What does a ClearRun API response look like?

Q: What does a ClearRun API response look like?

Score and evaluate return { verdict, receipt } . Chat returns responseText , verdict , receipt and a sessionId . Errors return { error, code } .

Score and evaluate return { verdict, receipt }. Chat returns responseText, verdict, receipt and a sessionId. Errors return { error, code }.

Last updated November 9, 2026

Score and evaluate

{
  "verdict": {
    "verdictId": "6e07586d-e028-43d6-bec3-0f4821b22ca0",
    "schemaVersion": "1.2.0",
    "score": 52,
    "grade": "High risk",
    "risk": "elevated",
    "summary": "Review Evidence support.",
    "timestamp": "2026-11-14T01:02:12.552Z",
    "signature": "QsF676qMfyH0UUP2EkF7flPQ+JJuiJ254T2MbX5n0B8O6KCClYCSzFfecN/GNtVWtDqSD7cOzBNhpTvcN1AlDA==",
    "signatureKeyId": "sig-1",
    "signatureAlg": "ed25519",
    "signalsDigest": "21414c50f3bf2aa7033ebd80cc8aa297a5c2937a95bc30656ac543b2aad1737a",
    "signalsSalt": "fbf678c0c5cb43b2cc9ce4b199dc6191",
    "componentSignals": [
      {
        "name": "Evidence support",
        "level": 3,
        "note": "Limited supporting evidence"
      },
      {
        "name": "Reasoning integrity",
        "level": 6,
        "note": "Internally consistent"
      }
    ]
  },
  "receipt": {
    "receiptId": "rct_1d4b359fe4ca942d0bfa096b862a1031",
    "verdictId": "6e07586d-e028-43d6-bec3-0f4821b22ca0",
    "workspaceId": "account:6823bee4-6a1b-4864-b659-21f2eabd073a",
    "inputHash": "d2a0eedab8b7da41ed9bb2bf610cba76011ebad1d7108744c61b0838425511e9",
    "outputHash": "a7dd34a9d95011e53ac9d91baa9c37dd82cd19976e53e2a5c919696c9817075b",
    "verdictHash": "5137bdcc5be93c6b29074c5d4f93899118eeedd9b3aa90d47a22a1e2045789ee",
    "timestamp": "2026-11-14T01:02:12.598Z",
    "keyId": "sig-1",
    "alg": "Ed25519",
    "prevHash": "abe2c1a67ced960260f39d08606420a8d3b15ebd4c809456faef7590d4dd1071",
    "receiptHash": "255cf6a0965ca2956a02bcf96c16058038345e4de742070ddced78436c6204f8",
    "signature": "l1ipO7QSL6o90Iat5MR/Ti7yODCv6TaGrckXH3gEGDWOkfoKxnxFVFi6VDKGVi0RtqhjoHIuCCFHKcO45zHgDw==",
    "encKeyId": "enc-2026-10",
    "status": "stored"
  },
  "creditsConsumed": 3,
  "creditsRemaining": 0,
  "trainingParticipation": true,
  "factLayer": null
}

This is a real free-plan response at schema 1.2.0, from one score run on November 13, 2026. Build on the fields above, and treat any field you do not need as optional.

Paid accounts (Pro, Business and Enterprise) receive four component signals: Evidence support, Reasoning integrity, Confidence calibration and Ambiguity handling. Free use, developer API access and public lookups receive Evidence support and Reasoning integrity. Enterprise responses may also include failureCategories and issues. The names of any enterprise-only categories are not listed here. signalsDigest is a digest of the signals in the same response. Treat the detail fields as optional.

Chat

Adds sessionId, messageId, executionId, responseText (also as response) and model.

Errors

{ "error": "Rate limit exceeded", "retryAfter": 12 }

code is there when the API has one. Some errors add fields, such as maxLength.