Skip to content
GitHub
Compute SDK

Product

Benchmarks

Resources

Docs Blog Become a partner

Vercel AI Gateway AI Gateway Benchmarks

Vercel AI Gateway
AI Gateway Benchmarks

Last benchmarked July 24, 2026

Request Latency

100% success
Cold E2E
831ms
Median
Warm TTFT
739ms
Median
Tokens/sec
88
Median
DNS
0.9ms
Median
TCP
5.7ms
Median
TLS
20.3ms
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
TCP5.7ms
TLS20.3ms
To First Byte775.9ms
First Byte → Token9.2ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

PartnersLatitude