Kimi AI Gateway Benchmark
Request Latency
Cold E2E
1242ms
Median
Warm TTFT
570ms
Median
Tokens/sec
108
Median
DNS
19.4ms
Median
TCP
1.6ms
Median
TLS
3.4ms
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.
DNS19.4ms
TCP1.6ms
TLS3.4ms
To First Byte1182.6ms
First Byte → Token0.7ms
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.