Kimi AI Gateway Benchmark
Request Latency
Cold E2E
1719ms
Median
Warm TTFT
1519ms
Median
Tokens/sec
35
Median
DNS
7.3ms
Median
TCP
21.9ms
Median
TLS
24.6ms
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.
DNS7.3ms
TCP21.9ms
TLS24.6ms
To First Byte1589.9ms
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.