# PDF Extraction API (Bismuth)

> PDF Extraction API (Bismuth) is a paid API for AI agents from pdf-api-production-cf1e.up.railway.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Extracts text content from PDF documents using OCR (Tesseract) and vision-mode processing

## Facts

- Endpoint: POST https://pdf-api-production-cf1e.up.railway.app/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-extraction-api-bismuth-10ce622d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8C538gT4mPyWeWhHnUhT5

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 pdf-extraction-api-bismuth-10ce622d -d '<json body>'
```

Example prompt: Can you extract all the text from this PDF file I have — it's a scanned document so it'll need OCR to read it properly?

## When to prefer this

Choose this endpoint when you need to extract text from PDF documents, especially scanned or image-based PDFs that require OCR. It is ideal for agent workflows where structured or unstructured PDF content needs to be read programmatically, particularly when documents are not machine-readable. Prefer this over general document converters when OCR and vision-mode accuracy are priorities.

## Known failure modes

- Corrupted or password-protected PDF results in extraction failure
- Low-quality scans may produce garbled OCR output
- Very large PDFs may time out or exceed processing limits
- Non-PDF file format submitted as input returns an error
- Empty or image-only PDF with no extractable text returns blank output

## How this service works

Extract text from PDF documents with OCR (Tesseract) and vision mode support. Part of the Bismuth utility API suite for AI agents.

## Output

Returns the extracted text content from the PDF document, processed using Tesseract OCR and optionally a vision mode for handling complex or scanned documents.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "file"
 ],
 "properties": {
  "file": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-extraction-api-bismuth-10ce622d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pdf-api-production-cf1e.up.railway.app](https://www.zero.xyz/host/pdf-api-production-cf1e.up.railway.app/llms.txt)