# 24K Labs Entity Extractor (Regex)

> 24K Labs Entity Extractor (Regex) is a paid API for AI agents from api.24klabs.ai, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-13).

Extracts and deduplicates emails, URLs, IPv4 addresses, @mentions, and #hashtags from free text, returning each entity type with occurrence counts.

## Facts

- Endpoint: POST https://api.24klabs.ai/api/entity-extract-regex
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/24k-labs-entity-extractor-regex-51ce807f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_x_4L8mmaT-tqioVelPYQ8

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 24k-labs-entity-extractor-regex-51ce807f -d '<json body>'
```

Example prompt: Pull out all the email addresses, URLs, @mentions, and hashtags from this text and tell me how many times each one appears: 'Contact us at info@example.com or support@example.com. Visit https://example.com for more. Follow @example and use #sale or #deals.'

## When to prefer this

Choose this endpoint when you need fast, lightweight extraction of common structured entities (emails, URLs, IPs, social handles, hashtags) from free text using pattern matching — no ML inference needed. Ideal when you don't need semantic understanding, just reliable regex-based identification and deduplication with counts. Prefer over NLP-based NER tools when speed and cost matter and entity types are well-defined.

## Known failure modes

- Empty or whitespace-only input returns empty entity lists
- Malformed or non-standard formats may not be captured by regex patterns (e.g. internationalized email domains)
- Very large text inputs may hit payload size limits
- Obfuscated entities (e.g. 'user [at] example [dot] com') will not be extracted
- Non-public IPv6 addresses are not covered by the IPv4-specific extractor

## How this service works

Pull deduped lists of emails, URLs, IPv4 addresses, @mentions and #hashtags out of free text, with counts.

## Output

A structured response containing deduplicated lists for each entity type found in the input text (emails, URLs, IPv4 addresses, @mentions, #hashtags), each accompanied by an occurrence count indicating how many times that entity appeared in the original text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "emails": [
   "bob@acme.io"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/24k-labs-entity-extractor-regex-51ce807f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.24klabs.ai](https://www.zero.xyz/host/api.24klabs.ai/llms.txt)