Dharma AI releases 2B Field Extractor for structured JSON
Dharma AI released the 2-billion-parameter Dharma Field Extractor, which accepts document images and returns typed fields as structured JSON. It supports open-ended extraction without a schema and schema-directed extraction with named, typed fields, including nested invoice line items, without per-document-type fine-tuning. Dharma AI reports that the model beat four general-purpose frontier configurations on its benchmark and cost 6 to 147 times less, but these comparisons are vendor-reported and depend on the company’s evaluation setup.
The release offers a specialized, self-hosted alternative for high-volume document-processing workloads that need structured output rather than full-page transcription.
A 2-billion-parameter model that extracts exactly the fields you ask for, from any document type, outperforming every frontier LLM we tested, at a fraction of the cost.

In April, we released DharmaOCR-LITE, a model specialized for OCR across a wide range of documents, from contracts and court filings to invoices, IDs and forms. The paper behind it made a narrow, well-measured case for domain specialization: a smaller model trained closer to its task beating general-purpose frontier APIs on that task.
OCR gives you the text on a page, faithful to the original formatting. That's exactly what you want when the job is the whole document, like a contract you'll read end to end or a manuscript you're digitizing.
However, there's a different use case: you don't want the page, you want specific fields out of it, in a shape a system downstream can consume. Every line item on an invoice, as a list. The patient name, exam type and date from a medical requisition, ready to schedule. The fields off an ID, mapped to the columns of an employee record.
#Dharma AI#Dharma Field Extractor#DharmaOCR-LITE#Claude Opus 5#GPT-5.6 Luna#GPT-5.6 Sol