Time to publish
Time until the first token the user can see. Later than time to first token when the model first generates hidden steps such as a plan.
Interview questions about Time to publish
- Server logs show a TTFT of 80 ms, yet users of your reasoning assistant say it takes seconds to start answering. Explain the gap.
TTFT counts the first generated token; the user waits for the first visible one, after every hidden plan or reasoning token, plus any tool calls.