Skip to content
GitHub

Product

Benchmarks Partners

Resources

Docs Blog

OpenAI (Direct) OpenAI AI Gateway Benchmarks

OpenAI (Direct)
OpenAI AI Gateway Benchmarks

Last benchmarked August 21, 2026

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

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
383ms
Median
Warm TTFT
344ms
Median
Tokens/sec
75
Median
DNS
0.8ms
Median
TCP
1.0ms
Median
TLS
2.7ms
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.

DNS0.8ms
TCP1.0ms
TLS2.7ms
To First Byte240.5ms
First Byte → Token132.2ms

Performance Over Time

Iteration Distribution

Cold E2E

Warm TTFT

Tokens/sec

DNS

TCP

TLS

PartnersLatitude