# Named-Entity Extraction: People, Orgs, Places, Products, Dates, Money, Tickers

> Named-Entity Extraction: People, Orgs, Places, Products, Dates, Money, Tickers is a paid API for AI agents from twin.unykorn.org, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-30).

Extracts named entities (people, organizations, places, products, dates, monetary values, and stock tickers) from up to 16,000 characters of input text.

## Facts

- Endpoint: POST https://twin.unykorn.org/ai/entities?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/named-entity-extraction-people-orgs-places-products-dates-money-tickers-e9677287
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eldJGifJCnnVCxSCtWzSv

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 named-entity-extraction-people-orgs-places-products-dates-money-tickers-e9677287 -d '<json body>'
```

Example prompt: Pull out all the named entities from this paragraph — I need the people, companies, locations, dates, dollar amounts, and any stock tickers mentioned: 'Apple Inc. CEO Tim Cook announced on Monday that the company would invest $430 billion in the US over the next five years, with major expansions in Austin, TX.'

## When to prefer this

Choose this endpoint when you need to identify and categorize multiple named entity types — especially the combination of financial entities (tickers, money) alongside standard NER types (people, orgs, places) — from a single text input. Ideal for financial document parsing, news article enrichment, knowledge graph population, or any workflow requiring structured entity extraction from free text up to 16,000 characters.

## Known failure modes

- Text exceeding 16,000 characters may be rejected or truncated
- Ambiguous abbreviations (e.g. 'Apple' as fruit vs company) may be misclassified
- Low-quality or highly informal text may yield missed or incorrect entities
- Payment failure via x402 protocol will prevent endpoint access
- Very short or context-free text may produce low-confidence extractions

## How this service works

Named-entity extraction: people, orgs, places, products, dates, money, tickers — Genesis402 / UnyKorn Operator Network

## Output

Returns a structured list of named entities found in the input text, categorized by type: people, organizations, places, products, dates, monetary values, and stock tickers. Each entity is labeled with its category and the text span as it appeared in the source.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "params": {
   "type": "object",
   "properties": {
    "text": {
     "type": "string",
     "description": "required, up to 16,000 chars"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/named-entity-extraction-people-orgs-places-products-dates-money-tickers-e9677287/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from twin.unykorn.org](https://www.zero.xyz/host/twin.unykorn.org/llms.txt)