Model API status / SiliconFlow
SiliconFlow Normal
OpenAI-compatible API for an open-source model inference platform.
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 |
|---|---|---|---|
| SiliconFlow11 samples | 65 ms成功 100% | 65 ms成功 100% | 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 SiliconFlow
Is SiliconFlow working right now?
As of 10/17 19:45, api.siliconflow.cn is reachable from Cloudflare edge nodes with a response time of 1433 ms. Over the past 24 hours, reachability was 100% and median latency was 760 ms.
What is the latency to SiliconFlow 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 100%，连接复用后往返中位数 65 ms，首次连接中位数 149 ms。
How does cdnping monitor SiliconFlow?
Every 5 minutes, we send a request without an API key from Cloudflare edge nodes to https://api.siliconflow.cn/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.