v1

latestOpenAPI 3.1.02026-07-134612587.0 KB

Endpoints

List endpoints [READ]

get/v2/endpoint/{namespace}

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)

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

Example response

{
  "items": [
    {
      "compute": {
        "instanceSize": "x1",
        "instanceType": "intel-spr",
        "scaling": {
          "maxReplica": 4,
          "measure": {
            "hardwareUsage": 80
          },
          "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://endpoint-id.region.vendor.endpoints.huggingface.cloud"
      }
    }
  ]
}