PDF to Text API - extract text from PDF (OCR for scans)
pdf_to_textExtract the text of a PDF with page markers. Scanned pages are read with OCR (English, German, Bulgarian; first 5 scanned pages per call). Runs on our server, files are deleted right after the call, nothing stored. Free: 25 calls/day per IP. Paid: $0.005 per call via x402 at https://radarbg.com/x402/pdf-to-text.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"fileName": "sample.pdf",
"fileContent": "JVBERi0xLjMKJenr8b8KMSAwIG9iago8PAovQ291bnQgMQovS2lkcyBbMyAwIFJdCi9NZWRpYUJveCBbMCAwIDU5NS4yOCA4NDEuODldCi9UeXBlIC9QYWdlcwo+PgplbmRvYmoKMiAwIG9iago8PAovT3BlbkFjdGlvbiBbMyAwIFIgL0ZpdEggbnVsbF0KL1BhZ2VMYXlvdXQgL09uZUNvbHVtbgovUGFnZXMgMSAwIFIKL1R5cGUgL0NhdGFsb2cKPj4KZW5kb2JqCjMgMCBvYmoKPDwKL0NvbnRlbnRzIDQgMCBSCi9QYXJlbnQgMSAwIFIKL1Jlc291cmNlcyA2IDAgUgovVHlwZSAvUGFnZQo+PgplbmRvYmoKNCAwIG9iago8PAovRmlsdGVyIC9GbGF0ZURlY29kZQovTGVuZ3RoIDExMgo+PgpzdHJlYW0KeJwzUvDiMtAzNVco53IKUdB3M1QwNNIzMFAISVNwDQEJGRvqGVoomFua6pmbK4SkKGh45pXlZyanKhgZGJnpGhgYKrhWJOYW5KQq+JSkaCqEZKHqMzPXMzEC6wvJL0nMAZpuADLeNTQIphYAsdgfAQplbmRzdHJlYW0KZW5kb2JqCjUgMCBvYmoKPDwKL0Jhc2VGb250IC9IZWx2ZXRpY2EKL0VuY29kaW5nIC9XaW5BbnNpRW5jb2RpbmcKL1N1YnR5cGUgL1R5cGUxCi9UeXBlIC9Gb250Cj4+CmVuZG9iago2IDAgb2JqCjw8Ci9Gb250IDw8L0YxIDUgMCBSPj4KL1Byb2NTZXQgWy9QREYgL1RleHQgL0ltYWdlQiAvSW1hZ2VDIC9JbWFnZUldCj4+CmVuZG9iago3IDAgb2JqCjw8Ci9DcmVhdGlvbkRhdGUgKEQ6MjAyNjExMTUyMDEzNTRaKQo+PgplbmRvYmoKeHJlZgowIDgKMDAwMDAwMDAwMCA2NTUzNSBmIAowMDAwMDAwMDE1IDAwMDAwIG4gCjAwMDAwMDAxMDIgMDAwMDAgbiAKMDAwMDAwMDIwNSAwMDAwMCBuIAowMDAwMDAwMjg1IDAwMDAwIG4gCjAwMDAwMDA0NjkgMDAwMDAgbiAKMDAwMDAwMDU2NiAwMDAwMCBuIAowMDAwMDAwNjUzIDAwMDAwIG4gCnRyYWlsZXIKPDwKL1NpemUgOAovUm9vdCAyIDAgUgovSW5mbyA3IDAgUgovSUQgWzwyMzc0NENDOUY1ODJDN0FCMkFGMjQ5MDVFRTQ3RjgzNz48MjM3NDRDQzlGNTgyQzdBQjJBRjI0OTA1RUU0N0Y4Mzc+XQo+PgpzdGFydHhyZWYKNzA4CiUlRU9GCg=="
},
"name": "pdf_to_text"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | Or several files: [{fileName, fileContent (base64)}] | |
| fileName | No | File name with extension, e.g. report.pdf | |
| language | No | OCR language for scanned pages | eng |
| pageMarks | No | Insert a line with the page number | |
| fileContent | No | The file as base64 (a data: URI is fine) |