Kimi AI Gateway Benchmark
Request Latency
Cold E2E
3094ms
Median
Warm TTFT
3291ms
Median
Tokens/sec
32
Median
DNS
9.9ms
Median
TCP
1.4ms
Median
TLS
5.8ms
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.
DNS9.9ms
TCP1.4ms
TLS5.8ms
To First Byte3065.1ms
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.