Gemini API (Google AI Studio) SLA
Google · AI models · no public SLA · SLA of Apr 28, 2026 · checked 38h ago
No public SLA, so there is no promise to test.
Incidents, last 365 days
Not enough status history yet.
Commitments and credits
The Gemini API Additional Terms of Service (last updated 2026-04-28) were read in full: they define Paid Services and data use but contain no service level, uptime percentage or service credit. For an uptime commitment on Gemini models, Google points enterprise buyers to Vertex AI, whose SLA is on file here under Google Cloud.
More in ai models
ServicePromisedFirst creditObserved 365dDowntime
Amazon BedrockAWS · AI models · Standard99.9%First credit10%Observed 365d99.178%All incidents 99.852%
Claude API (Standard tier)Anthropic · AI modelsNoneFirst creditn/aObserved 365d98.76%All incidents 94.774%
Cohere API (SaaS: Command, Embed, Rerank)Cohere · AI modelsNoneFirst creditn/aObserved 365d100%All incidents 99.986%
Vertex AI (Gemini API on Vertex)Google Cloud · AI models · Vertex AI Platform: Training, Deployment, Batch Prediction99.9%First credit10%Observed 365d100%All incidents 99.488%
Hugging Face Inference EndpointsHugging Face · AI modelsNoneFirst creditn/aObserved 365dNo feed
Terms, exclusions and sources
- Measured
- No uptime commitment published.
- Not covered
- No service level, uptime or credit clause in the Gemini API Additional Terms of Service; Google's published SLA for Gemini models is the Vertex AI one (listed under Google Cloud)
- Status history
- No public status history