OCR a PDF or image
ocrRead a PDF or image and return its text as Markdown (tables kept as tables) or JSON blocks. Pass file_url for a public link, or file_base64 for file contents. Models jina/jina-ocr and deepseek/deepseek-ocr are free; auto picks the best model for the document.
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": "ocr"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model ID from list_models, or auto (default). | |
| pages | No | Page range such as 1-5,8. Default all pages. | |
| format | No | Output format. Default markdown. | |
| file_url | No | Public http(s) URL of a PDF, PNG, JPG, WebP or GIF. | |
| filename | No | File name with extension, recommended with file_base64. | |
| file_base64 | No | Base64 file contents, instead of file_url. |