Documents are processed as tokens as well, unless its bitmap is ocr'd.
Images tho are natively compatible with Multi-Modal LLMs, so theres no image->text translation layer in between.
It's that the unit of cost is different (e.g. "visual token" vs text token)
Images tho are natively compatible with Multi-Modal LLMs, so theres no image->text translation layer in between. It's that the unit of cost is different (e.g. "visual token" vs text token)