Gemini AI Gateway Benchmark
Request Latency
BaselineNo gateway involved — a direct call to Anthropic's API, used as the no-gateway control every other provider is compared against.
Cold E2E
2125ms
Median
Warm TTFT
2020ms
Median
Tokens/sec
94
Median
DNS
1.1ms
Median
TCP
1.5ms
Median
TLS
4.7ms
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
TCP1.5ms
TLS4.7ms
To First Byte2106.1ms
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.