Endpoint for calculating price for image2text (OCR) inference
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
application/json Image to text conversion parameters
Image file to extract text from. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.
The OCR model to use for text extraction. Available models can be retrieved via the GET /api/v1/client/models endpoint.
"Nanonets_Ocr_S_F16"
Language code for OCR processing (optional)
"en"
Output format for extracted text
text, json "text"
Calculated price for img2txt inference.