glm — AI API latency & reliability by region

Edge latency and uptime of the glm API measured from each region, updated automatically.

Regionp50 TTFBp95Uptime
Asia (Tokyo)361 ms386 ms100%
Europe (Germany)804 ms1301 ms100%
South America (São Paulo)649 ms662 ms100%
US (Central)397 ms417 ms100%

Latency over time (p50, by region)

glm p50 latency over time (ms), by region0514102807-23 14:0007-23 15:0007-23 15:00Asia (Tokyo)Europe (Germany)South America (São Paulo)US (Central)