---
title: 'Safety overview: GPT-6 Astra'
link: https://openai.com/index/safety-overview-gpt-6-astra
source: openai-com
published: 2026-09-03T00:00:00Z
updated: 2026-09-03T00:00:00Z
first_seen: 2026-10-19T01:26:53.998049939Z
labels:
- safety
summary: GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.
content: feed
html: 2026-09-03-safety-overview-gpt-6-astra.html
---

GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.