Kimi AI Gateway Benchmark
Request Latency
Cold E2E
923ms
Median
Warm TTFT
648ms
Median
Tokens/sec
90
Median
DNS
22.2ms
Median
TCP
16.0ms
Median
TLS
33.2ms
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.
DNS22.2ms
TCP16.0ms
TLS33.2ms
To First Byte721.3ms
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.