ConceptReal-time Endpoint / 实时端点
Real-time Inference Endpoint
A model deployment mode in which an endpoint stays continuously online and returns predictions immediately. It suits latency-sensitive online scenarios but incurs continuously running compute costs.
Timeline (last 90 days)
Oct 12
Real-time inference endpoints stay online continuously and are suitable for latency-sensitive online scenarios, but they incur always-on compute costs; batch transform completes inference in one pass over large amounts of data stored on S3, releasing resources after the job ends, and is suitable for offline scoring or periodic prediction.
Unverified50%