# Aayat AI JSON Extraction

> Aayat AI JSON Extraction is a paid API for AI agents from aayatai.com, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-02).

Extracts structured JSON from any web page, PDF, Word, Excel, or raw text using a caller-supplied JSON Schema and Llama 3.3 70B

## Facts

- Endpoint: POST https://aayatai.com/extract-json?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/aayat-ai-json-extraction-79aa38c5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Zm8KMn-3Ae8VnIkbN5Zi8

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 aayat-ai-json-extraction-79aa38c5 -d '<json body>'
```

Example prompt: Pull the product name, price, and availability from https://example.com/product/123 and return it as JSON with fields: name (string), price (number), currency (string), and in_stock (boolean).

## When to prefer this

Choose this endpoint when you need to turn arbitrary web pages, PDFs, Word docs, Excel files, or raw text into a specific JSON structure you define. It is especially well-suited for ad-hoc extraction tasks where the schema varies per use case, such as scraping prices, parsing invoices, extracting contacts, or pulling event details. Prefer it over general-purpose LLMs when you need guaranteed JSON-mode output conforming to your schema and want per-call pay-as-you-go pricing with no charge on failures.

## Known failure modes

- URL unreachable or returns non-200 — extraction fails, not charged
- Document exceeds 40,000 character limit — truncated or rejected
- Schema is too complex or ambiguous — LLM may hallucinate or omit fields
- Source page requires JavaScript rendering — static content only
- PDF/Word parsing may fail for scanned or image-based documents
- Instructions conflict with schema — unpredictable field population

## How this service works

AI structured extraction: give a URL (web page, PDF, Word, Excel...) or text plus your own JSON Schema, get back JSON that fits it. POST {"url": "...", "schema": {"type": "object", "properties": {...}}, "instructions": "optional"}. Great for prices, contacts, specs, events, invoices and tables. Uses Llama 3.3 70B in JSON mode. Up to 40,000 characters of source; failures are not charged.

## Output

A JSON object conforming to the caller-supplied JSON Schema, populated with values extracted from the source URL or text. Fields not found in the source are typically null or omitted. Failures (e.g. unreachable URL, content too long) are not charged.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "maxLength": 2048,
   "description": "Page or document to read (use this or text)."
  },
  "text": {
   "type": "string",
   "maxLength": 40000,
   "description": "Text to read (use this or url)."
  },
  "schema": {
   "type": "object",
   "description": "JSON Schema describing the JSON you want back."
  },
  "instructions": {
   "type": "string",
   "maxLength": 800,
   "description": "Extra guidance, e.g. 'prices in GBP, ignore ads'."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aayat-ai-json-extraction-79aa38c5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from aayatai.com](https://www.zero.xyz/host/aayatai.com/llms.txt)