OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
1226ms
Median
Warm TTFT
773ms
Median
Tokens/sec
44
Median
DNS
1.3ms
Median
TCP
86.4ms
Median
TLS
87.7ms
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.
DNS1.3ms
TCP86.4ms
TLS87.7ms
To First Byte525.1ms
First Byte → Token346.5ms
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.