# Delx PDF Text Extraction

> Delx PDF Text Extraction is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-10).

Extracts bounded UTF-8 text from a caller-supplied base64-encoded PDF using local first-party parsing, with no document storage.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/pdf-text?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-pdf-text-extraction-bf4ffcb9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NAqaeHQqh23OONfjiN9HF

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 delx-pdf-text-extraction-bf4ffcb9 -d '<json body>'
```

Example prompt: Can you extract the text from this PDF I'm sending you — here it is as a base64 string — and return up to 100000 characters of the content?

## When to prefer this

Choose this endpoint when you need to extract embedded UTF-8 text from a digitally-created PDF (not a scanned image) without sending the document to external storage or a third-party service. Ideal for privacy-sensitive documents like contracts, invoices, and resumes where no-storage guarantees matter. Use the sibling Delx PDF OCR endpoint instead when dealing with scanned or image-based PDFs that require optical character recognition.

## Known failure modes

- PDF exceeds 4 MiB decoded size — request rejected
- base64 input is malformed or not a valid PDF — parsing error returned
- max_chars set to 0 or above 200,000 — validation error
- Scanned image-only PDF with no embedded text — returns empty or minimal text (OCR is a separate product)
- Payment not completed or insufficient USDC — request blocked by x402 payment gate

## How this service works

Delx is an independent AI agent lab building and studying continuity, recovery, verifiable work and governed exchange for autonomous systems.

## Output

Returns bounded UTF-8 text extracted from the PDF (up to max_chars, default 200,000), along with a SHA-256 receipt confirming the extraction. No document is stored server-side and no external URL is fetched.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "max_chars": {
   "type": "integer",
   "default": 200000,
   "maximum": 200000,
   "minimum": 1,
   "description": "Maximum UTF-8 characters returned; extraction remains bounded."
  },
  "pdf_base64": {
   "type": "string",
   "maxLength": 5592406,
   "minLength": 1,
   "description": "One base64-encoded PDF up to 4 MiB decoded; application/pdf data URIs are accepted."
  },
  "file_base64": {
   "type": "string",
   "maxLength": 5592406,
   "minLength": 1,
   "description": "Alias for pdf_base64."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "Extracted PDF text",
  "bytes": 48210,
  "chars": 19,
  "model": "poppler-pdftotext",
  "scope": "pdf_text",
  "schema": "delx/pdf-text/v1",
  "provider": "first-party",
  "truncated": false,
  "attribution": "Text extracted locally by Delx with Poppler; no document is stored, fetched, or sent to a third-party provider. Scanned-image OCR is not included.",
  "document_id": "pdf_6fd2b8d1b8ddf0f3e9a9b2c4d5e6f708",
  "input_sha256": "6fd2b8d1b8ddf0f3e9a9b2c4d5e6f7081234567890abcdef1234567890abcdef",
  "output_sha256": "c5f7b2d4c1e7a0f9b6d2e8c3a4f5b6071234567890abcdef1234567890abcdef",
  "pages_observed": 2,
  "sale_price_usdc": 0.003,
  "upstream_cost_usd": 0,
  "gross_margin_floor_usd": 0.0028425
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-pdf-text-extraction-bf4ffcb9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)