Gemini AI Gateway Benchmark
Request Latency
Cold E2E
989ms
Median
Warm TTFT
966ms
Median
Tokens/sec
38
Median
DNS
1.9ms
Median
TCP
1.5ms
Median
TLS
3.9ms
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.
DNS1.9ms
TCP1.5ms
TLS3.9ms
To First Byte927.8ms
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.