OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
727ms
Median
Warm TTFT
663ms
Median
Tokens/sec
51
Median
DNS
2.4ms
Median
TCP
5.9ms
Median
TLS
21.0ms
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.
DNS2.4ms
TCP5.9ms
TLS21.0ms
To First Byte662.0ms
First Byte → Token9.0ms
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.