# NoJunk AI Text – Extract

> NoJunk AI Text – Extract is a paid API for AI agents from nojunk-ai-text.mick8511.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-16).

Extracts named fields from text into strict JSON using LLM intelligence, returning null for any field not found in the source text and never inventing data.

## Facts

- Endpoint: POST https://nojunk-ai-text.mick8511.workers.dev/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nojunk-ai-text-extract-49219944
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RtwVEUC8TRNn8YSDWD1j3

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 nojunk-ai-text-extract-49219944 -d '<json body>'
```

Example prompt: Extract the CEO name, company name, revenue, headquarters, and revenue growth percentage from this text and return them as JSON — if any field isn't mentioned, leave it null: 'Acme Corp, led by Jane Doe, reported $4.2 billion in revenue this quarter, representing 12% year-over-year growth.'

## When to prefer this

Use this endpoint when you need strict, hallucination-resistant field extraction — it returns null rather than guessing, which is critical for structured data pipelines. Prefer it over general-purpose LLM calls when you need consistent JSON schema output, pay-per-result pricing (no charge on failure), and up to 24,000 characters of context. Best for agents that need to parse documents, reports, or articles into database-ready records without post-processing cleanup.

## Known failure modes

- Text exceeds 24,000 character limit — request rejected
- No fields specified or field list exceeds 20 items — validation error
- Payment not processed — 402 response, no charge
- LLM returns low-confidence result — confidence field reflects this
- Text is in an unsupported encoding or binary format — extraction fails
- Ambiguous field names lead to unexpected null returns — use descriptive field definitions object instead of plain array

## How this service works

NoJunk AI Text extract: Extract named fields from text into strict JSON; null for anything the text does not state, nothing invented.

## Output

A JSON object with a `data` key containing each requested field mapped to its extracted value (or null if absent from the text), plus `model` (the LLM used), `confidence` (high/medium/low), `notes` (explanations for nulls or ambiguities), `usage` (prompt and completion token counts), and `generated_at` timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The text to extract from (1 to 24000 characters)"
  },
  "fields": {
   "type": [
    "array",
    "object"
   ],
   "description": "Fields to extract: an array of 1-20 field names, or an object {name: description}"
  },
  "instructions": {
   "type": "string",
   "description": "Optional extra extraction instructions"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "ceo": "Jane Doe",
   "company": "Acme Corp",
   "revenue": "$4.2 billion",
   "headquarters": null,
   "revenue_growth_pct": 12
  },
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  "notes": "Headquarters is not mentioned in the text.",
  "usage": {
   "prompt_tokens": 260,
   "completion_tokens": 48
  },
  "confidence": "high",
  "generated_at": "2026-10-15T12:00:00.000Z"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nojunk-ai-text-extract-49219944/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from nojunk-ai-text.mick8511.workers.dev](https://www.zero.xyz/host/nojunk-ai-text.mick8511.workers.dev/llms.txt)