Model API status / xAI
xAI API Normal
The official API for Grok models.
Probed from Cloudflare edge DFW · updated 2 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 |
|---|---|---|---|
| xAI API11 samples | 269 ms成功 9% | 269 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 xAI API
Is the xAI API working right now?
As of 10/17 19:45, api.x.ai is reachable from Cloudflare edge nodes with a response time of 53 ms. Over the past 24 hours, reachability was 100% and median latency was 44 ms.
What is the latency to the xAI 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 269 ms，首次连接中位数 685 ms。
How does cdnping monitor the xAI API?
Every 5 minutes, we send a request without an API key from Cloudflare edge nodes to https://api.x.ai/v1/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.