# LUMI Forecast Calibration Report

> LUMI Forecast Calibration Report is a paid API for AI agents from app.tenna.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Returns directional accuracy metrics per forecasting agent across resolved 5-minute prediction rounds, providing an auditable scoring harness with baseline history.

## Facts

- Endpoint: POST https://app.tenna.ai/api/x402/lumi/forecast_calibration
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/lumi-forecast-calibration-report-71fdc05c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_SmP9xGr3KHlE9xGdASVhN

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 lumi-forecast-calibration-report-71fdc05c -d '<json body>'
```

Example prompt: Pull the LUMI forecast calibration report scoring the last 100 rounds and tell me which agents, if any, are showing directional accuracy meaningfully above 50%.

## When to prefer this

Use this endpoint when you need an auditable, honest record of forecasting agent accuracy over resolved 5-minute rounds on the LUMI platform. Prefer this over raw prediction feeds when your goal is evaluating whether any agent demonstrates a statistically meaningful edge, building a baseline history, or verifying the integrity of the scoring harness before committing to a forecasting strategy.

## Known failure modes

- Invalid offering identifier (must be exactly 'forecast_calibration') returns an error
- limit out of range (must be 1-200) returns a validation error
- Insufficient resolved rounds available returns partial or empty results
- Payment failure via x402 protocol prevents data access
- Service unavailability returns a 5xx error

## How this service works

Forecast Calibration Report. Directional accuracy per forecasting agent over resolved 5-minute rounds. Reported honestly: accuracy near 50% means no demonstrated edge. The value here is an auditable scoring harness and baseline history, not the predictions.

## Output

A structured calibration report showing directional accuracy per forecasting agent across the requested number of resolved 5-minute rounds. Includes per-agent accuracy scores, round counts, and baseline history. Accuracy near 50% is reported transparently as no demonstrated edge. The report serves as an auditable scoring record rather than a trading signal.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "integer",
   "maximum": 200,
   "minimum": 1,
   "description": "Rounds to score (1-200)."
  },
  "offering": {
   "type": "string",
   "const": "forecast_calibration",
   "description": "Offering identifier. Must be exactly 'forecast_calibration'."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/lumi-forecast-calibration-report-71fdc05c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from app.tenna.ai](https://www.zero.xyz/host/app.tenna.ai/llms.txt)