latency: meaning and examples

/ˈleɪtnsi/

What does latency mean?

delay between request and response; how long you wait

Examples in context

• Latency is under 200ms.
• We optimized for low latency.
• Latency matters for real-time apps.
• We use edge deployment to cut latency.

A distinction worth remembering

Latency describes a delay. Throughput describes how much work a system handles over time. A system can have high throughput while an individual user still waits.

Usage tip

Key metric for AI APIs.

Try it yourself

Describe an application where a short response time matters more than processing many requests at once.

Explore this vocabulary topic · More words · Read current briefings