Kimi AI Gateway Benchmark
Want the full logs for this run?Sign up free →
Request Latency
Cold E2E
3140ms
Median
Warm TTFT
2474ms
Median
Tokens/sec
30
Median
DNS
3.7ms
Median
TCP
1.3ms
Median
TLS
5.0ms
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.
DNS3.7ms
TCP1.3ms
TLS5.0ms
To First Byte3119.1ms
First Byte → Token0.5ms