OpenAI Codex app adds GPT-5.3-Codex model, mid-turn steering, and file attachments
OpenAI released updates to the Codex app introducing support for GPT-5.3-Codex, a new mid-turn steering capability allowing users to redirect the model while it is actively working, and support for arbitrary file attachments. Mid-turn steering is a notable agentic UX feature that enables real-time human-in-the-loop intervention during long-running tasks. The release also includes a minor UI bug fix.
Related guides (3)
Related events (8)
OpenAI releases GPT-5.3-Codex, upgraded agentic coding model with faster inference and real-time steering
OpenAI released GPT-5.3-Codex, an incremental upgrade to GPT-5.2-Codex targeting complex software engineering tasks. The new model runs 25% faster, improves reasoning and professional knowledge, and adds better real-time collaboration features including progress updates and in-session steering. It is available immediately across ChatGPT paid plans via the Codex app, CLI, IDE extension, and Codex Cloud, with API access forthcoming.
OpenAI Codex app adds GPT-5.3-Codex-Spark model and conversation forking
OpenAI's Codex app release notes announce support for a new model variant, GPT-5.3-Codex-Spark, alongside UX features including conversation forking and a floating pop-out window. Windows alpha testing is also beginning. The update signals continued iteration on a specialized coding-focused model tier within the GPT-5 family.
OpenAI releases GPT-5-Codex: GPT-5 variant optimized for agentic coding
OpenAI has published an addendum to the GPT-5 system card introducing GPT-5-Codex, a version of GPT-5 specifically optimized for agentic coding within the Codex environment. The model features dynamic thinking-effort adjustment, scaling compute based on task complexity—responding quickly to simple queries while sustaining longer independent work on complex coding tasks. This represents a specialized derivative of GPT-5 targeting software engineering agents rather than general-purpose use.
Introducing GPT-5.3-Codex
OpenAI has announced GPT-5.3-Codex, described as a Codex-native agent combining frontier coding performance with general reasoning capabilities. The model is designed to support long-horizon, real-world technical work. The announcement positions it as an agentic coding system rather than a standalone language model.
OpenAI releases GPT-5.2-Codex to Responses API
OpenAI has released GPT-5.2-Codex via the Responses API, a variant of GPT-5.2 specifically optimized for agentic coding tasks in Codex and similar environments. The release extends the GPT-5.2 model family with a coding-specialized deployment. This is a tier-1 announcement from OpenAI's official release notes.
OpenAI releases GPT-5.4 in Codex with native computer-use and 1M context window
OpenAI has made GPT-5.4 available across all Codex surfaces — the app, CLI, IDE extension, and Codex Cloud — positioning it as the recommended model for most Codex tasks. GPT-5.4 is the first general-purpose model in Codex with native computer-use capabilities and experimental support for a 1M token context window. The release also includes stronger tool use and tool search for agentic workflows, and the model is available via API.
OpenAI Introduces GPT-5.1-Codex-Max for Agentic Coding
OpenAI has released GPT-5.1-Codex-Max, a new model optimized for agentic coding tasks within the Codex platform. The model targets long-running, project-scale software development work with improvements in reasoning and token efficiency. It is positioned as a faster and more capable successor for autonomous coding workflows.
OpenAI Codex adds goal mode GA, locked remote computer use, plugin sharing, and analytics
OpenAI shipped a batch of Codex updates including general availability of goal mode (autonomous outcome-directed execution) across app, IDE extension, and CLI, plus locked computer use for secure remote operation after Mac screen lock. Plugin sharing enables ChatGPT Business workspace members to reuse internally built plugins, and a new admin analytics console tracks usage metrics including accepted lines of code and model usage. The update also includes browser-use improvements and Appshots for attaching app windows to Codex threads.