Kimi AI Gateway Benchmark
Request Latency
Cold E2E
1693ms
Median
Warm TTFT
1778ms
Median
Tokens/sec
35
Median
DNS
2.7ms
Median
TCP
6.3ms
Median
TLS
19.8ms
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.
DNS2.7ms
TCP6.3ms
TLS19.8ms
To First Byte1638.4ms
First Byte → Token8.6ms
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.