# Delx Citation Extract

> Delx Citation Extract is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-15).

Extracts URL and DOI citation patterns from caller-supplied text without any network access, returning structured JSON results

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/citation-extract
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-citation-extract-09f91314
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yztZnVMskIGo0OTwi_C_q

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 delx-citation-extract-09f91314 -d '<json body>'
```

Example prompt: Can you scan through this text I have and pull out all the URLs and DOI citations from it? Here's the content: 'See Smith et al. doi:10.1038/s41586-021-03819-2 and also https://arxiv.org/abs/2103.00020 for further reading.'

## When to prefer this

Choose this endpoint when you already hold text locally and need to extract URL or DOI citation patterns without any network round-trips — it is purely local, stateless, and deterministic, making it ideal for high-volume or privacy-sensitive extraction tasks where no external fetching or live web access is desired. Prefer it over general-purpose NLP or web-scraping tools when the input is already in-hand and you need fast, consistent, machine-readable citation extraction at low cost.

## Known failure modes

- Empty or whitespace-only text input returns an empty citation list
- Malformed DOIs that don't match standard patterns may not be captured
- Very long text inputs may hit payload size limits
- Ambiguous citation formats (non-standard DOI prefixes) may be missed
- Non-UTF-8 encoded text may cause parsing errors

## How this service works

Harvest URL and DOI citation patterns from text without network access — call when harvesting URL/DOI citation patterns without network. Use on text/URLs the agent already holds—adjacent to high-volume extract demand, never advertised as general web or X search. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, and no claim of live chain tip, web search, or med…

## Output

A deterministic machine-readable JSON object listing all extracted URL and DOI citation patterns found in the submitted text, with no network lookups or external validation performed — purely derived from the text supplied by the caller

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "UTF-8 text to encode, chunk, index, or analyze (caller-supplied only)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "dois": [
   "10.1000/xyz123"
  ],
  "urls": [
   "https://example.com/a"
  ],
  "schema": "delx/util-citation-extract/v1",
  "advisory": "Pattern harvest only; links are not fetched.",
  "doi_count": 1,
  "url_count": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-citation-extract-09f91314/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)