Gemini AI Gateway Benchmark
Request Latency
Cold E2E
2201ms
Median
Warm TTFT
2032ms
Median
Tokens/sec
91
Median
DNS
2.9ms
Median
TCP
0.9ms
Median
TLS
7.4ms
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.
DNS2.9ms
TCP0.9ms
TLS7.4ms
To First Byte2176.4ms
First Byte → Token0.8ms
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.