Gemini AI Gateway Benchmark
Request Latency
Cold E2E
2045ms
Median
Warm TTFT
1858ms
Median
Tokens/sec
94
Median
DNS
1.1ms
Median
TCP
14.1ms
Median
TLS
29.4ms
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.
DNS1.1ms
TCP14.1ms
TLS29.4ms
To First Byte1924.4ms
First Byte → Token0.2ms
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.