- In short
- P95 latency is the value below which 95% of requests complete, making it a more useful design target than the median because SLA breaches are driven by the slower requests at the tail, not the typical one. A demo tested one request at a time will not reveal p95 latency under concurrent production load. Latency is driven by task complexity, model size, and output length, while volume alone primarily pressures cost rather than latency at moderate request rates.
Full concept guide coming soon
We are building the in-depth, exam-aligned guide for this knowledge point. In the meantime, explore the prerequisites and related concepts below, watch the official Anthropic Academy lessons, and start an adaptive study session to master it with Archie.
Watch and learn
Official Anthropic Academy lessons first, then hand-picked walkthroughs. Videos load only when you press play.
No videos curated for this concept yet
We are still curating the best official and community videos for this topic.
References & primary sources
Adaptive study
Master this concept with Archie
Practice it inside an adaptive study session. Archie, your Socratic AI tutor, tracks your mastery with Bayesian Knowledge Tracing and schedules the perfect next review.