Addendum to GPT-5 system card: GPT-5-Codex

OpenAI Blog Models
openai gpt-5 coding-agent reinforcement-learning agentic-ai safety code-generation

Summary

OpenAI has released GPT-5-Codex, a version of GPT-5 optimized for agentic coding tasks, trained with reinforcement learning on real-world coding environments. It is available via Codex CLI, IDE extensions, GitHub, and ChatGPT mobile, with comprehensive safety measures including sandboxing and prompt injection mitigations.

This addendum to the GPT-5 system card shares a new model: GPT-5-Codex, a version of GPT-5 further optimized for agentic coding in Codex. GPT-5-Codex adjusts its thinking effort more dynamically based on task complexity, responding quickly to simple conversational queries or small tasks, while independently working for longer on more complex tasks.
Original Article
View Cached Full Text

Cached at: 04/20/26, 02:53 PM

# Addendum to GPT-5 system card: GPT-5-Codex Source: [https://openai.com/index/gpt-5-system-card-addendum-gpt-5-codex/](https://openai.com/index/gpt-5-system-card-addendum-gpt-5-codex/) GPT‑5‑Codex is a version of GPT‑5 optimized for agentic coding in Codex\. Like its predecessor, codex\-1, this model was trained using reinforcement learning on real\-world coding tasks in a variety of environments to generate code that closely mirrors human style and PR preferences, adhere precisely to instructions, and iteratively run tests until passing results are achieved\. This model is available locally in the terminal or IDE through Codex CLI and IDE extension, and on the cloud via the Codex web, GitHub, and the ChatGPT mobile app\. This addendum outlines the comprehensive safety measures implemented for GPT‑5‑Codex\. It details both model\-level mitigations, such as specialized safety training for harmful tasks and prompt injections, and product\-level mitigations like agent sandboxing and configurable network access\.

Similar Articles

Addendum to GPT-5.2 System Card: GPT-5.2-Codex

OpenAI Blog

OpenAI releases GPT-5.2-Codex, an advanced agentic coding model optimized for complex software engineering tasks with improved long-horizon capabilities, Windows support, and cybersecurity features. The release includes comprehensive safety documentation through a system card outlining model and product-level mitigations.

GPT-5.3-Codex System Card

OpenAI Blog

OpenAI releases GPT-5.3-Codex, the most capable agentic coding model combining frontier coding performance with advanced reasoning, featuring interactive long-running task execution and novel high-capability safeguards in the cybersecurity domain.

Introducing GPT-5.2-Codex

OpenAI Blog

OpenAI releases GPT-5.2-Codex, an advanced agentic coding model optimized for complex software engineering tasks with improvements in long-context understanding, Windows support, and cybersecurity capabilities. The model achieves state-of-the-art performance on SWE-Bench Pro and Terminal-Bench 2.0, and is now available to paid ChatGPT users with API access coming in the following weeks.

Introducing GPT-5.3-Codex

OpenAI Blog

OpenAI introduces GPT-5.3-Codex, an advanced agentic coding model that combines frontier coding capabilities with reasoning and professional knowledge, achieving state-of-the-art performance on SWE-Bench Pro and Terminal-Bench while being 25% faster than its predecessor.

Introducing upgrades to Codex

OpenAI Blog

OpenAI releases GPT-5-Codex, an optimized version of GPT-5 specialized for agentic software engineering tasks, available via API and across Codex's integrated development environment with improved code review capabilities and long-form task execution.