# Animica Entity Extraction API

> Animica Entity Extraction API is a paid API for AI agents from animica.dev, paid per call via x402, $0.001796/call, status unknown (last checked 2026-09-15).

Extracts named entities (people, organizations, locations, dates, amounts, URLs, emails, phones, wallet addresses, etc.) from free-form text

## Facts

- Endpoint: POST https://animica.dev/x402/entities
- Price: $0.001796/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/animica-entity-extraction-api-b1dca5f7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_78y8Z80uUtMydhYZNz30i

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 animica-entity-extraction-api-b1dca5f7 -d '<json body>'
```

Example prompt: Can you scan this text and extract all the people, organizations, and wallet addresses mentioned: 'Alice from Acme Corp sent 0.5 ETH to 0x1234...abcd on January 3rd'?

## When to prefer this

Choose this endpoint when you need lightweight, pay-per-call named entity recognition without managing your own NLP infrastructure or API keys. It is particularly well-suited for AI agent pipelines that need to identify crypto wallet addresses alongside standard NER types (people, orgs, locations), which most mainstream NER APIs do not support. At $0.005 per call it is cost-effective for low-to-medium volume extraction tasks.

## Known failure modes

- Empty or whitespace-only input text returns zero entities
- Invalid entity type filter values are rejected with a validation error
- Very long texts may exceed model context limits and produce partial results
- Ambiguous text may result in misclassified entity types
- Non-English text may yield lower accuracy depending on model support

## How this service works

Pull people, organizations, locations, dates, amounts, products, URLs, emails, phone numbers and wallet addresses out of text, each with the exact surface form as it appeared so you can locate it. Types are constrained by schema, so the result is always one of the known kinds. Priced per call. For high-volume use, buy prepaid credits (POST /x402/credits/buy) and send X-Animica-Credits on each request — no settlement, no gas, no per-call payment round trip. Paying in ANM on the animica:1 lane is also ~25% cheaper because we sponsor no gas there.

## Output

Returns a JSON object containing an array of extracted entities, each with a type (person, organization, location, date, amount, product, url, email, phone, wallet_address, or other), the matched text, and an optional normalized value. Also includes a total count of entities found and the model used for extraction.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "text to scan"
  },
  "types": {
   "type": "array",
   "description": "restrict to a subset of person, organization, location, date, amount, product, url, email, phone, wallet_address, other"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/animica-entity-extraction-api-b1dca5f7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from animica.dev](https://www.zero.xyz/host/animica.dev/llms.txt)