Kimi AI Gateway Benchmark
Request Latency
Cold E2E
1987ms
Median
Warm TTFT
1631ms
Median
Tokens/sec
34
Median
DNS
8.2ms
Median
TCP
83.8ms
Median
TLS
85.3ms
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.
DNS8.2ms
TCP83.8ms
TLS85.3ms
To First Byte1617.1ms
First Byte → Token0.0ms
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.