Reading · by Datalab
Surya
Read scans in 90 languages in correct reading order, locally.
document, image → text, data
- Way in
- Official APINo sign-up, no key
- To start
- Freecode Apache-2.0; weights OpenRAIL-M variant
- Runs
- On your Mac
- Checked
- Nov 3, 2026Prices as of that day
What it can do 1
OCR + layout + tables + reading order for document pagesneeds llama-server binary (no brew here: use llama.cpp release tarball), or opt-in MLX backend via mlx_vlm.server (SURYA_INFERENCE_BACKEND=mlx)document, image → text, datafree (local)
Does the same job
Prices and limits as of Nov 3, 2026, from Datalab’s own pages. They change; check before you rely on them.Not affiliated with Datalab. Not advice.Something wrong?