Kimi AI Gateway Benchmark
Want the full logs for this run?Sign up free →
Request Latency
Cold E2E
2933ms
Median
Warm TTFT
2455ms
Median
Tokens/sec
30
Median
DNS
4.5ms
Median
TCP
1.7ms
Median
TLS
6.7ms
Median
Cold Connection Breakdown
Where a fresh request's time goes: DNS lookup, TCP connect, TLS handshake, then time to first response byte, then first byte to first streamed token.
DNS4.5ms
TCP1.7ms
TLS6.7ms
To First Byte2869.5ms
First Byte → Token9.3ms