Time to First Token
Median seconds until the first output token.
Time to First Token measures perceived responsiveness for streamed responses. Artificial Analysis defines it as the time from request submission to the first received token, with lower values ranking better in this app.
Test type: Hosted endpoint latency measurement. Lower values mean the response starts sooner.
Coverage
314 models have this metric.
0.16s
Current leader: Command A+
Project links
Values come from the current Artificial Analysis performance dataset, read from Supabase when configured.
Top TTFT Models
Top models ranked by TTFT.
Leaderboard
| Rank | Model | Creator | Value | Speed | Blended Price |
|---|---|---|---|---|---|
| #1 | Command A+ | Cohere | 0.16s | 191 tok/s | - |
| #2 |
