Run a suite on a version
Plays every case of the suite against one version of its agent, a draft or a published one, and judges each run with the reviews you expect. It is charged: each turn as a test and each review at its price, so quote.maxUsd is the most the whole suite can cost. Pass quoteOnly to get the price and run nothing. A case that cannot run is counted as refused with its reason, not as failed.
Requires an API key with the workspace:write 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 suite id.
application/json- body
versionId?stringThe version to run every case against: a published version of the suite’s agent. Give this or draft.
draft?booleanRun on the agent’s current draft: it is sealed as a version first. Give this or versionId.
quoteOnly?booleanAnswer the price and run nothing.
quotedMaxUsd?numberThe most the person saw and agreed to. A run whose ceiling is now higher is refused price_changed (409).
The most the run can cost, and the suite run once it is queued
application/json- response
quote*suiteRun*|nullcurl -X POST "https://api.vlayers.ai/v1/tests/$SUITE_ID/runs" \ -H "Authorization: Bearer $VOICELAYER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "versionId": "0192f5b0-7c3e-7a51-9b2d-4e8f1a6c3d21", "quoteOnly": true }'{ "quote": { "cases": 3, "maxUsd": 1.2, "typicalUsd": 0.3, "maxTurns": 20, "maxAttemptsPerRun": 2, "analyzersMaxUsd": 0.1 }, "suiteRun": { "id": "0192f5fa-e3f2-7d40-8f90-0123456789ab", "suiteId": "0192f5f8-c1d0-7b2e-8d7e-8f9012345678", "versionId": "0192f5d5-9cad-7ebf-9a4b-5c6d7e8f9012", "status": "queued", "quoteMaxUsd": 1.2, "cases": 3, "passed": 0, "failed": 0, "refused": 0, "createdBy": "user_2abc", "createdAt": "2026-10-20T15:04:05.000Z", "finishedAt": null, "expiresAt": "2026-10-20T15:04:05.000Z" }}