LLMgateway Gemini AI Gateway Benchmarks
Gemini AI Gateway Benchmarks
Last benchmarked August 21, 2026
Request Latency
Cold E2E
2028ms
Median
Warm TTFT
1870ms
Median
Tokens/sec
101
Median
DNS
0.9ms
Median
TCP
1.7ms
Median
TLS
5.5ms
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.
DNS0.9ms
TCP1.7ms
TLS5.5ms
To First Byte102.6ms
First Byte → Token1897.0ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Partners