Concentrate AI
Anthropic AI Gateway Benchmark

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

Request Latency

100% success
Cold E2E
626ms
Median
Warm TTFT
496ms
Median
Tokens/sec
58
Median
DNS
1.2ms
Median
TCP
1.0ms
Median
TLS
8.4ms
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.

DNS1.2ms
TCP1.0ms
TLS8.4ms
To First Byte605.2ms
First Byte → Token0.1ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

PartnersGoogle Cloud Run