Kimi AI Gateway Benchmark
Request Latency
Cold E2E
3897ms
Median
Warm TTFT
3397ms
Median
Tokens/sec
34
Median
DNS
65.5ms
Median
TCP
76.3ms
Median
TLS
154.4ms
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.
DNS65.5ms
TCP76.3ms
TLS154.4ms
To First Byte3318.9ms
First Byte → Token0.2ms
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.