OpenAI expands Codex and its API at DevDay with security scans, a Decisions API, and Ultrafast
Published on · Sep 30 · Wed Source · The Decoder

OpenAI expands Codex and its API at DevDay with security scans, a Decisions API, and Ultrafast

At DevDay 2026, OpenAI upgraded Codex with reusable cloud environments, GitHub security scans, and desktop code review. The Agents API gained Computer Use, a new Decisions API launched, and an Ultrafast premium tier was introduced.

Key Takeaways

  • Key Highlight:At DevDay 2026, OpenAI upgraded Codex with reusable cloud environments, GitHub security scans, and desktop code review. The Agents API gained Computer Use, a new Decisions API launched, and an Ultrafast premium tier was introduced.
  • Innovation & Tech:Highlights advancements in OpenAI, API, Agent, demonstrating rapid progress in model capabilities.
  • Industry Impact:Reported via The Decoder, offering actionable signals for developers and technology leaders.
KeywordsOpenAIAPIAgentCodexDevDayDecisionsUltrafastAt

OpenAI used its DevDay 2026 event to roll out a broad set of developer-facing updates centered on its Codex coding tool and platform APIs.

Codex now supports reusable cloud environments, automated security scans for GitHub repositories, and a code review interface within the desktop app, aiming to make AI-assisted development safer and more integrated into existing workflows.

The Agents API added Computer Use capabilities, allowing agents to interact with desktop interfaces, while the new Decisions API is designed for fast, single-decision calls rather than multi-step agent workflows.

A premium Ultrafast tier was also announced, suggesting OpenAI is segmenting performance levels for developers willing to pay for lower-latency inference.

This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.

Industry Insights & Analysis

As artificial intelligence rapidly evolves, breakthroughs surrounding OpenAI, API, Agent, Codex are shifting toward scalable, robust real-world implementations.

Driven by both open-source ecosystems and proprietary model architectures, the integration between compute optimization, data engineering, and agentic workflows is accelerating. This development provides a strategic benchmark for upcoming AI tooling and developer workflows.