As of September 06, 2026, the nebius AI API responds in 100 ms p50 (edge, time-to-first-byte) from Europe (Germany) — its fastest measured region — with 100% uptime. Slowest is Asia (Tokyo) at 498 ms p50.
Is nebius down right now?
Reachable from all 4 regions
Last successful probe Sep 6, 17:15 UTC · every 5 minutes from 4 region(s) · status feed checked Sep 6, 17:17 UTC
2 isolated failure(s) in the last 72 hours, the most recent (host probes) visible from only one region (Asia (Tokyo)). A single-region failure cannot be separated from a problem on that network path, so it is not called an outage. Measured from outside nebius’s own network, independently of its status page; full log: measured AI API incidents.
Real requests: not measured for nebius — 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.
nebius’s status page lists no open incident (checked Sep 6, 17:17 UTC).
Edge latency, 24 h
100 ms
p50 from Europe (Germany), the fastest region
Uptime, 24 h
100%
1,151 probes across 4 region(s)
Failed probes, 72 h
2
of 3,455 · Asia (Tokyo)
Reported by nebius, 72 h
0
on status.nebius.com
Was nebius down in the last 3 days?
No. 2 isolated single-region probe failure(s) were recorded, none of which meets the bar for an outage (two or more regions at once).
Asia (Tokyo) only — not an outage · under one 5-minute probe cycle · 1 failed probe(s) · timeout
Asia (Tokyo) only — not an outage · under one 5-minute probe cycle · 1 failed probe(s) · timeout
What nebius’s own status page reported
Nothing. nebius’s status page lists no incident in the last 72 hours (checked Sep 6, 17:17 UTC).
Is nebius 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 nebius API from each region?
Region
p50 TTFB
p95
Uptime
Asia (Tokyo)
498 ms
570 ms
100%
Europe (Germany)
100 ms
205 ms
100%
South America (São Paulo)
473 ms
529 ms
100%
US (Central)
239 ms
299 ms
100%
Measured from Europe (Germany), nebius responds in 100 ms; from Asia (Tokyo) the same API takes 498 ms — 5.0× 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 nebius’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
nebius’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 nebius’s
own reports are shown next to the measurements rather than folded into them.