# Is Gemini API Down? Google AI Status and Fetch Checks

TL;DR: Check whether a Gemini API failure is an outage, browser fetch issue, bad endpoint, invalid key, or runtime network problem.

Official status: https://status.cloud.google.com/
Public endpoint: https://generativelanguage.googleapis.com/v1beta/models
Run diagnosis: https://llmping.app/#diagnose

## Honest boundary

llmping does not ping user API keys and does not claim fake real-time provider status. Use the checks below to separate outage symptoms from key, quota, permission, and runtime problems.

## Historical uptime

llmping samples provider public endpoints and official status feeds every 5 minutes with a Cloudflare Worker and stores real samples in D1. The status page displays 7, 30, and 90 day public endpoint uptime once samples exist.

Uptime API: https://llmping-uptime-worker.stcatzlee.workers.dev/api/uptime?provider=gemini

## Quick checks

- fetch failed is usually a client/runtime transport issue, not a model response.
- 403 or permission errors often mean the API is not enabled or the key is restricted.
- 404 can mean the model string or endpoint method is wrong.
- Check Google Cloud status only after you separate browser CORS/runtime errors from API responses.

## cURL test command

```bash
curl -i "https://generativelanguage.googleapis.com/v1beta/models?key=$GEMINI_API_KEY"
```

## Related pages

- https://llmping.app/errors/gemini/fetch-failed/
- https://llmping.app/errors/openai/401/
- https://llmping.app/errors/claude/econnreset/