Deploy any model as a high-performance, low-latency micro-service with a RESTful API. Easily monitor, scale, and version deployments. Deployments take a trained model and expose them as a persistent service at a known URI.
During the Beta period, Gradient Deployments have a number of restrictions.
Teams are limited to a single running deployment.
Only K80 and CPU nodes are supported.
The exposed endpoint URI is subject to change.
Billing for deployments is not currently enabled. You will not see Gradient Deployments on your invoice.
Deployments go through a series of states. They are enumerated here: