Get Inference Usage Attribution Rollup

Returns inference request and token usage across the Edges the caller manages, grouped by the selected attribution dimension.

GET /api/v1/edges/inference/usage-attribution

Get Inference Usage Attribution Rollup

cURL

curl --request GET \
  --url https://{tenantDomain}.conductor.one/api/v1/edges/inference/usage-attribution \
  --header 'Authorization: Bearer <token>'

200

{
  "edgeCount": 123,
  "rows": [
    {
      "attributionId": "<string>",
      "cacheReadTokens": "<string>",
      "cacheWriteTokens": "<string>",
      "costNanoUsd": "<string>",
      "inputTokens": "<string>",
      "missingUsageCallCount": "<string>",
      "modelBreakdown": [
        {
          "cacheReadTokens": "<string>",
          "cacheWriteTokens": "<string>",
          "costNanoUsd": "<string>",
          "inputTokens": "<string>",
          "missingUsageCallCount": "<string>",
          "modelName": "<string>",
          "outputTokens": "<string>",
          "requestCount": "<string>",
          "unpricedRequestCount": "<string>"
        }
      ],
      "outputTokens": "<string>",
      "requestCount": "<string>",
      "unpricedRequestCount": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Authorization · string · header · required

This API uses OAuth2 with the Client Credential flow. Client Credentials must be sent in the BODY, not the headers. For an example of how to implement this, refer to the c1TokenSource.Token() function.

Query Parameters

dimension · enum<string>

The dimension field.

Available options: TB_USAGE_ATTRIBUTION_DIMENSION_UNSPECIFIED, TB_USAGE_ATTRIBUTION_DIMENSION_TEAM, TB_USAGE_ATTRIBUTION_DIMENSION_APPLICATION, TB_USAGE_ATTRIBUTION_DIMENSION_AGENT, TB_USAGE_ATTRIBUTION_DIMENSION_COST_CENTER, TB_USAGE_ATTRIBUTION_DIMENSION_USER, TB_USAGE_ATTRIBUTION_DIMENSION_PROVIDER, TB_USAGE_ATTRIBUTION_DIMENSION_MODEL

page_size · integer<int32>

The pageSize field.

since · string<int64>

The since field.

until · string<int64>

The until field.

Response

200 - application/json

Successful response

The EdgeServiceGetInferenceUsageAttributionRollupResponse message.

edgeCount · integer<uint32>

Number of authorized Edges included. Zero means the caller manages no Edges, as distinct from Edges that have no traffic yet.

rows · Tb Usage Attribution Row · object[] | null

Ordered by (input_tokens + output_tokens) descending, limited to page_size.

Show child attributes