Vercel AI Gateway
Anthropic AI Gateway Benchmark

Want the full logs for this run?Sign up free →

Request Latency

100% success
Cold E2E
529ms
Median
Warm TTFT
478ms
Median
Tokens/sec
59
Median
DNS
2.2ms
Median
TCP
1.1ms
Median
TLS
7.0ms
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.

DNS2.2ms
TCP1.1ms
TLS7.0ms
To First Byte487.4ms
First Byte → Token10.5ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

PartnersGoogle Cloud Run