HUhuggingface
Endpoints

List endpoints [READ]

Changed on
get/v2/endpoint/{namespace}

Request

  • Base URL
    https://api.endpoints.huggingface.cloud (the document declares no server; this is the origin it was published from)
  • URL
    https://api.endpoints.huggingface.cloud/v2/endpoint/{namespace}
  • Auth
    HTTP bearer

Path parameters

namespacestring required

User or organization name

Query parameters

tagsstring

Filter by tags (comma-separated)

searchstring

Filter by name substring

cursorstring

Pagination cursor

limitinteger

Max results (default: 20)

typestring

Filter by endpoint type(s) (comma-separated): public, authenticated, private

taskstring

Filter by model task(s) (comma-separated)

statestring

Filter by endpoint state(s) (comma-separated): updating, running, paused, failed, scaledToZero

instanceTypestring

Filter by instance type(s) (comma-separated)

instanceSizestring

Filter by instance size(s) (comma-separated)

enginestring

Filter by engine(s) (comma-separated): huggingface, huggingface-neuron, tgi, tgi-neuron, tei, llamacpp, vllm, vllm-omni, vllm-neuron, sglang, hfserve, custom

sortBystring

Field to sort on: createdAt (default), updatedAt, name, lastActivity

directionstring

Sort direction: asc or desc (default)

Response

Endpoints listed successfully

nextCursorstring nullable

Use as query param cursor to fetch previous cursor results

prevCursorstring nullable

Use as query param cursor to fetch next cursor results

totalItemsinteger required

Total number of endpoints matching the filters, ignoring limit/cursor

Example response

{
  "items": [
    {
      "compute": {
        "instanceSize": "x1",
        "instanceType": "intel-spr",
        "scaling": {
          "maxReplica": 4,
          "measure": {
            "hardwareUsage": 80
          },
          "minReplica": 1,
          "scaleToZeroTimeout": 15,
          "schedule": [
            {
              "at": "07:30",
              "maxReplica": 4,
              "minReplica": 1,
              "scaleToZeroTimeout": 15
            }
          ]
        }
      },
      "model": {
        "env": {
          "MAX_CONCURRENT_REQUESTS": "128"
        },
        "image": {
          "tgi": {
            "healthRoute": "/health",
            "port": 80,
            "url": "https://host/image:tag",
            "maxBatchPrefillTokens": 2048,
            "maxBatchTotalTokens": 2048,
            "maxInputLength": 1024,
            "maxTotalTokens": 1512,
            "disableCustomKernels": true
          }
        },
        "repository": "meta-llama/Llama-2-7b-hf",
        "revision": "main",
        "secrets": {
          "HF_TOKEN": "hf_xxx"
        }
      },
      "name": "my-endpoint",
      "network": {
        "cidrList": [
          "10.0.0.0/8"
        ]
      },
      "privateService": {
        "accountId": "123456789012"
      },
      "provider": {
        "region": "us-east-1",
        "vendor": "aws"
      },
      "route": {
        "domain": "api.example.com",
        "path": "/v1/models/gpt2"
      },
      "status": {
        "readyReplica": 2,
        "targetReplica": 4,
        "url": "https://68a0f3b5c6ee5c9dcc0e0a01.endpoints.huggingface.cloud"
      }
    }
  ]
}

Changes

  • 029d3baf0ca3Revision changes
    • info

      added the new optional query request parameter engine

    • info

      added the new optional query request parameter instanceSize

    • info

      added the new optional query request parameter instanceType

  • b42f445e0429Revision changes
    • breaking

      added subschema #2 subschema #3 subschema #4 subschema #5 subschema #6 subschema #7 subschema #8 subschema #10 to the /// response property oneOf list for the response status

    • info

      added the optional property //// to the response with the status

    • info

      removed subschema #2 subschema #3 subschema #4 subschema #5 subschema #6 subschema #7 subschema #8 subschema #10 from the /// response property oneOf list for the response status