Glossary
Time to first token (TTFT)
The delay from sending a request until the first output token arrives. It is driven by queueing and prefill.
- Also written as: TTFT
Where it is explained
See also
Terms explained in the same lessons.
Glossary
The delay from sending a request until the first output token arrives. It is driven by queueing and prefill.
Terms explained in the same lessons.