doc_to_markdown
Document to clean markdown for AI agents, $0.05 per file: PDF, DOCX, XLSX, ODT, ODS, CSV, HTML or XML in, LLM-ready markdown (or plain text) out. One call: send a url or the file as base64 (max 10 MB) — no upload step, no polling. A PDF without a text layer (a scan) returns 400 and you pay nothing; use /doc/ocr for images. USDC on Base, no account, no API key.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "doc_to_markdown"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | http(s) link to the file; we fetch it. Send this OR file_base64. | |
| format | No | markdown | |
| filename | No | Optional original filename of file_base64 (its extension helps detect the type) | |
| max_chars | No | Truncate the output to this many characters | |
| media_type | No | Optional MIME type of file_base64 (helps tell DOCX/XLSX apart) | |
| file_base64 | No | The file bytes, base64-encoded. Send this OR url. |