LLMgateway Kimi AI Gateway Benchmarks
Kimi AI Gateway Benchmarks
Last benchmarked August 21, 2026
Request Latency
Cold E2E
1374ms
Median
Warm TTFT
2585ms
Median
Tokens/sec
34
Median
DNS
19.3ms
Median
TCP
1.7ms
Median
TLS
5.2ms
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.
DNS19.3ms
TCP1.7ms
TLS5.2ms
To First Byte125.0ms
First Byte → Token1196.4ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Partners