OpenAI AI Gateway Benchmark
Request Latency
Cold E2E
521ms
Median
Warm TTFT
484ms
Median
Tokens/sec
56
Median
DNS
2.6ms
Median
TCP
1.1ms
Median
TLS
4.0ms
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.
DNS2.6ms
TCP1.1ms
TLS4.0ms
To First Byte348.0ms
First Byte → Token155.2ms
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.