# Delx Commerce — Reliability Curve (Calibration)

> Delx Commerce — Reliability Curve (Calibration) is a paid API for AI agents from commerce.delx.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-02).

Computes a reliability curve (calibration curve) from forecast probabilities and binary outcomes, grouped into bins, to evaluate forecast calibration quality.

## Facts

- Endpoint: POST https://commerce.delx.ai/api/v1/x402/reliability-curve?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-commerce-reliability-curve-calibration-52d15db8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6pZky-U1ziHNuew2UfuiY

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 delx-commerce-reliability-curve-calibration-52d15db8 -d '<json body>'
```

Example prompt: I have 100 binary outcomes and their associated forecast probabilities — can you compute a reliability curve using 10 calibration bins so I can see how well my model's predictions line up with actual hit rates?

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-call reliability/calibration curve computation with no signup overhead. It is ideal for agents that periodically audit model calibration, need verifiable pay-per-result pricing via USDC/x402, or lack access to a statistical computing environment. Prefer it over building calibration code in-house when integrating into automated ML evaluation pipelines.

## Known failure modes

- Mismatched array lengths between forecasts and outcomes returns an error
- Forecast values outside [0,1] may cause unexpected binning behavior
- Too few data points relative to bin count yields bins with n=0 or n=1, producing noisy estimates
- Invalid bins value (non-integer or <=0) causes a request error
- Empty outcomes or forecasts arrays return no points

## How this service works

Pay-per-result APIs for agents. No signup. Exact price. Verifiable delivery. USDC on Base + Solana via x402.

## Output

Returns a JSON array of calibration curve points, each containing the bin index, number of samples in the bin (n), the mean forecast probability for that bin, and the observed hit rate. The schema identifier is 'delx/util-reliability-curve/v1'.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "bins": {
   "type": "integer",
   "description": "Number of calibration bins"
  },
  "outcomes": {
   "type": "array",
   "description": "Binary outcomes 0/1 aligned with forecasts"
  },
  "forecasts": {
   "type": "array",
   "description": "Forecast probabilities in [0,1]"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "points": [
   {
    "n": 2,
    "bin": 0,
    "hit_rate": 0,
    "mean_forecast": 0.15
   },
   {
    "n": 2,
    "bin": 3,
    "hit_rate": 1,
    "mean_forecast": 0.8500000000000001
   }
  ],
  "schema": "delx/util-reliability-curve/v1"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-commerce-reliability-curve-calibration-52d15db8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from commerce.delx.ai](https://www.zero.xyz/host/commerce.delx.ai/llms.txt)