Kimi AI Gateway Benchmark
Want the full logs for this run?Sign up free →
Request Latency
Cold E2E
2400ms
Median
Warm TTFT
2209ms
Median
Tokens/sec
31
Median
DNS
2.1ms
Median
TCP
1.1ms
Median
TLS
3.6ms
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.
DNS2.1ms
TCP1.1ms
TLS3.6ms
To First Byte2384.8ms
First Byte → Token1.0ms