Gemini AI Gateway Benchmark
Request Latency
Cold E2E
2114ms
Median
Warm TTFT
2003ms
Median
Tokens/sec
96
Median
DNS
3.3ms
Median
TCP
6.4ms
Median
TLS
19.4ms
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.
DNS3.3ms
TCP6.4ms
TLS19.4ms
To First Byte2037.0ms
First Byte → Token17.2ms
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.