Anthropic (Direct) Anthropic AI Gateway Benchmarks

Anthropic AI Gateway Benchmarks

Last benchmarked August 21, 2026

No-gateway control — a direct call to Anthropic's API, used to measure how much latency each gateway adds.

Baseline

100% success

No gateway involved — a direct call to Anthropic's API, used as the no-gateway control every other provider is compared against.

Cold E2E

486ms

Median

Warm TTFT

486ms

Median

Tokens/sec

Median

DNS

0.9ms

Median

TCP

1.1ms

Median

TLS

3.2ms

Median

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

TCP1.1ms

TLS3.2ms

To First Byte473.9ms

First Byte → Token1.8ms

Partners