# Inference402 Extract – Named Entity & Field Extraction

> Inference402 Extract – Named Entity & Field Extraction is a paid API for AI agents from inference402.worlddata402.workers.dev, paid per call via x402, $0.008/call, status unknown (last checked 2026-10-19).

Extracts specified named fields (dates, names, amounts, organizations, custom fields, etc.) from free-form text using Llama 3.3 70B, paid per-call in USDC via x402

## Facts

- Endpoint: GET https://inference402.worlddata402.workers.dev/v1/extract?utm_source=zero.xyz
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/inference402-extract-named-entity-field-extraction-5e6bfab9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VnWX6WimYX4e5SqDID66t

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 inference402-extract-named-entity-field-extraction-5e6bfab9
```

Example prompt: Extract the invoice number, dates, amounts, and organization names from this text: 'Invoice #4471 dated 2026-03-02 from Nile Tech LLC for EGP 12,500, billed to Omar Khaled.'

## When to prefer this

Choose this endpoint when you need to pull specific named fields from unstructured or semi-structured text without writing custom regex or NLP pipelines. It is ideal for invoice parsing, contract analysis, form data extraction, and any scenario where you need flexible, LLM-powered field extraction on a pay-per-call basis with no API key or account setup. Prefer this over general chat endpoints when the task is purely extraction into a structured JSON output.

## Known failure modes

- Text exceeds 8000 character limit — request will be rejected or truncated
- Empty or missing `fields` array — no extraction targets specified
- Requested fields not present in text — returns empty arrays for those keys
- Model hallucination — LLM may infer plausible but incorrect values for ambiguous text
- Payment failure via x402 — USDC balance insufficient or Base mainnet transaction error
- Rate limiting or Cloudflare Worker timeout on very long processing

## How this service works

Pay-per-call AI inference for agents: chat (Llama 3.3 70B / 3.1 8B), structured JSON, summarize, translate (incl. Egyptian Arabic), extract, classify, sentiment, keywords, rewrite, embeddings, moderation, vision and speech-to-text. USDC on Base mainnet over x402. No API key, no account.

## Output

A JSON object with a `data` key containing arrays of extracted values keyed by each requested field name (e.g. dates, names, amounts, organizations, invoice_number), plus a `model` field indicating the Llama model used for extraction.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 8000
  },
  "fields": {
   "type": "array",
   "items": {
    "type": "string",
    "maxLength": 64
   },
   "maxItems": 20,
   "minItems": 1,
   "description": "Field names to extract, e.g. names, dates, amounts, organizations, locations, emails, or custom like invoice_number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "dates": [
    "2026-03-02"
   ],
   "names": [
    "Omar Khaled"
   ],
   "amounts": [
    "EGP 12,500"
   ],
   "organizations": [
    "Nile Tech LLC"
   ],
   "invoice_number": [
    "4471"
   ]
  },
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/inference402-extract-named-entity-field-extraction-5e6bfab9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from inference402.worlddata402.workers.dev](https://www.zero.xyz/host/inference402.worlddata402.workers.dev/llms.txt)