authorization
header to Key BYTEZ_KEY
(e.g. 'Authorization': 'Key ABC123')
Path Parameters
The model you want to run (e.g., openai-community/gpt2
).
Body
application/json
Define cluster behavior using `timeout` and `capacity`
Minutes to wait before shutting down if no requests are received