As of September 07, 2026, the glm AI API responds in 93 ms p50 (edge, time-to-first-byte) from Asia (Tokyo) — its fastest measured region — with 100% uptime. Slowest is South America (São Paulo) at 548 ms p50.
Is glm down right now?
Reachable from all 4 regions
Last successful probe Sep 7, 05:47 UTC · every 5 minutes from 4 region(s)
Every probe from every region reached the glm API successfully in the last 72 hours. Measured from outside glm’s own network, independently of its status page; full log: measured AI API incidents.
Real requests: not measured for glm — only the API host is probed here, so errors limited to specific models are invisible to these probes. That is exactly what a status page tends to report, hence the line below.
glm publishes no machine-readable status page, so there is nothing to cross-check against.
Edge latency, 24 h
93 ms
p50 from Asia (Tokyo), the fastest region
Uptime, 24 h
100%
1,153 probes across 4 region(s)
Failed probes, 72 h
0
of 3,455 probes, all regions
Reported by glm, 72 h
—
no machine-readable status page
Was glm down in the last 3 days?
No. All 3,455 probes from 4 region(s) reached the glm API in the last 72 hours.
What glm’s own status page reported
glm publishes no machine-readable status page, so there is nothing to set against the measurements above.
Is glm getting faster or slower?
hourly p50 latencyall probes succeededsome probes failedhalf or more failedno data
One panel per region: the line is the hourly p50 edge latency (shared scale, ms), the strip beneath it is the outcome of that hour’s host probes. Hover any hour for the numbers. Flat is good; a rising line means the endpoint is slowing down from that origin, a gap means no probe succeeded in that hour.
How fast is the glm API from each region?
Region
p50 TTFB
p95
Uptime
Asia (Tokyo)
93 ms
128 ms
100%
Europe (Germany)
199 ms
303 ms
100%
South America (São Paulo)
548 ms
709 ms
100%
US (Central)
263 ms
425 ms
100%
Measured from Asia (Tokyo), glm responds in 93 ms; from South America (São Paulo) the same API takes 548 ms — 5.9× longer for an identical request. That difference is the network path, not the model, and it applies to every call you make.
What is actually being measured here?
A probe in each region opens a real connection to glm’s own API host every five
minutes and times DNS resolution, the TCP handshake, the TLS handshake and the first byte of the
response. Nothing is routed through a gateway or aggregator, so these figures describe
glm’s infrastructure rather than a reseller’s. Uptime counts a probe as failed only when the
service genuinely fails — a 401 from an unauthenticated probe means the endpoint answered
correctly and is counted as up.
What this page does not tell you
These are edge latency numbers: the time before the model begins generating. They
say nothing about answer quality, throughput, price, or how long a full completion takes — those
depend on the model you call. Edge latency matters because it is unavoidable: it is paid on every
request, before a single token exists, and no prompt engineering removes it. Where an API key is
available, inference time-to-first-token is measured separately and shown on the region pages with the
model named next to the figure. Likewise, an unauthenticated probe cannot see errors that hit only some
models or some accounts — the kind a status page usually reports — which is why glm’s
own reports are shown next to the measurements rather than folded into them.