04 · How Models Run
TTFT
Time To First Token
How long after you hit enter before the first word appears. A core latency metric — low TTFT feels responsive.
Concrete example
The pause before a chatbot starts typing back at you.
Time To First Token
How long after you hit enter before the first word appears. A core latency metric — low TTFT feels responsive.
The pause before a chatbot starts typing back at you.