OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
896ms
Median
Warm TTFT
714ms
Median
Tokens/sec
48
Median
DNS
1.2ms
Median
TCP
15.0ms
Median
TLS
32.3ms
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.
DNS1.2ms
TCP15.0ms
TLS32.3ms
To First Byte514.1ms
First Byte → Token285.3ms
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.