OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
600ms
Median
Warm TTFT
534ms
Median
Tokens/sec
53
Median
DNS
1.1ms
Median
TCP
1.5ms
Median
TLS
5.3ms
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.
DNS1.1ms
TCP1.5ms
TLS5.3ms
To First Byte361.0ms
First Byte → Token222.3ms
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.