LLMgateway
Anthropic AI Gateway Benchmark

Request Latency

100% success
Cold E2E
801ms
Median
Warm TTFT
759ms
Median
Tokens/sec
46
Median
DNS
1.2ms
Median
TCP
1.7ms
Median
TLS
6.1ms
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
TCP1.7ms
TLS6.1ms
To First Byte152.8ms
First Byte → Token629.8ms

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