Time-to-first-token ranking: DeepSeek V4.1 Flash last 24 hours
Time from sending a request to receiving the first token, measured live over the last 24 hours. Lower is better.
Data4 routes · 4 relaysSynced 11/16/2026, 00:45:19, updated every 15 minutes
Model: DeepSeek V4.1 Flash
| Rank | Model @ relay | First token | Samples | Availability | Session cost | Data security |
|---|---|---|---|---|---|---|
| 1 | 1.31 s | 166 | 98.2% | ¥2.59 | 4 | |
| 2 | 1.87 s | 47 | 57.5% | — | 4 | |
| 3 | 2.12 s | 47 | 100.0% | — | 0 | |
| 4 | 3.04 s | 46 | 87.0% | — | 0 |
FAQ
How is time to first token measured?
Time from sending a request to receiving the first token, measured live over the last 24 hours. Lower is better.
Why does the same relay appear more than once?
Each row is one “model @ relay” route. Different models and groups at the same relay can perform very differently, so they are ranked separately.