# NovaPath Election Evidence API

> NovaPath Election Evidence API is a paid API for AI agents from instructional-decision-engine-x402.vercel.app, paid per call via x402, $0.1/call, status unknown (last checked 2026-11-01).

Returns AI-explained, source-verified election vote counts for historical US presidential contests (2016, 2020, 2024) with exact totals, statuses, timestamps, and source URLs preserved.

## Facts

- Endpoint: POST https://instructional-decision-engine-x402.vercel.app/ai/election-evidence?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/novapath-election-evidence-api-67ab5d0e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_n5sVqUduZLD8BFgWMXgCy

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 novapath-election-evidence-api-67ab5d0e -d '<json body>'
```

Example prompt: Can you pull the reviewed 2020 US presidential vote counts for California, Texas, and Florida — I need the exact totals with source URLs and timestamps explaining what the numbers mean?

## When to prefer this

Choose this endpoint when you need AI-explained, source-cited historical US presidential election vote counts (2016, 2020, 2024) with exact totals and provenance preserved. Prefer it over generic web search when you need machine-readable, structured election data with verified source URLs and timestamps, not narrative summaries. Avoid if you need forecasts, winner declarations, non-presidential races, or real-time unofficial returns not yet imported into the reviewed dataset.

## Known failure modes

- Unavailable or unreviewed contest rejected before payment is processed
- Invalid contestId pattern returns validation error
- Jurisdiction codes not matching pattern (e.g. lowercase or invalid state abbreviation) rejected
- Requesting more than 5 jurisdictions at once returns a schema validation error
- Non-presidential or future contests not yet in reviewed dataset rejected
- Malformed request body returns 400-level error

## How this service works

Explain available reviewed election counts with AI while preserving exact source totals, status, timestamps and source URLs. Current coverage: historical 2016, 2020 and 2024 presidential votes. Future unofficial returns require a reviewed source import. No forecasts or winner declarations; unavailable contests reject before payment.

## Output

Returns an AI-generated explanation of the requested election contest's vote counts alongside exact, unmodified source totals, result status labels, timestamps of data capture, and source URLs for each jurisdiction requested. No forecasts or winner declarations are made; only reviewed historical data is returned.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "contestId": {
   "type": "string",
   "pattern": "^us-(?:president|senate|house|governor)-20[0-9]{2}(?:-[A-Z0-9-]{1,12})?$"
  },
  "jurisdictions": {
   "type": "array",
   "items": {
    "type": "string",
    "pattern": "^(?:US|[A-Z]{2}(?:-[0-9]{2})?)$"
   },
   "maxItems": 5,
   "minItems": 1,
   "uniqueItems": true
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/novapath-election-evidence-api-67ab5d0e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from instructional-decision-engine-x402.vercel.app](https://www.zero.xyz/host/instructional-decision-engine-x402.vercel.app/llms.txt)