OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
640ms
Median
Warm TTFT
516ms
Median
Tokens/sec
54
Median
DNS
0.8ms
Median
TCP
19.1ms
Median
TLS
21.3ms
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.
DNS0.8ms
TCP19.1ms
TLS21.3ms
To First Byte334.9ms
First Byte → Token223.7ms
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.