Email me

Status / Gemini API

Live status · AI model API (Google AI Studio) · checked every 5 minutes

Is Gemini API down?

UpNo. Gemini API is up.

Last check from Washington, D.C. Google publishes Gemini API status at aistudio.google.com/status, a page with no public JSON feed, so our state comes from our own checks.

Failing for you while it is up here? Check whether it is you. Down? What to do now.

100%uptime, 24 hours
100%uptime, 7 days
100%uptime, 30 days
142 mstypical response, 24 hours (slowest 5%: 291 ms)

Uptime counts from Oct 24, 2026, when we started checking. Response time is time to the first byte from Washington, D.C.

What works right now

  • UpAPI front doorYes: generativelanguage.googleapis.com is answering requests.403 in 187 ms

Failing for you? Check whether it is you

  1. Is it you?

    429 RESOURCE_EXHAUSTED is your rate limit or quota. 503 UNAVAILABLE ("the model is overloaded") and 500 INTERNAL are on Google's side. 400 and 403 are the request or the key.

What to do while Gemini API is down

When Gemini API is down, requests to generativelanguage.googleapis.com (Google AI Studio keys) fail. Gemini on Vertex AI is a separate endpoint with separate capacity.

  1. Retry with backoff, or switch model size

    Capacity is per model: when a Pro model is overloaded, a Flash model often is not.

  2. Move to Vertex AI

    The Google Gen AI SDK talks to both. Vertex AI uses your Google Cloud project, quotas and billing instead of the AI Studio key.

    from google import genai
    client = genai.Client(vertexai=True, project="your-project", location="us-central1")
  3. Fail over to another provider

    Find a similar-price model on our price table and check its features on the model reference.

Last 24 hours

Loading the live chart...

Last 30 days

Loading...

Incident timeline

Outages our checks saw, and incidents from the official status page, newest first.

  1. No incidents recorded yet.

    Failed checks and official incidents will show here as they happen.

Official status

The official page: https://aistudio.google.com/status (it publishes no machine-readable feed).

This provider publishes no machine-readable status, so we rely on our checks.

Get alerts, or show it in your README

Follow the RSS feed of Gemini API incidents in any reader, or paste this badge into a README; it updates itself.

Live Gemini API status badge
[![Gemini API status](https://tensorust-status.vercel.app/api/badge?id=gemini-api)](https://tensorust.com/status/gemini-api/)

How we check Gemini API

Every 5 minutes, from Washington, D.C., with no API key. A failed check is retried once after 2 seconds before it counts; Gemini API is down when every critical check fails, and degraded when some do or the official page reports a problem.

  • https://generativelanguage.googleapis.com/v1beta/models: generativelanguage.googleapis.com answering (403 without a key is the healthy reply).

Other services

Up next

Next for you: While you wait, or for when it is back.Is OpenAI API down?Live OpenAI API status, uptime and what to do while it is down.Read it next →

Get the receipts by email.

What my AI agents tried this week, with the real numbers: what worked, what flopped, what made money. One email when there is something worth reading.

No spam, never sold. Every email has a one-click unsubscribe.

Did this answer your question?

Popular in the shop

All 124 tools →

Browse: Bundles and kitsHome, family and schoolMoney and businessAI toolsSports and fitnessMaking and hobbiesFood and drinkIndie dev and launchTrading and quant

Free: Landing page teardown iPhone app cost calculator LLM API cost calculator Paid online: $49 Launch Check App builds Articles FAQ