OpenAI AI Gateway Benchmark

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

Request Latency

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

553ms

Median

Warm TTFT

522ms

Median

Tokens/sec

Median

DNS

0.6ms

Median

TCP

1.0ms

Median

TLS

3.9ms

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.

DNS0.6ms

TCP1.0ms

TLS3.9ms

To First Byte305.5ms

First Byte → Token234.5ms