Back to Browse
SignalHarness Model Output Consensus Analyze
x402
SignalHarness Model Output Consensus Analyze is a paid API for AI agents from signalharness.ai, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-13).
Analyzes caller-supplied JSON data to evaluate consensus or consistency across model outputs, returning structured analysis with warnings and evidence scope.
Price / call$0.025
Success—
StatusUnknown
How this service works
Explore 330 pay-per-call x402 API services and 27 agent-native digital products, with Base USDC pricing, secure Polar checkout, and free discovery.
Output
Returns a JSON object containing an analysis_json field with structured consensus findings, a warnings array (e.g. reminders to verify caller-supplied data), and an evidence_scope field indicating the data provenance (caller_supplied_data). Wrapped in a receipt with payment metadata including paymentId, requestId, executionId, latencyMs, and a resultSha256 for integrity verification.
Example use cases
Multi-model sentiment agreement check
“I got sentiment predictions from three different LLMs on a customer review and I want to know if they agree — can you run consensus analysis on this JSON: {"gpt4": "positive", "claude": "positive", "gemini": "neutral"}?”
Detecting conflicting classification outputs
“My pipeline ran the same document through two classifiers and got different labels — can you analyze this output JSON for consensus and flag where they disagree: {"classifier_1": "spam", "classifier_2": "not_spam"}?”
Validating ensemble model predictions
“I have an ensemble of five models that each predicted a risk score for this loan application — can you analyze this JSON and tell me if there's consensus or significant divergence: {"model_scores": [0.82, 0.79, 0.85, 0.80, 0.91]}?”
Technical details
Endpoint
POSThttps://signalharness.ai/api/agent/services/model_output_consensus_analyze/invokeWhen to prefer
Choose this endpoint when you need a lightweight, pay-per-call consensus analysis on JSON-encoded model outputs without standing up your own evaluation infrastructure. Ideal for multi-model pipelines where you want a third-party check on output agreement. Best suited for structured JSON data from LLMs, classifiers, or scoring models. Prefer alternatives if you need real-time streaming analysis, very large payloads, or domain-specific model evaluation frameworks.
Side effects
- Malformed or invalid JSON in request_json field causes rejection
- Input JSON exceeding 65536 character limit is refused
- Caller-supplied data that does not represent model outputs may yield low-utility analysis
- Analysis warnings indicate results are not independently verified — reliance risk
- Payment failure on Base network prevents execution
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| request_json | string |
Output
Schema · Response
{
"type": "json",
"example": {
"replay": false,
"result": {
"warnings": [
"Verify the caller-supplied data before relying on this result."
],
"service_id": "model_output_consensus_analyze",
"analysis_json": "{\"example\":\"schema-valid caller-supplied data\"}",
"evidence_scope": "caller_supplied_data"
},
"status": "succeeded",
"receipt": {
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"usage": [],
"status": "succeeded",
"network": "eip155:8453",
"artifacts": [],
"endedAtMs": 0,
"latencyMs": 0,
"paymentId": "example-payment",
"receiptId": "example-receipt",
"requestId": "example-request",
"serviceId": "model_output_consensus_analyze",
"executionId": "example-execution",
"startedAtMs": 0,
"amountAtomic": "25000",
"resultSha256": "23fd4698aecf730fa18abbb2a0df7a72e76a112142bab949c017f2d844c0d22a",
"serviceVersion": "1.0.0",
"settlementReference": "0x0000000000000000000000000000000000000000000000000000000000000000"
},
"artifacts": [],
"requestId": "example-request",
"executionId": "example-execution"
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"