Kimi AI Gateway Benchmark
Request Latency
Cold E2E
831ms
Median
Warm TTFT
550ms
Median
Tokens/sec
147
Median
DNS
2.8ms
Median
TCP
19.9ms
Median
TLS
42.5ms
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.
DNS2.8ms
TCP19.9ms
TLS42.5ms
To First Byte639.2ms
First Byte → Token0.1ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Become a partner
Want your logo featured across our benchmarks? Become a ComputeSDK benchmark partner.