Model Catalog
OCR
Optical Character Recognition models that convert images, scanned documents, and PDFs into machine-readable text. Ideal for document digitization, data extraction, and handwriting recognition.
5 items
allenai
olmOCR-2-7B-1025-FP8
Deployed 228 times
Image-Text-to-Text
vLLM Engine
Apache 2.0 License
GPU 1x Nvidia L40S
$ 1.8
lightonai
LightOnOCR-1B-1025
Image-Text-to-Text
vLLM Engine
Apache 2.0 License
GPU 1x Nvidia L4
$ 0.8
deepseek-ai
DeepSeek-OCR
Deployed 209 times
Image-Text-to-Text
vLLM Engine
MIT License
GPU 1x Nvidia L4
$ 0.8
rednote-hilab
dots.ocr
Image-Text-to-Text
vLLM Engine
MIT License
GPU 1x Nvidia L4
$ 0.8
nanonets
Nanonets-OCR-s
Image-Text-to-Text
vLLM Engine
MIT License
GPU 1x Nvidia L40S
$ 1.8