# What Is TPOT (time per output token)?

> TPOT (time per output token) is the average time taken to generate each token once output has started. TTFT measures how long before the model starts speaking, TPOT how fast it speaks; together they describe the full latency of a request.

URL: https://vuke.top/en/glossary/tpot · Updated November 12, 2026

TPOT (time per output token) is the average time taken to generate each token once output has started. TTFT measures how long before the model starts speaking, TPOT how fast it speaks; together they describe the full latency of a request.

## In the measurements

Report R3 records TTFT p50 / p90 / p99, TPOT, throughput and disk bandwidth together across nine load levels [R3](https://vuke.top/en/evidence/R3).

Source: [R3](https://vuke.top/en/evidence/R3)