Get an endpoint's traffic and latency metrics
One step with Hugging Face. We can help you get access.
Look something up
Get an endpoint's traffic and latency metrics
with Hugging Face · Artificial Intelligence Management
Use Hugging Face: its Hugging Face Inference Endpoints API lets you get an endpoint's traffic and latency metrics in a single step (GET /endpoint/{namespace}/{endpoint_name}/metrics). capabilities.work can help you get signed up and connected.
- How many requests is my endpoint handling, and what are its latencies?
- Can I check the error rate of an Inference Endpoint?
Say it to your AI assistant
- Get performance metrics for endpoint {endpoint_name} in {namespace}.
- Show request counts, latency and errors for {endpoint_name} under {namespace}.
For your developer
GET /endpoint/{namespace}/{endpoint_name}/metrics in Hugging Face Inference Endpoints API. Full spec on APIs.io.