Unverified50% confidenceFactExact time
For streaming responses, time to first token (TTFT) distinguishes different troubleshooting directions better than total duration; for example, returning the first token in 350 milliseconds versus only after 8 seconds represents completely different experiences and root causes.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedTime to First Token (TTFT) refers to the time interval between a user sending a request and the model outputting the first token, and is primarily constrained by the duration of the prefill stage.73% similarUnverifiedCompressing TTS time-to-first-byte latency to within 50 milliseconds means nearly imperceptible instant feedback.73% similarUnverified缓存命中时prefill阶段可跳过已缓存部分，TTFT可从数秒压缩至毫秒级70% similarUnverifiedTPOT (Time Per Output Token) refers to the average time taken to generate each subsequent token, and total response time is roughly equal to TTFT + TPOT × number of output tokens.70% similarUnverifiedA Time to First Token (TTFT) below 500ms is generally considered a smooth interactive experience, while exceeding 2 seconds creates a noticeable sense of waiting.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033757API
curl https://kongchang.com/api/v1/knowledge/claims/1033757MCP
get_claim(id=1033757)