LightOnOCR 2 1B

unknown

Lightonai

End-to-end 1B-parameter vision-language OCR model from the French company LightOn that converts documents (PDFs, scans, images) into clean, naturally ordered text without a brittle OCR pipeline

Limits

Context16,384
InputUnknown
OutputUnknown

Modalities

Inputtext, image
Outputtext

Release info

Release2026-01-16
Last update2026-01-16
Knowledge cutoffUnknown

Provider offerings

Provider-specific prices and limits stay separate from canonical model facts.

ProviderProvider model IDInputOutputContextOutput limit
No visible provider offerings yet.

Capabilities

Attachments

Yes

Reasoning

No

Tool calling

No

Structured output

Unknown

Temperature

Yes