Skip to main content
Get comprehensive details about a specific serverless endpoint, including its current status, configuration, and usage metrics.

​
Path Parameters

  • endpointId: The unique identifier of the endpoint

​
Example Usage

curl -X GET "https://api.tensorone.ai/v2/endpoints/ep_1234567890abcdef" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json"

​
Response

Returns detailed endpoint information: 
{
    "id": "ep_1234567890abcdef",
    "name": "my-text-generation-model",
    "status": "active",
    "url": "https://api.tensorone.ai/v2/ep_1234567890abcdef/runsync",
    "templateId": "tpl_llama2_7b",
    "gpuType": "NVIDIA A100",
    "createdAt": "2024-01-15T10:30:00Z",
    "updatedAt": "2024-01-15T12:45:00Z",
    "metrics": {
        "totalExecutions": 1250,
        "averageLatency": 2.3,
        "lastExecution": "2024-01-15T12:44:30Z"
    },
    "configuration": {
        "workerCount": 2,
        "maxConcurrency": 10,
        "timeoutSeconds": 300
    }
}

​
Response Fields

  • id: Unique endpoint identifier
  • name: Human-readable endpoint name
  • status: Current status (active, inactive, pending, error)
  • url: Direct URL for executing the endpoint
  • templateId: Template used to create this endpoint
  • gpuType: Allocated GPU type
  • metrics: Usage statistics and performance data
  • configuration: Current endpoint settings

​
Error Responses

  • 404 Not Found: Endpoint doesn’t exist or you don’t have access
  • 401 Unauthorized: Invalid or missing API key
Metrics data is updated in real-time and reflects the last 30 days of activity.