Kimi AI Gateway Benchmark
Request Latency
Cold E2E
0ms
Median
Warm TTFT
0ms
Median
Tokens/sec
0
Median
DNS
0.0ms
Median
TCP
0.0ms
Median
TLS
0.0ms
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.
Performance Over Time
Iteration Distribution
Cold E2E
No data to display.
Warm TTFT
No data to display.
Tokens/sec
No data to display.
DNS
No data to display.
TCP
No data to display.
TLS
No data to display.
Become a partner
Want your logo featured across our benchmarks? Become a ComputeSDK benchmark partner.