# Coinslot Extract

> Coinslot Extract is a paid API for AI agents from coinslot.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-15).

Extracts structured, deduplicated entities (emails, URLs, IPv4/IPv6, phone numbers, dates) from raw text with occurrence counts

## Facts

- Endpoint: POST https://coinslot.dev/api/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/coinslot-extract-535fba7a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_r2oUj3bsWgR0RcXzBTeQP

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 coinslot-extract-535fba7a -d '<json body>'
```

Example prompt: Pull out all the emails, phone numbers, URLs, and dates from this raw text and give me a deduplicated list with counts for each: [paste text here]

## When to prefer this

Choose this endpoint when you need to programmatically pull multiple types of structured entities (emails, URLs, IPs, phones, dates) from a single unstructured text blob in one call, with deduplication and counts included automatically. Prefer it over regex-based solutions when you want reliable, battle-tested patterns without writing and maintaining extraction logic yourself. It is especially useful for log analysis, email parsing, document scanning, and data pipeline enrichment tasks where the input is raw text up to 500KB.

## Known failure modes

- Text exceeds 500KB limit — request rejected with payload-too-large error
- Malformed or missing `text` field — 400 bad request
- No entities of a given type found — empty array returned for that type (not an error)
- Ambiguous phone number formats (e.g. short codes, non-standard separators) may be missed or misclassified
- Dates in highly unusual or locale-specific formats may not be recognized

## How this service works

Pull structured data out of raw text: emails, URLs, IPv4/IPv6, phone numbers, dates. Deduplicated with counts. POST { text } (max 500KB).

## Output

A structured JSON object containing deduplicated arrays for each entity type (emails, URLs, IPv4, IPv6, phone numbers, dates), each entry annotated with an occurrence count indicating how many times it appeared in the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Raw text, max 500KB"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/coinslot-extract-535fba7a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from coinslot.dev](https://www.zero.xyz/host/coinslot.dev/llms.txt)