Serverless Inference

Deeptrin also offers serverless inference capabilities. With this feature, you are billed based on the actual runtime of the inference service, which can significantly reduce operational costs for small to medium-sized applications or for applications with peak-and-valley API usage patterns.

1. To create a serverless inference service, go to "My Inference" page. Click "New inference" button

My Inference

1. Currently, we require users to submit a request to inform us of their serverless inference needs, and the model setup and usage are handled through offline coordination.

New Inference

A version that supports users in independently creating serverless inference models is under development and will be available soon.