Kimi AI Gateway Benchmark
Request Latency
Cold E2E
3299ms
Median
Warm TTFT
3208ms
Median
Tokens/sec
32
Median
DNS
36.5ms
Median
TCP
84.5ms
Median
TLS
85.9ms
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.
DNS36.5ms
TCP84.5ms
TLS85.9ms
To First Byte2904.8ms
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.