LandingAI launches ADE Gen2 with DPT-3 document parsing models
LandingAI has released Agentic Document Extraction (ADE) Gen2, a rebuild of its document-intelligence platform around the DPT-3 model family. The service is generally available, with deployment options including US or EU cloud, customer VPCs on AWS, Azure or Google Cloud, Snowflake, and on-premises or air-gapped environments. Developers can begin in the ADE playground.
Gen2 replaces Gen1’s flat chunk list with a document tree containing pages and typed blocks, including tables, figures, marginalia, signatures and barcodes. DPT-3 Pro analyzes layout and supports scanned pages, handwriting, non-Latin scripts and LaTeX. DPT-3 Verity is designed for digitally created documents and supplies a bounding box and confidence score for each word. Verity is listed as a public preview.
Billing now combines page and output-character charges. On priority processing, Pro costs 1 credit per page plus 0.5 credits per 1,000 characters, while Verity costs 0.3 credits per page plus 0.2 credits per 1,000 characters. Standard processing costs half as much and runs asynchronously. LandingAI projects 25% to 80% savings on mixed workloads, but identifies those figures as estimates. Gen1 client code requires migration to Gen2 endpoints.
Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.