# agentshelf.syntexa.ch Regex Wikidata Q-ID Extractor

> agentshelf.syntexa.ch Regex Wikidata Q-ID Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.006/call, status unknown (last checked 2026-10-02).

Extracts Wikidata Q-identifiers (e.g. Q42, Q76) from text using regex, returning up to 20 matches

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-wikidata?utm_source=zero.xyz
- Price: $0.006/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-syntexa-ch-regex-wikidata-q-id-extractor-b63f3b4a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_km5lYGGhPnqbiDethUj-g

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 agentshelf-syntexa-ch-regex-wikidata-q-id-extractor-b63f3b4a -d '<json body>'
```

Example prompt: Can you scan this text and pull out all the Wikidata Q IDs it mentions — something like Q42 or Q76 — up to 20 of them? Here's the text: 'Douglas Adams (Q42) wrote The Hitchhiker's Guide, and Barack Obama (Q76) is a famous politician.'

## When to prefer this

Use this endpoint when you need fast, offline regex-based extraction of Wikidata Q IDs from text and do not require semantic entity disambiguation. Prefer the free sandbox endpoint POST /v1/sandbox/regex-wikidata for testing or when cost matters. Choose this over NLP-based entity linkers when you only need syntactic Q-ID pattern matching (e.g. 'Q' followed by digits) and low latency without network dependencies.

## Known failure modes

- Empty match list returned when text contains no Wikidata Q IDs — still billed $0.006 USDC
- Input text exceeds 100,000 character limit — request rejected with validation error
- Text shorter than 1 character — request rejected
- More than 20 matches present — only first 20 returned, remainder silently truncated
- Malformed JSON body — HTTP 400 error

## How this service works

Call when an agent needs Wikidata Q ids extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.006 USDC. Prefer unpaid POST /v1/sandbox/regex-wikidata first.

## Output

A list of up to 20 Wikidata Q ID strings (e.g. ['Q42', 'Q76', 'Q317521']) found in the input text via regex matching. If no Q IDs are present, an empty list is returned but the call is still billed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "Q42"
   ],
   "maxLength": 100000,
   "minLength": 1,
   "description": "Input for this SKU. The route description says whether it is plain text, a URL, base64 bytes, or an already-encoded token."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-syntexa-ch-regex-wikidata-q-id-extractor-b63f3b4a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)