OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
1098ms
Median
Warm TTFT
694ms
Median
Tokens/sec
48
Median
DNS
2.4ms
Median
TCP
1.5ms
Median
TLS
7.8ms
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
TCP1.5ms
TLS7.8ms
To First Byte737.0ms
First Byte → Token337.5ms
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.