OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
989ms
Median
Warm TTFT
1461ms
Median
Tokens/sec
57
Median
DNS
1.4ms
Median
TCP
1.9ms
Median
TLS
6.4ms
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.
DNS1.4ms
TCP1.9ms
TLS6.4ms
To First Byte135.5ms
First Byte → Token830.5ms
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.