# Match Forecast Probabilities – Dixon-Coles (World Cup 2026)

> Match Forecast Probabilities – Dixon-Coles (World Cup 2026) 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 Dixon-Coles statistical match outcome probabilities for World Cup fixtures, including model-vs-market differences and de-vigged market probabilities for informational research.

## Facts

- Endpoint: POST https://agents.machina.gg/world-cup/v1/get-match-forecast
- 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: 2
- Provider: agents.machina.gg
- Website: https://agents.machina.gg
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-machina-gg-match-forecast-probabilities-dixon-coles-world-cup-0bf05e7a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xIk10PnXOB69PPEWH7WUw

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-match-forecast-probabilities-dixon-coles-world-cup-0bf05e7a -d '<json body>'
```

Example prompt: Can you pull the Dixon-Coles forecast probabilities for the England vs France World Cup 2026 match, including how the model probabilities compare to the market odds?

## When to prefer this

Use this endpoint when you need rigorous statistical match outcome probabilities for a specific World Cup 2026 fixture using the Dixon-Coles methodology, especially when you want to compare model-derived probabilities against de-vigged market odds. Prefer this over generic sports data APIs when the user specifically needs a quantitative, model-based forecast grounded in historical backtests and transparent sourcing. This is purely informational and research-oriented — it does not make betting recommendations.

## Known failure modes

- Match identifier not found or not yet scheduled returns a 404 or empty result
- Match not yet in the system (pre-tournament fixtures not yet loaded)
- Malformed POST body returns a 400 validation error
- Market odds not yet available for the fixture returns partial results without model-vs-market difference
- Payment failure or insufficient balance returns a 402 error

## How this service works

Dixon-Coles match probabilities with model-vs-market differences and de-vigged probabilities. Informational research output with no selection, ranking, or recommendation of wagers.

## Output

A JSON object containing Dixon-Coles computed probabilities for each match outcome (home win, draw, away win), corresponding de-vigged market probabilities, and the numerical difference between model and market for each outcome, all grounded in Machina Sports's forecasting engine with no betting selection or recommendation.

## 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-match-forecast-probabilities-dixon-coles-world-cup-0bf05e7a/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)