# fittings Citation Extractor

> fittings Citation Extractor is a paid API for AI agents from fittings.sh, paid per call via x402, $0.007/call, status unknown (last checked 2026-10-11).

Extracts and normalizes DOIs, arXiv IDs, PMIDs, PMCIDs, and ISBNs from free text, returning deduplicated identifiers with their character offsets.

## Facts

- Endpoint: POST https://fittings.sh/v1/text/extract-citations?utm_source=zero.xyz
- Price: $0.007/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/fittings-citation-extractor-4f463862
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uNR3Qz3ntQIN_EFS3KxAl

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 fittings-citation-extractor-4f463862 -d '<json body>'
```

Example prompt: Can you pull out all the DOIs, arXiv IDs, and ISBNs from this paragraph and tell me where each one first appears? Here's the text: 'See Smith et al. (doi:10.1038/nature12373) and also arXiv:1706.03762 for background.'

## When to prefer this

Use this endpoint when you need to reliably parse multiple citation identifier types (DOIs, arXiv IDs, PMIDs, PMCIDs, ISBNs) from unstructured text in a single call with deduplication and offset tracking. It's ideal over regex-based approaches when you need normalization and multi-format support simultaneously, and preferable to general NLP tools when the goal is specifically academic/bibliographic identifier extraction.

## Known failure modes

- Text exceeds 200,000 character limit — request rejected
- Invalid citation kind specified in 'kinds' array — may return error or empty results
- Text contains no recognizable citation identifiers — returns empty list
- Malformed or ambiguous identifiers in text may be missed or incorrectly normalized

## How this service works

Pulls DOIs, arXiv ids, PMIDs, PMCIDs and ISBNs out of free text, deduplicated and normalized, with the character offset of each first occurrence.

## Output

A list of deduplicated, normalized citation identifiers found in the input text, each with its type (doi, arxiv, pmid, pmcid, isbn), normalized value, and the character offset of its first occurrence in the source text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Free text, up to 200000 characters"
  },
  "kinds": {
   "type": "array",
   "description": "Restrict to these kinds: doi, arxiv, pmid, pmcid, isbn. Default all."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fittings-citation-extractor-4f463862/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fittings.sh](https://www.zero.xyz/host/fittings.sh/llms.txt)