Kimi AI Gateway Benchmark
Request Latency
Cold E2E
3074ms
Median
Warm TTFT
3369ms
Median
Tokens/sec
32
Median
DNS
20.6ms
Median
TCP
3.4ms
Median
TLS
13.4ms
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.
DNS20.6ms
TCP3.4ms
TLS13.4ms
To First Byte2949.3ms
First Byte → Token14.3ms
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.