Gemini AI Gateway Benchmark
Request Latency
Cold E2E
2371ms
Median
Warm TTFT
2202ms
Median
Tokens/sec
81
Median
DNS
2.3ms
Median
TCP
1.2ms
Median
TLS
7.3ms
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.
DNS2.3ms
TCP1.2ms
TLS7.3ms
To First Byte1698.8ms
First Byte → Token651.6ms
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.