Promised uptime vs actual

Vendors35Services99

35 vendors · 99 services

Gemini API on Vertex AI SLA

Google Cloud · AI models · promises up to 99.5% · SLA of Jun 30, 2026 · checked 13d ago

Official SLAStatus page

No major outage in the 252 days of history: 100% observed against the 99.5% Gemini Online Inference API (generateContent / streamGenerateContent).

Last 90 days: no major outage.

Incidents, last 365 days

No incidents on file for this service.

Major outage time per month

Allowed per month: 3.6 h

Commitments and credits

99.5%
Gemini Online Inference API (generateContent / streamGenerateContent)
Gemini Online Inference API on Gemini Enterprise Agent Platform (95% for models designated for shorter availability)
Credit: below 99.5%: 10% · below 99%: 25% · below 95%: 50%
99%
Provisioned Throughput latency (Gemini 2.5 Pro/Flash/Flash-lite, global endpoint)
Monthly Latency Target Attainment (p50 TPS vs. target: 60/80/110 TPS)
Credit: below 99%: 10% · below 95%: 25% · below 90%: 50%

SLA changes

SLA page changedUnverifiedOct 23, 2026
Gemini API on Vertex AI
The SLA page text changed (5 sentences added, 5 removed); it still states 99.5% and 99%.
2 weeks agoPage

More in ai models

Missed its SLA99.9%
Amazon Bedrock
AWS promises 99.9% uptime, with a 10% credit when it misses; its status page showed 3 d of major outage in the last year.
Observed 99.178% over 365 days
No SLA
Claude API (Standard tier)
Anthropic publishes no SLA for it; its status page showed 4.4 d of major outage in the last year.
Observed 98.805% over 365 days
Missed its SLA99.5%
Claude API Priority Tier
Anthropic promises 99.5% uptime; its status page showed 4.3 d of major outage in the last year.
Observed 98.809% over 365 days
No SLA
Claude Enterprise (claude.ai)
Anthropic publishes no SLA for it; its status page showed 4.5 d of major outage in the last year.
Observed 98.757% over 365 days
No SLA
Cohere API (SaaS: Command, Embed, Rerank)
Cohere publishes no SLA for it; its status page showed no major outage in the last year.
Observed 100% over 365 days
No SLA
Cohere private deployments / Model Vault / North
Cohere publishes no SLA for it; its status history is still building.
No SLA
Gemini API (Google AI Studio)
Google publishes no SLA for it; its status page has no history this site can read.
Kept its SLA99.9%
Vertex AI Platform (training, prediction, pipelines)
Google Cloud promises 99.9% uptime, with a 10% credit when it misses; its status page showed no major outage in the 252 days on file.
Observed 100% over 365 days
Terms, exclusions and sources
Measured
Calendar month per Project; Downtime = more than 5% server-side 5xx Error Rate over 5+ consecutive minutes
Credit cap
50% of the amount due for the Covered Service for the month
Claim window
Within 30 days from the time Customer becomes eligible
How to claim
Notify Google technical support; provide log files/identifying info showing Downtime Periods and when they occurred
Not covered
Features designated pre-general availability; Features excluded from the SLA in the Documentation; Errors caused by factors outside Google's reasonable control; Errors from Customer's or third-party software or hardware; Requests using Grounding with Google Search; Deadlines set shorter than the server default (deadline_exceeded)
Status history
Status history since Feb 27, 2026
Weighted uptime
All incidents, weighted: 99.467% · Downtime
generateContent and streamGenerateContent methods of Gemini Online Inference API on Gemini Enterprise Agent Platform 99.5%* ... 99.0% - < 99.5% 10% 95.0% - < 99.0% 25% < 95.0% 50%
Google Cloud, Last modified June 30, 2026. Read the SLA

Product renamed on the SLA page to 'Gemini Online Inference API on Gemini Enterprise Agent Platform'. The latency tier's uptime field holds the 99% latency attainment, not availability. The Vertex AI Platform (training, prediction, pipelines) has its own SLA page and is listed as its own service.

All Google Cloud SLAsHow this is measured