Live status
Is Gemini down right now?
Gemini: no problems in our tests of Google's models in the last 15 minutes · official status (Google Cloud and Workspace status): no open incidents · checked
Updated . While people are reading it, this page is refreshed about once a minute.
Our tests of Google's models
We send "Reply with OK" to Gemini 3.8 Flash every 5 minutes and Gemini 3.1 Pro (preview) every 30 minutes, and time how long each takes to start answering and to finish. The verdict covers the last 15 minutes: our last three tests.
Last test
- Answered, last 15 min
- 100%
- Answered, last hour
- 100%
- Answered, last 24 h
- 100%
- Median first token, 24 h
- 1.6 s
The last 24 hours
| Model | Last 24 h | First token | Whole reply | Last test |
|---|---|---|---|---|
| Gemini 3.8 FlashEvery 5 minutes | 43 of 43 answered | 1.6 s | 1.6 s | AnsweredThrough OpenRouter, |
| Gemini 3.1 Pro (preview)Every 30 minutes | 7 of 7 answered | 2.3 s | 2.3 s | AnsweredThrough OpenRouter, |
No failed tests in the last 24 hours.
What Google's status page says
Google's own status page, read at most once a minute. It reports incidents once Google's team confirms them, so it can lag behind what users and our tests see.
From Google Cloud and Workspace status, read
- Vertex AI Gemini API (Google Cloud)Operational
- Gemini app (Google Workspace)Operational
Open incidents
None listed right now.
Resolved on Google Cloud and Workspace status in the last 14 days
None listed.
What our test covers, and what it doesn't
Our test calls Google's Gemini models through the Gemini API, as llmwise's chat uses them, directly or through OpenRouter. The Gemini app is a separate Google product on top of the same models, with its own sign-in and settings.
Each test is one message of a few words, with the reply capped at 32 tokens, tried once, with no retry and no switch to another route. A test counts as failed when the model refuses it as busy (a rate limit or "overloaded"), breaks (a server error), drops the connection, or takes more than 30 seconds. A test our own request broke doesn't count against Gemini.
What to do now
Check the two answers above. If both look fine, it's likely your browser, account or network.
Reload and start a new chat; try the other Google account you use, if any.
If you get "overloaded", wait a minute, or switch from Pro to Flash.
If Google's side is having trouble, ask another company's model for now.
Ask another model
llmwise has Claude, GPT, Grok and more in one chat, so an outage at one company doesn't stop your work. The free trial is 5 messages, with a sign-in link by email and no card.
Gemini errors, and how to fix them
The errors people see most with Gemini, what each one usually means, and what to try.
"Something went wrong" in the Gemini app
A catch-all: a server hiccup or a problem with the chat.
Reload, start a new chat, and try again. Check that you're signed in to the Google account you meant to use.
503 "The model is overloaded"
Google has no room for the model right now.
Retry after a few seconds with a growing wait between tries, or switch from Pro to a Flash model.
429 RESOURCE_EXHAUSTED
Your project used up its requests or tokens for now.
Slow down, or raise your quota in Google AI Studio or Google Cloud. It's your project's limit, not an outage.
Gemini isn't available on a work or school account
An admin setting, not an outage.
Ask your admin, or use a personal Google account. Nothing is down.
Other AI status pages
Questions
Is Gemini down for everyone, or just me?
Compare the two answers above. If our test of Gemini passes and Google's status shows no Gemini incident, it's more likely your browser, account or network. Signing in with a different Google account is a quick check: work and school accounts can have Gemini turned off by their admin.
What does "The model is overloaded" mean in Gemini?
It's Google's API saying the model is too busy right now (a 503). It passes on its own; retrying after a short wait usually works, and a Flash model is often less busy than Pro.
Which Google status pages do you read?
Google has no single status page for Gemini. Google Cloud's status covers the Vertex AI Gemini API, and Google Workspace's status covers the Gemini app for work accounts; we read both. Google AI Studio has its own status page with no public feed, so it isn't included.
What can I use while Gemini is down?
Another company's model. In llmwise Claude, GPT, and Grok are in the same chat, and the free trial is 5 messages with no card.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.