/
/HF Inference Endpoints API
ChangesDocsSign in
Sign in
  • APIs
  • Generators
  • Stacks
  • Projects
  • Docs
  • History
  • Schema
Checked 8h ago · Updated 1w ago
Audit Logs1
CIDR Lists4
Custom Domains3
Endpoints17
Metrics16
  • postGet endpoint metrics [READ]
  • postGet endpoint hardware CPU and RAM [READ]
  • postGet endpoint hardware GPU and VRAM [READ]
  • postGet endpoint pending request [READ]
  • postGet endpoint replica ids [READ]
  • postGet endpoint replica running [READ]
  • postGet endpoint replica status [READ]
  • postGet endpoint response elapsed [READ]
  • postGet endpoint response status code [READ]
  • postGet endpoint response status code grouped [READ]
  • postGet endpoint vLLM inter-token latency [READ]
  • postGet endpoint vLLM KV cache usage [READ]
  • postGet endpoint vLLM prefix cache hit ratio [READ]
  • postGet endpoint vLLM requests waiting and running [READ]
  • postGet endpoint vLLM time to first token [READ]
  • getGet endpoint OpenMetrics export [READ] [PRO]
Private Services2
Providers3
    Metrics

    Get endpoint OpenMetrics export [READ] [PRO]

    get/v2/endpoint/{namespace}/{name}/open-metrics

    Path parameters

    namespacestring required

    User or organization name

    namestring required

    Endpoint name

    Response

    OpenMetrics returned successfully

    Changes

    No recorded changes to this endpoint across all 7 revisions of this API.