OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
1068ms
Median
Warm TTFT
728ms
Median
Tokens/sec
44
Median
DNS
0.7ms
Median
TCP
84.3ms
Median
TLS
85.8ms
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.
DNS0.7ms
TCP84.3ms
TLS85.8ms
To First Byte484.4ms
First Byte → Token237.5ms
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.