OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
663ms
Median
Warm TTFT
629ms
Median
Tokens/sec
49
Median
DNS
2.0ms
Median
TCP
5.7ms
Median
TLS
19.6ms
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.
DNS2.0ms
TCP5.7ms
TLS19.6ms
To First Byte595.6ms
First Byte → Token10.3ms
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.