Traffic is steady and needs low latency. Which option fits?
Why A is the answer
A real-time endpoint
Real-time endpoints serve persistent, low-latency traffic.
In detail
- A real-time endpoint suits steady, low-latency traffic.
- It runs all the time, so it is billed all the time.
Use case
An illustrative scenario, not a real incident.
A recommendation API has steady traffic and tight latency needs, so it uses a real-time endpoint.
See it in different ways
flowchart TD
A{"Traffic pattern"} -->|"Steady, low latency"| B["Real-time endpoint"]
A -->|"Sporadic, idle gaps"| C["Serverless inference"]
A -->|"Long jobs, large payloads"| D["Asynchronous inference"]
A -->|"A whole dataset offline"| E["Batch transform"]stateDiagram-v2 [*] --> Traffic Traffic --> RealTime: steady and low latency Traffic --> Serverless: sporadic, cold starts are fine Traffic --> Asynchronous: large payloads, long runs Traffic --> BatchTransform: a whole dataset
sequenceDiagram participant P0 as App participant P1 as Real-time endpoint P0->>P1: Request P1-->>P0: Prediction in milliseconds
Key point: Real-time endpoints serve steady, low-latency traffic.
Why the other options are wrong
- B. Batch transform
- Batch has high latency.
- C. A nightly processing job
- A nightly job has high latency.
- D. A notebook run by hand
- A manual run is not a service.