Noxtua AI Models

Discover the Noxtua AI Model family, the foundation of our Noxtua Legal Copilot, revolutionizing legal workflows. Empower your legal practice by utilizing the Copilot to summarize, analyze, and draft legal documents with ease, all while seamlessly switching between different languages. Noxtua brings the precision and accuracy in language usage that lawyers need.

Our advanced AI models are custom-trained on exclusive high-quality legal data sets selected and meticulously labeled by legal experts specifically to train Noxtua, ensuring professional confidentiality and compliance with European data protection standards. Built on our proprietary AI models, specifically tailored for the legal domain, Noxtua is the secure and independent alternative from Germany, proudly serving as Europe's first sovereign Legal AI.

Legal Copilot

Noxtua Legal Large Language Model

The Noxtua Legal Large Language Model (LLM) is Xayn’s proprietary language model specialized on the legal domain and the basis for the Noxtua Legal Copilot. Xayn trained the model on exclusive high-quality legal data sets selected and meticulously labeled by legal experts specifically to train Noxtua. The datasets are mainly provided by legal experts such as the law firms CMS and Nordemann and dejure.org, one of Germany’s largest legal databases, as well as other members of the Legal AI Alliance. They include documents such as various court decisions from Germany and other EU countries, contract templates and interactions with contracts and lawyers as well as a synthetically generated and legally reviewed dataset. Xayn has no access to their customer’s data which is being processed during their usage of Noxtua.

Boasting a processing capacity of up to 128,000 tokens context length and 105bn parameters, the Noxtua Legal LLM is well-suited to process long legal texts.

Noxtua Voyage Embed

Noxtua Voyage Embed is a fine-tuned legal search embedding model specialized in European and German law, jointly launched by Xayn, Stanford spin-off Voyage AI and dejure.org, one of Germany’s most extensive legal databases. Noxtua Voyage Embed (voyage-law-2-xayn) outperforms Open AI’s most potent search model (text-embedding-3-large) on average by a factor of 2 on legal text benchmarks, boasting 1.7 times better search accuracy and 2.2 times better ranking quality with a 3x smaller dimensionality. This makes the model at least twice as good at finding relevant legal documents that lawyers are looking for — all while using less energy and resources to run.

The search model has been trained on a vast dataset by dejure.org and Noxtua, comprising approximately 20 billion tokens of legal texts. With a processing capacity of up to 32k tokens context length, Noxtua Voyage Embed proves invaluable for handling lengthy legal texts. This specialized model can be utilized to create custom AI search solutions centered around legal topics, as it has been trained on high-quality legal documents and is thus highly adept in the legal domain.

Press Release

As featured in

Selected Clients & Partners

“This is the most specialized Legal AI I’ve ever seen.”

Dr. Bernd-Michael Zinow
(General Counsel, EnBW — Energie Baden-Württemberg AG)
“With Noxtua, lawyers finally have a Legal AI that combines legal competency with legal compliance.”

Dr. Markus Kaulartz
(Partner at CMS, Co-Initiator of Noxtua)
“Noxtua is one of a kind in the Legal AI industry because it is trained on legal data."

Oliver García
(CEO, dejure.org)
“Noxtua delivers what others promise: high-quality output with real value for our work as IP lawyers.”

Dr. Stanislaus Jaworski (Partner at NORDEMANN)