capabilities.work

Pause an endpoint to stop compute costs

One step with Hugging Face. We can help you get access.

Get something done

Pause an endpoint to stop compute costs

with Hugging Face · Artificial Intelligence Management

Use Hugging Face: its Hugging Face Inference Endpoints API lets you pause an endpoint to stop compute costs in a single step (POST /endpoint/{namespace}/{endpoint_name}/pause). capabilities.work can help you get signed up and connected.

  • Can I stop paying for an endpoint's compute but keep its configuration for later?
  • Is there a way to put an endpoint on hold until I resume it manually?
Say it to your AI assistant
  • Pause endpoint {endpoint_name} in {namespace}.
  • Stop billing on {endpoint_name} under {namespace} by pausing it.
For your developer

POST /endpoint/{namespace}/{endpoint_name}/pause in Hugging Face Inference Endpoints API. Full spec on APIs.io.

More you can do with Hugging Face

List Inference Endpoints in a namespaceDeploy a new Inference EndpointGet an Inference Endpoint's detailsChange an endpoint's model, hardware or scalingPermanently delete an Inference EndpointResume a paused endpointScale an endpoint down to zero replicasRead an endpoint's runtime logsGet an endpoint's traffic and latency metricsGenerate an image with a chosen Hub modelComplete a prompt via the completions APIGenerate text in one response on TGI