GPT-6 Astra in OpenAI's Prism: Almost Unlimited?

Users discovered a way to use GPT-6 Astra in OpenAI's Prism editor, bypassing Codex limits.
Users discovered that in Prism, OpenAI's free scientific text editor, it is possible to select the GPT-6 Astra Extra High model and continue working even after exhausting Codex limits.
Presumably, Prism uses a separate request pool unrelated to Codex and Work restrictions. OpenAI has not confirmed this yet.
Prism itself is available to Free, Go, Plus, and Pro users. The documentation only states that the built-in assistant works on frontier models. Usage limits are not specified.
BUT: Prism is designed for LaTeX and scientific texts, so it lacks the terminal and local file access found in Codex. For reasoning, translation, and working with large texts, this currently looks like almost unlimited access to Astra.
Why it matters
AnalysisThis provides OpenAI users with access to a top-tier model for scientific tasks without the strict limitations often found in coding tools.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
OpenAI GPT (Flagship Models of the GPT Series)
The primary universal line of large language models from OpenAI (GPT-4, GPT-4o). Optimized for complex text analysis, programming, creativity, and daily intellectual tasks.
Four Resume Tips from OpenAI’s Head of Applied AI Development
Wulfie Bain, OpenAI’s head of applied AI development, shared four resume rules: keep it short, remove irrelevant details, highlight outcomes, and lead with the strongest achievements.
OpenAI Prepares Animated GIF Generation for ChatGPT
OpenAI has added experimental support for animated GIF generation in Codex, powered by the OpenAI Images API. The feature could soon arrive in ChatGPT as a replacement for static images.
Codex Skills for Beginners: Automating AI Agent Workflows
A comprehensive hands-on guide to building and executing Codex Skills: SKILL.md anatomy, explicit vs. auto-triggering, skills vs. scripts vs. tools, Skills API, and safety boundaries.