OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
768ms
Median
Warm TTFT
699ms
Median
Tokens/sec
54
Median
DNS
1.3ms
Median
TCP
1.8ms
Median
TLS
5.0ms
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
TCP1.8ms
TLS5.0ms
To First Byte487.9ms
First Byte → Token264.6ms
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.