OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
622ms
Median
Warm TTFT
573ms
Median
Tokens/sec
53
Median
DNS
1.7ms
Median
TCP
0.9ms
Median
TLS
6.7ms
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.
DNS1.7ms
TCP0.9ms
TLS6.7ms
To First Byte386.3ms
First Byte → Token214.7ms
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.