All providers · Provider record

As of Jun 9, 21:59 UTC · revalidates every 60 seconds · pipeline ingests every 5 minutes.

Impact-weighted uptime

Google AI published 0.2 incidents per 30 days on average to its status feed across the last 6 months (n=1). We surface this number instead of classifying providers because uptime feeds vary in publishing volume for reasons we cannot judge from outside; compare the uptime numbers below across providers with this denominator in mind.

7 days
100.00%
n=0 live
30 days
100.00%
n=0 live
90 days
100.00%
n=0 live

Uptime weighted by per-incident UIS over the window, computed from incidents this provider published to its own feed. n splits into live (observed in real time) and historical (re-derived from the provider's own archive). Not directly comparable across providers — see the feed-volume disclosure above. How this is computed.

Multi-region reachability + latency

Multi-region probe · last 30 min
3/3 reachable
iad · Washington DC
83 ms
HTTP 200 · 14 min ago
sfo · San Francisco
77 ms
HTTP 200 · 7 min ago
fra · Frankfurt
100 ms
HTTP 200 · 4 min ago

Probes hit the provider's status page from each region every 15 minutes. Per-region latency variance is a signal worth watching even when the provider's own status feed reports operational. When ≥1 region reports unreachable while ≥1 other reports reachable, the disagreement also feeds the §6.1 multi-source confirmation gate.

Published SLA compliance

SLA verdict
MET+0.10 pp
Published target
99.90%
Our measurement (30d)
100.00%

Published SLA: 99.90% · Vertex AI Online Prediction, monthly · source (cloud.google.com) →

Computed by comparing our impact-weighted uptime against the provider's own published target. We are not making a cross-provider claim here — each provider is held to its own commitment. Measurement methodology is the same impact-weighted formula used elsewhere on this page.

Component classification · 7 rules

primary inference3 rules
auxiliary1 rule
secondary api3 rules

Components classified by class (primary inference, secondary API, auxiliary). Flagship models tracked: 3.

Latency probe · parallel-run, methodology v1.0

gemini-2.0-flash
probe latency · last 24h p95
no data
current 15m p95
7d baseline p95
no data
0 buckets · σ no data
Δ vs baseline
no data
drift state
no data
methodology v1.0 §4.10 · parallel-run · latency is not used in UIS or auto-posts

Alt-signal observations · last 24 hours

Unconfirmed signal observations from the last 1440 minutes. None are published incidents; they corroborate confirmed incidents and feed the multi-source gate. Single-source signal is intentionally not auto-posted.

Per-model community reports · last 24 hours

No flagship-model mentions in the last 24 hours.

Per-model claims are gated: published only when the provider names the model OR at least two GitHub SDK issues name it with an HTTP 5xx pattern within 30 minutes. Other mentions are surfaced as community reports without a per-model claim.

Incident history

UISTitleComponentsStarted (UTC)DurationStatusConf.
78Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint.historical recordAgent Assist, Dialogflow CX +12026-02-27 12:371h 58mresolvedhistorical
100We are investigating elevated error rates with multiple products in us-east1historical recordDialogflow CX, Vertex AI Online Prediction2025-07-18 14:422h 5mresolvedhistorical
100Multiple GCP products are experiencing Service issues.historical recordAgent Assist, Dialogflow CX +72025-06-12 17:517h 27mresolvedhistorical