Model API status / Google
Gemini API Normal
The Gemini model API from Google AI Studio, served through Google's global front-end network.
Probed from Cloudflare edge DFW · updated 1 min ago (10/17 19:45)
Past 24 hours Hourly median latency. Red marks hours with failures
Past 30 days One cell per day. Hover for details
Measured in mainland China
By carrier
| API | All | China Unicom | Mobile |
|---|---|---|---|
| Gemini API11 samples | 102 ms成功 9% | 102 ms成功 11% | Insufficient samples |
Values are the median round-trip time over a reused connection. “Success” is the share of requests that received a response within 6 seconds.
FAQ
About Gemini API
Is the Gemini API working right now?
As of 10/17 19:45, generativelanguage.googleapis.com is reachable from Cloudflare edge nodes with a response time of 33 ms. Over the past 24 hours, reachability was 100% and median latency was 65 ms.
What is the latency to the Gemini API from mainland China?
过去 7 天中国大陆访客共测得 11 个样本，请求成功率 9%，连接复用后往返中位数 102 ms，首次连接中位数 282 ms。
How does cdnping monitor the Gemini API?
Every 5 minutes, we send a request without an API key from Cloudflare edge nodes to https://generativelanguage.googleapis.com/v1beta/models. Any status code below 5xx, such as 401, counts as reachable. We record the time from sending the request to receiving the response headers. See the methodology page for details.