OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
502ms
Median
Warm TTFT
452ms
Median
Tokens/sec
64
Median
DNS
1.1ms
Median
TCP
1.1ms
Median
TLS
4.2ms
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
TCP1.1ms
TLS4.2ms
To First Byte356.6ms
First Byte → Token132.8ms
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.