The port on which the model will be exposed.

Regions

Please select a hardware

Show advanced configuration settings
The minimum number of running containers to avoid cold boots. From 0 to 3.
The maximum number of concurrent running containers. From 1 to 25.
Sec
Idle time before scaling down containers.
Sec
This is how long the autoscaling waits before deleting the pod that doesn't receive requests. The countdown starts from the last request.
Container Deployment Triggers
CPU Usage
%
GPU Usage
%
GPU Memory
%
RAM Usage
%
HTTP Requests
/sec
Environment variables

Checkout

Total
$0/ h$0/ month
Deploy