# SignalHarness Model Output Latency Comparator (Caller-Supplied Metrics)

> SignalHarness Model Output Latency Comparator (Caller-Supplied Metrics) is a paid API for AI agents from signalharness.ai, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-15).

Compares model output latency metrics supplied by the caller and returns a structured analysis of relative performance differences.

## Facts

- Endpoint: POST https://signalharness.ai/api/agent/services/model_output_latency_compare_from_supplied_metrics/invoke
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/signalharness-model-output-latency-comparator-caller-supplied-metrics-2fb26665
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cGRXGe5mVbTOdIwA-RZoV

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability signalharness-model-output-latency-comparator-caller-supplied-metrics-2fb26665 -d '<json body>'
```

Example prompt: I've collected latency measurements for GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro across 100 requests each — can you run those numbers through SignalHarness to compare which model is consistently fastest and flag any outliers?

## When to prefer this

Choose this endpoint when you already have latency metrics collected from your own benchmarking runs and want a structured comparison without re-running inference. It is best suited for post-hoc analysis where you control the data, as opposed to endpoints that run live model calls to measure latency directly. Useful when you need a signed, tamper-evident receipt of the analysis for audit or compliance purposes.

## Known failure modes

- Malformed or non-JSON request_json input returns a validation error
- Missing or empty request_json causes a schema rejection
- Caller-supplied data that is not interpretable as latency metrics may produce a schema-valid but semantically meaningless analysis
- Payment failure on the x402 protocol blocks execution
- Result accuracy is fully dependent on the quality and accuracy of caller-supplied data — garbage in, garbage out

## 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 analysis object containing a comparison of the caller-supplied latency metrics, along with a warnings array noting that results are based on caller-supplied data, the service ID, and a signed receipt with execution metadata including payment ID, network, and a SHA-256 hash of the result for integrity verification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "request_json": {
   "type": "string",
   "maxLength": 65536,
   "minLength": 2
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "replay": false,
  "result": {
   "warnings": [
    "Verify the caller-supplied data before relying on this result."
   ],
   "service_id": "model_output_latency_compare_from_supplied_metrics",
   "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_latency_compare_from_supplied_metrics",
   "executionId": "example-execution",
   "startedAtMs": 0,
   "amountAtomic": "15000",
   "resultSha256": "bf04d1fbf6d5e760b5cf2ece4a758bfeb4b367c9ba85850679d2e4f6d3566bb3",
   "serviceVersion": "1.0.0",
   "settlementReference": "0x0000000000000000000000000000000000000000000000000000000000000000"
  },
  "artifacts": [],
  "requestId": "example-request",
  "executionId": "example-execution"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/signalharness-model-output-latency-comparator-caller-supplied-metrics-2fb26665/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from signalharness.ai](https://www.zero.xyz/host/signalharness.ai/llms.txt)