Models (AI Data Plane)

Fetches the details of the given model.

In order to access this endpoint, the provided API key must have at least one of the following roles:

  • Organization Member

To learn more, see Organization, Project, and Database Access Overview.

get/v4/organizations/{organizationId}/aiServices/models/{modelId}

Request

Response

Successfully fetched the model based on the ModelId.

Example response

{
  "model": {
    "id": "fffffffff-aaaa-1414-eeee-000000000000",
    "name": "my-new-model",
    "config": {
      "catalogModelName": "meta-llama/Llama-3.1-8B-Instruct",
      "provider": "meta",
      "quantization": "fullPrecision",
      "optimization": "latency",
      "dimensions": 4096,
      "caching": {
        "enableStandard": true,
        "semantic": {
          "embeddingModel": "my-embedding-model-id",
          "scoreThreshold": 0.75,
          "dimensions": 4096,
          "distanceMetric": "dot_product"
        },
        "defaultCache": "semantic",
        "expiryTTL": 1000
      },
      "enableBatching": true,
      "keywordFiltering": [
        "harassment",
        "murder"
      ]
    },
    "cloudConfig": {
      "provider": "aws",
      "region": "us-east-1",
      "compute": {
        "cpu": 4,
        "gpuMemory": 48
      }
    },
    "status": "deploying",
    "usageMetrics": {
      "tokens": {
        "value": 345,
        "trend": "increasing"
      },
      "requests": {
        "value": 4094,
        "trend": "increasing"
      }
    },
    "connectionString": "http://endpoint.com",
    "audit": {
      "createdBy": "ffffffff-aaaa-1414-eeee-000000000000",
      "createdAt": "2021-09-01T12:34:56Z",
      "modifiedBy": "ffffffff-aaaa-1414-eeee-000000000000",
      "modifiedAt": "2021-09-01T12:34:56Z",
      "version": 1
    },
    "actions": [
      "delete"
    ]
  }
}

Changes

    • warning

      added the new sparse-embedding-generation enum value to the // response property for the response status

    • info

      api tag Models (AI Data Plane) added

    • info

      api tag Models (AI Services) removed