Vercel AI Gateway
Anthropic AI Gateway Benchmark

Request Latency

100% success
Cold E2E
618ms
Median
Warm TTFT
542ms
Median
Tokens/sec
57
Median
DNS
2.7ms
Median
TCP
6.6ms
Median
TLS
18.5ms
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.

DNS2.7ms
TCP6.6ms
TLS18.5ms
To First Byte566.0ms
First Byte → Token10.0ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

Become a partner

Want your logo featured across our benchmarks? Become a ComputeSDK benchmark partner.

LatitudeGoogle Cloud Run
PartnersLatitude