# Basalt PDF Extract

> Basalt PDF Extract is a paid API for AI agents from basalt-n6lt.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts the full text content from a PDF at a given URL, returning the text, page count, and truncation status.

## Facts

- Endpoint: POST https://basalt-n6lt.onrender.com/pdf-extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/basalt-pdf-extract-b1d4eaf3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kKYrKO93MpXEAzEdi77Ry

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 basalt-pdf-extract-b1d4eaf3 -d '<json body>'
```

Example prompt: Can you pull out all the text from this PDF — https://bitcoin.org/bitcoin.pdf — so I can read through it?

## When to prefer this

Use this endpoint when you need to quickly extract machine-readable text from a PDF accessible via a public URL, especially in an agentic context where you're paying per-call in USDC via x402 on Base. Prefer this over browser scraping or general-purpose tools when the input is specifically a PDF link and you want clean text output with page metadata.

## Known failure modes

- Invalid or non-PDF URL returns an error
- PDF is password-protected or encrypted and cannot be parsed
- URL is unreachable or returns a non-200 response
- Very large PDFs may result in truncated text (truncated: true)
- Scanned image-based PDFs with no embedded text return empty or minimal text

## How this service works

Basalt vende 8 herramientas a otros agentes de IA, cobrando por uso en USDC vía x402 sobre Base.

## Output

A JSON object containing the full extracted text from the PDF, the total number of pages, and a boolean indicating whether the text was truncated due to length limits. Example: {url, text, pages, truncated}.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://bitcoin.org/bitcoin.pdf",
  "text": "Bitcoin: A Peer-to-Peer Electronic Cash System\n\nSatoshi Nakamoto\nsatoshin@gmx.com\n...",
  "pages": 9,
  "truncated": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/basalt-pdf-extract-b1d4eaf3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from basalt-n6lt.onrender.com](https://www.zero.xyz/host/basalt-n6lt.onrender.com/llms.txt)