Concentrate AI Kimi AI Gateway Benchmarks
Kimi AI Gateway Benchmarks
Last benchmarked August 21, 2026
Request Latency
Cold E2E
1425ms
Median
Warm TTFT
2598ms
Median
Tokens/sec
34
Median
DNS
12.4ms
Median
TCP
1.1ms
Median
TLS
5.0ms
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.
DNS12.4ms
TCP1.1ms
TLS5.0ms
To First Byte1387.9ms
First Byte → Token0.1ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Partners