See what scoring a goal costs
Prices scoring before you turn it on: maxUsd is the most one judgement can cost (a hard ceiling), typicalUsd is an estimate of a usual one. A conversation is judged at most maxScoresPerConversation times, and a goal read from a known outcome costs nothing (outcomeIsFree). Pass sampleRate to price a share of conversations. The ceiling is the longest goal text allowed; pass criteriaBytes (the UTF-8 size of a goal being edited) to price that text.
Requires an API key with the workspace:read scope.
apiKeyAuthorizationBearer <token>A secret API key from the dashboard (Developers → API keys): vl_live_…, or vl_test_… for test mode. Each operation says which scope the key needs.
id*stringThe agent id.
sampleRate?numberThe share of conversations to score, above 0 up to 1. Default: the goal's own.
0 < value <= 1criteriaBytes?|The UTF-8 byte size of the goal text being edited, at most 2000. Default: the longest a goal may be.
0 <= value <= 2000The most one judgement can cost, a typical one, and the limits
application/json- response
maxUsd*numbertypicalUsd*numbermaxScoresPerConversation*integersampleRate*numberoutcomeIsFree*booleancurl "https://api.vlayers.ai/v1/agents/$AGENT_ID/goal/quote?sampleRate=0.5" \ -H "Authorization: Bearer $VOICELAYER_API_KEY"{ "maxUsd": 0.0123, "typicalUsd": 0.0031, "maxScoresPerConversation": 3, "sampleRate": 1, "outcomeIsFree": true}