# AI API latency, week of 03 August 2026: what actually moved

Published 2026-08-10 · covers 03 August 2026

Week of 03 August 2026: 3 different providers were fastest across the 4 regions we measure from, and 7 provider-region pairs moved by more than a quarter against the week before. Who led each region last week? Region Fastest p50 TTFB Uptime Asia (Tokyo) fireworks 16 ms 100% Europe (Germany) nscale 99 ms 100% South America (São Paulo) openrouter 58 ms 100% US (Central) fireworks 36 ms 100% What changed by more than 25%? Provider Region Week before This week Change inference-net Europe (Germany) 103 ms 198 ms +92% inference-net Asia (Tokyo) 355 ms 670 ms +89% reka US (Central) 374 ms 169 ms -55% friendli Asia (Tokyo) 295 ms 425 ms +44% hyperbolic US (Central) 217 ms 131 ms -40% inference-net US (Central) 114 ms 156 ms +37% openai Europe (Germany) 225 ms 294 ms +31%

Source: https://llmlatency.dev/blog/latency-week-2026-w32 · CC BY 4.0