Gemini AI Gateway Benchmark
Request Latency
Cold E2E
1856ms
Median
Warm TTFT
1752ms
Median
Tokens/sec
110
Median
DNS
7.8ms
Median
TCP
1.0ms
Median
TLS
5.8ms
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.
DNS7.8ms
TCP1.0ms
TLS5.8ms
To First Byte1821.1ms
First Byte → Token4.3ms
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.