---
title: "Get endpoint metrics [READ]"
method: POST
path: "/v2/endpoint/{namespace}/{name}/metrics"
tags: ["Metrics"]
---

# Get endpoint metrics [READ]

`POST /v2/endpoint/{namespace}/{name}/metrics`

## Path parameters

- `namespace` string, required
- `name` string, required

## Request body

- MetricsParams
  - `replicaId` string, nullable — Optionally filter by replica ID
  - `start` string, date-time, required — RFC 3339 Date Format. Ex: 2021-01-01T00:00:00Z
  - `stop` string, date-time, required — RFC 3339 Date Format. Ex: 2021-01-01T00:00:00Z

## Response `200`

Endpoint aggregated metrics returned successfully

- AllGraphs
  - `start` string, date-time, required
  - `stop` string, date-time, required
  - `timeWindowSeconds` integer, required
  - `hardwareCpu` GraphHardware, required
    - `series` SeriesHardware[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `deviceId` integer, nullable
      - `max` number, float, nullable
      - `replicaId` string, required
  - `hardwareGpu` GraphHardware, required
    - `series` SeriesHardware[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `deviceId` integer, nullable
      - `max` number, float, nullable
      - `replicaId` string, required
  - `hardwareGpuMem` GraphHardware, required
    - `series` SeriesHardware[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `deviceId` integer, nullable
      - `max` number, float, nullable
      - `replicaId` string, required
  - `hardwareMem` GraphHardware, required
    - `series` SeriesHardware[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `deviceId` integer, nullable
      - `max` number, float, nullable
      - `replicaId` string, required
  - `pendingRequest` GraphPendingRequest, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `series` SeriesPendingRequest[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `status` string, required
  - `replicaIds` string[], required
  - `replicasRunning` GraphReplicasRunning, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `series` SeriesReplicasRunning[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `max` number, float, nullable
      - `status` string, required
  - `replicasStatus` GraphReplicasStatus, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `replicaIds` string[], required
    - `series` SeriesReplicasStatus[], required
      - `data` DataRange[], required
        - `x` string, date-time, required
        - `x2` string, date-time, required
        - `y` string, required
      - `stage` string, required
  - `responseElapsed` GraphElapsed, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `series` SeriesElapsed[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `percentile` string, required
      - `summary` number, float, nullable
  - `responseStatusCode` GraphStatusCode, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `series` SeriesStatusCode[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `statusCode` string, required
      - `sum` number, float, required
  - `responseStatusCodeGrouped` GraphStatusCode, required
    - `start` string, date-time, required
    - `stop` string, date-time, required
    - `timeWindowSeconds` integer, required
    - `series` SeriesStatusCode[], required
      - `data` DataPoint[], required
        - `x` string, date-time, required
        - `y` number, float, required
      - `statusCode` string, required
      - `sum` number, float, required
  - `vllm` GraphsVllm
    - `itl` GraphHardware, required
      - `series` SeriesHardware[], required
        - `data` DataPoint[], required
          - `x` string, date-time, required
          - `y` number, float, required
        - `deviceId` integer, nullable
        - `max` number, float, nullable
        - `replicaId` string, required
    - `kvCache` GraphHardware, required
      - `series` SeriesHardware[], required
        - `data` DataPoint[], required
          - `x` string, date-time, required
          - `y` number, float, required
        - `deviceId` integer, nullable
        - `max` number, float, nullable
        - `replicaId` string, required
    - `prefixCache` GraphHardware, required
      - `series` SeriesHardware[], required
        - `data` DataPoint[], required
          - `x` string, date-time, required
          - `y` number, float, required
        - `deviceId` integer, nullable
        - `max` number, float, nullable
        - `replicaId` string, required
    - `requests` GraphVllmRequests, required
      - `start` string, date-time, required
      - `stop` string, date-time, required
      - `timeWindowSeconds` integer, required
      - `running` GraphHardware, required
        - `series` SeriesHardware[], required
          - `data` DataPoint[], required
            - `x` string, date-time, required
            - `y` number, float, required
          - `deviceId` integer, nullable
          - `max` number, float, nullable
          - `replicaId` string, required
      - `waiting` GraphHardware, required
        - `series` SeriesHardware[], required
          - `data` DataPoint[], required
            - `x` string, date-time, required
            - `y` number, float, required
          - `deviceId` integer, nullable
          - `max` number, float, nullable
          - `replicaId` string, required
    - `ttft` GraphHardware, required
      - `series` SeriesHardware[], required
        - `data` DataPoint[], required
          - `x` string, date-time, required
          - `y` number, float, required
        - `deviceId` integer, nullable
        - `max` number, float, nullable
        - `replicaId` string, required

---

[API](https://skmtc.net/huggingface/apis/hf-inference-endpoints-api.md) · [All operations](https://skmtc.net/huggingface/apis/hf-inference-endpoints-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/huggingface/hf-inference-endpoints-api/versions/52e3f4cdbf86/schema)
