I Was Measuring LLM Latency Wrong

For a long time, I recorded one latency number for every LLM request: latency_ms = response_finished_at - request_started_at It looked useful. I could calculate an average, add a p95 chart, and see whether a model was getting slower. But whenever a user complained that an AI feature felt slow, ...

Source: [Dev.to](https://dev.to/plasma_01/i-was-measuring-llm-latency-wrong-49h4)