Astra for Law pairs GPT-6 Astra with a 230-million-URL legal index

OpenAI announced Astra for Law on September 17, combining GPT-6 Astra with legal-specific settings, tools, context, instructions, and a dedicated U.S. legal search index. It is a configuration built for legal work, not a separate new base model.

Legal retrieval across more than 230 million URLs

The index covers U.S. case law, statutes, regulations, court rules, and administrative decisions, with new sources added daily. It incorporates CourtListener material from the nonprofit Free Law Project, whose collection covers more than 99.9 percent of published U.S. precedential case law.

A higher reported score, with a private-set caveat

OpenAI tested the complete setup on 200 U.S. legal research questions from a private validation set of Vals AI’s Legal Research Bench. At the highest reasoning effort, the company reported a 54.0 percent overall correctness pass rate for Astra for Law, compared with 38.7 percent for GPT-6 Astra using web search alone—a 40 percent relative improvement. OpenAI also reported 24 percent more reference cases on case-law questions and up to 54 percent more relevant passages from the correct opinions on an audited set. These vendor-reported results do not establish accuracy across every legal matter or remove the need for lawyer review.

Controlled access puts governance alongside capability

Selected law firms will receive initial access through Trusted Access in ChatGPT and Codex, while API availability is described as coming soon. The model picker lists GPT-6 Astra Law, and the announced API identifier is gpt-6-astra-law. Eligible firms can use Zero Data Retention on the API, while ChatGPT Enterprise usage is excluded from human review by default. Firms still need to apply their own permissions, ethical walls, confidentiality practices, and professional review when bringing the system into legal work.