# World Cup Historical Forecast Backtests

> World Cup Historical Forecast Backtests is a paid API for AI agents from agents.machina.gg, paid per call via MPP or x402, $0.12/call, status healthy (last checked 2026-09-14, last successful call 2026-09-03).

Returns historical backtest results for Dixon-Coles match forecast models applied to World Cup 2026 matches, enabling evaluation of model accuracy over time.

## Facts

- Endpoint: POST https://agents.machina.gg/world-cup/v1/backtest-forecasts
- Price: $0.12/call
- Payment: MPP, x402
- Status: healthy
- Last checked: 2026-09-14
- Last successful call: 2026-09-03
- Success rate: 100% of calls made through Zero
- Rating: 5.0 / 5 from 1 review
- Activations on Zero: 1
- Provider: agents.machina.gg
- Website: https://agents.machina.gg
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-machina-gg-world-cup-historical-forecast-backtests-8f48a4c4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kw8ZkPn53bE2XOXuX6wLL

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 agents-machina-gg-world-cup-historical-forecast-backtests-8f48a4c4 -d '<json body>'
```

Example prompt: Can you pull the historical backtest results for the World Cup match forecast model so I can see how accurate the Dixon-Coles predictions have been compared to actual match outcomes?

## When to prefer this

Use this endpoint when you need to evaluate the historical predictive accuracy of the World Cup Dixon-Coles forecasting model before relying on it for research or analysis. Prefer this over the live match forecast endpoint when the goal is model validation and retrospective analysis rather than getting current predictions. This is the right choice for sports analytics research, model auditing, or building confidence in forecast reliability.

## Known failure modes

- HTTP 402 if payment is not provided or insufficient funds
- Empty or minimal backtest data if insufficient historical matches have been played
- Request body malformation if JSON schema not followed correctly
- Timeout if the backtest computation takes too long server-side

## How this service works

Historical backtests of the match forecasts. Informational research output with no selection, ranking, or recommendation of wagers.

## Output

Returns structured JSON containing historical backtest results for the Dixon-Coles match forecasting model applied to World Cup 2026 matches. Data includes past match predictions versus actual outcomes, accuracy metrics, and model performance indicators. Output is grounded, source-cited, and strictly informational — no wagering recommendations.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-machina-gg-world-cup-historical-forecast-backtests-8f48a4c4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.machina.gg](https://www.zero.xyz/host/agents.machina.gg/llms.txt)