DeepSeek · OCR
DeepSeek-OCR
DeepSeek OCR model for extracting text from images with high accuracy. Supports URLs and base64 images.
Evidence and sources
Sources: Neosantara Inference data, Models.dev data, Hugging FacePrimary data from Neosantara Inference
from Models.dev: name, weights availability
from Hugging Face: release date
Advantages and trade-offs
Compared with 10 representative OCR models
Advantages
Trade-offs
Shorter context than most peers
Input & output
as stated by the model's providersText
Images
Text
Also known as: deepseek-ai/deepseek-ocr, novita/deepseek/deepseek-ocr
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works