# Suverse Wikipedia Full-Text Search

> Suverse Wikipedia Full-Text Search is a paid API for AI agents from proxy.suverse.io, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Full-text searches English Wikipedia via the MediaWiki API, returning ranked page titles, snippets, and word counts for a query — no API key required.

## Facts

- Endpoint: POST https://proxy.suverse.io/v1/data/suverse-wiki-search
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/suverse-wikipedia-full-text-search-ce4afea4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_klzXdFPYptw2fHN9xdoq2

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 suverse-wikipedia-full-text-search-ce4afea4 -d '<json body>'
```

Example prompt: Search Wikipedia for articles about 'quantum entanglement' and give me the top ranked page titles and their snippets so I can pick the right one to read in full.

## When to prefer this

Use this endpoint when an agent needs to discover which Wikipedia article best matches a topic before fetching its full content — especially useful for disambiguation, pre-fetching, or building a pipeline where you search first and then retrieve. Prefer this over direct MediaWiki API calls when you need a managed, payment-metered proxy with consistent response formatting. Not suited for fetching full article text or non-English Wikipedia.

## Known failure modes

- Empty results if the query matches no Wikipedia articles
- Rate limiting or HTTP 402 if payment is not properly attached
- Vague or irrelevant snippets for highly ambiguous single-word queries
- MediaWiki API downtime causing 5xx errors
- Query too long or malformed body returning a 400 error

## How this service works

Full text search of English Wikipedia via the MediaWiki API, no key. Returns ranked page titles, snippets, and word counts for the query. For AI agents finding the right article before fetching a summary.

## Output

Returns a ranked list of Wikipedia page results, each containing a page title, a short text snippet from the article highlighting the matched content, and the word count of the full article — enabling the agent to identify the most relevant article before fetching its full content.

## 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
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/suverse-wikipedia-full-text-search-ce4afea4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from proxy.suverse.io](https://www.zero.xyz/host/proxy.suverse.io/llms.txt)