# Unstructured Text to JSON Extractor (Claude Haiku)

> Unstructured Text to JSON Extractor (Claude Haiku) is a paid API for AI agents from x402-seller-0ay3.onrender.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Extracts structured JSON fields from unstructured text using a caller-provided JSON Schema, powered by Claude Haiku 4.5

## Facts

- Endpoint: POST https://x402-seller-0ay3.onrender.com/api/ai/extract
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/unstructured-text-to-json-extractor-claude-haiku-d442ef6f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LW-BTeiNsdiC1vzAFJFQP

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 unstructured-text-to-json-extractor-claude-haiku-d442ef6f -d '<json body>'
```

Example prompt: Extract the invoice number, customer name, total amount, and due date from this text as JSON — here's the text: 'Invoice #4521 for Jane Doe. Total due: $340.00. Payment due by September 15, 2026.' Use a schema with fields invoice_number, customer, total, and due_date.

## When to prefer this

Choose this endpoint when you have unstructured or semi-structured text (emails, invoices, descriptions, transcripts) and need to pull specific fields into a machine-readable JSON object using a schema you define. It is ideal for any schema that varies per use case since you supply the schema dynamically. Prefer this over regex or rule-based parsers when the text is natural language and field positions are inconsistent. If you need to extract from a web URL rather than raw text, use the sibling web-scrape endpoint instead.

## Known failure modes

- Text exceeds 8000 character limit — request will be rejected or truncated
- Malformed or invalid JSON Schema in the schema field causes extraction failure
- Fields not present or inferable from the source text will be null or omitted
- Ambiguous text may cause Claude to hallucinate plausible-sounding but incorrect field values
- Schema with overly complex nested structures may reduce extraction accuracy
- Rate limiting or service unavailability on the Render hosting platform

## How this service works

Extract JSON from text — pull structured fields (invoice data, contact info, product specs, any custom schema) out of unstructured text, via Claude Haiku 4.5. JSON body: {text: string (max 8000 chars), schema: object (JSON Schema describing the fields to extract)}.

## Output

Returns a JSON object with a 'data' key containing the extracted fields as specified by the caller's JSON Schema — e.g. {"data": {"invoice_number": "4521", "customer": "Jane Doe", "total": 340, "due_date": "2026-09-15"}}. Field names and types match the schema provided in the request.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Source text (max 8000 chars)."
  },
  "schema": {
   "type": "object",
   "description": "JSON Schema describing the fields to extract."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "total": 340,
   "customer": "Jane Doe",
   "due_date": "2026-09-15",
   "invoice_number": "4521"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/unstructured-text-to-json-extractor-claude-haiku-d442ef6f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-seller-0ay3.onrender.com](https://www.zero.xyz/host/x402-seller-0ay3.onrender.com/llms.txt)