Get AI Config metrics

For the complete documentation index, see llms.txt. For the full documentation snapshot, see llms-full.txt.

Retrieve usage metrics for an AI Config by config key.

GET /api/v2/projects/{projectKey}/ai-configs/{configKey}/metrics

Get AI Config metrics

cURL

curl --request GET \
  --url https://app.launchdarkly.com/api/v2/projects/{projectKey}/ai-configs/{configKey}/metrics \
  --header 'Authorization: <api-key>'

200

{
  "judgeRelevance": 0.14894159,
  "inputCost": 7.386281948385884,
  "outputCost": 1.2315135367772556,
  "generationSuccessCount": 5,
  "inputTokens": 0,
  "generationErrorCount": 2,
  "thumbsDown": 9,
  "judgeToxicity": 0.6846853,
  "totalTokens": 1,
  "judgeAccuracy": 0.10246457,
  "generationCount": 5,
  "timeToFirstTokenMs": 2,
  "outputTokens": 6,
  "thumbsUp": 7,
  "durationMs": 3,
  "satisfactionRating": 0.4145608
}

Authorizations

Authorization · string · header · required

Path Parameters

projectKey · string · required

configKey · string · required

Query Parameters

from · integer · required

The starting time, as milliseconds since epoch (inclusive).

to · integer · required

The ending time, as milliseconds since epoch (exclusive). May not be more than 100 days after from.

env · string · required

An environment key. Only metrics from this environment will be included.

Response

200

application/json

Metrics computed

inputTokens · integer

outputTokens · integer

totalTokens · integer

generationCount · integer · deprecated

Number of attempted generations

generationSuccessCount · integer

Number of successful generations

generationErrorCount · integer

Number of generations with errors

thumbsUp · integer

thumbsDown · integer

durationMs · integer

timeToFirstTokenMs · integer

satisfactionRating · number<float>

A value between 0 and 1 representing satisfaction rating

Required range: 0 <= x <= 1

inputCost · number<double>

Cost of input tokens in USD

outputCost · number<double>

Cost of output tokens in USD

judgeAccuracy · number<float>

Average accuracy judge score (0.0-1.0)

Required range: 0 <= x <= 1

judgeRelevance · number<float>

Average relevance judge score (0.0-1.0)

Required range: 0 <= x <= 1

judgeToxicity · number<float>

Average toxicity judge score (0.0-1.0)

Required range: 0 <= x <= 1