Kimi AI Gateway Benchmark
Request Latency
BaselineNo gateway involved — a direct call to Anthropic's API, used as the no-gateway control every other provider is compared against.
Cold E2E
4708ms
Median
Warm TTFT
3086ms
Median
Tokens/sec
32
Median
DNS
24.6ms
Median
TCP
1.1ms
Median
TLS
6.5ms
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.
DNS24.6ms
TCP1.1ms
TLS6.5ms
To First Byte4650.3ms
First Byte → Token0.1ms
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.