The pause before a served model’s first word appears, while it reads the whole prompt at once. Chapter 14.
From The AI Compute Race. Read the book
Where the book uses it
- Chapter 14 — The Convergence
One campus, Meta’s Hyperion, run through four possible futures to show how science, power, money and permission meet in the price of an accelerator-hour.
Related terms
From the glossary of The AI Compute Race.
How to cite this page
Dryburgh, Lee S. “Time to first token.” In The AI Compute Race. DRYBURGH. https://dryburgh.com/vol1/glossary/time-to-first-token (accessed 2026-11-01).
BibTeX
@misc{dryburgh-time-to-first-token-2026,
author = {Dryburgh, Lee S.},
title = {{Time to first token}},
howpublished = {In \emph{The AI Compute Race}, DRYBURGH},
year = {2026},
url = {https://dryburgh.com/vol1/glossary/time-to-first-token},
note = {Accessed 2026-11-01}
}