Serverless Real-Time Inference

Serverless Real-Time Inference was renamed - Databricks now calls it Model Serving, as of March 2023.

Serverless Real-Time Inference → Model Serving

Highly available, low-latency service for deploying ML and GenAI models behind autoscaling REST endpoints.

• Puts a trained model behind a REST endpoint and manages the servers for you, elastically scaling capacity up under load and back down when the traffic dries up. 🔗

Category

AI / ML

In use from

2022🔗

Renamed

March 2023🔗

Verified

2026-07-18