Pydantic AI Gateway AI Gateway Benchmarks
AI Gateway Benchmarks
Last benchmarked July 24, 2026
Request Latency
Cold E2E
727ms
Median
Warm TTFT
583ms
Median
Tokens/sec
86
Median
DNS
0.9ms
Median
TCP
1.6ms
Median
TLS
4.8ms
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.
DNS0.9ms
TCP1.6ms
TLS4.8ms
To First Byte711.4ms
First Byte → Token0.8ms