Neon OpenAI AI Gateway Benchmarks
OpenAI AI Gateway Benchmarks
Last benchmarked August 21, 2026
Request Latency
Cold E2E
698ms
Median
Warm TTFT
503ms
Median
Tokens/sec
59
Median
DNS
0.8ms
Median
TCP
19.5ms
Median
TLS
40.1ms
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.
DNS0.8ms
TCP19.5ms
TLS40.1ms
To First Byte435.4ms
First Byte → Token143.7ms
Performance Over Time
Iteration Distribution
Cold E2E
Warm TTFT
Tokens/sec
DNS
TCP
TLS
Partners