Reading · by Baidu PaddlePaddle

PaddleOCR

Read scanned pages in 100 languages into text and tables.

document, image → text, data
Way in
Official APINo sign-up, no key
To start
Freeopen source (Apache-2.0)
Runs
On your Mac
Checked
Nov 3, 2026Prices as of that day

What it can do 1

Parse PDFs/images into structured text, tables and layoutPaddlePaddle CPU wheels on macOS for classic PP-OCR; PaddleOCR-VL-1.6’s card tells macOS users to use Docker for the native pipeline, else serve the VLM via GGUF/llama-server (vl_rec_backend=llama-cpp-server) or MLX-VLMdocument, image → text, datafree (local)

Does the same job

Prices and limits as of Nov 3, 2026, from Baidu PaddlePaddle’s own pages. They change; check before you rely on them.Not affiliated with Baidu PaddlePaddle. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.