Available now

Extract PDF text API

Turn selectable PDF text into searchable content for document workflows without manually copying pages.

PDF documentSearchable textStructured data

One API key. One prepaid wallet.

PDF documentExtract textSearchable textIllustrative API workflow

Try the Extract PDF text tool

Use this tool directly. No API key required.

2 credits per successful request.

Sign in or buy credits

What it does

Extract selectable text; no OCR. REST uses multipart file, default 50 MB / 500 pages. MCP accepts base64 up to 10 MB.

Endpoint and pricing

POST /v1/documents/pdf/extract

2 credits per successful request at current catalog pricing.

Input schema (MCP)

{
  "type": "object",
  "properties": {
    "base64": {
      "type": "string",
      "contentEncoding": "base64"
    }
  },
  "required": [
    "base64"
  ],
  "additionalProperties": false
}

Output data schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "pages": {
      "type": "integer"
    },
    "characters": {
      "type": "integer"
    }
  }
}

REST request formats and response envelopes: OpenAPI specification. Discover free samples through MCP.