HeadsUpAI

OpenAI Targets Tenfold Speed Increase for Codex Agentic Coding This Year

· Updated

OpenAI is targeting a tenfold performance increase for its Codex agentic coding platform within 2026. This follows the launch of Codex /fast mode, providing a 1.5x speedup for GPT-5.4 users. The team confirmed they have a clear engineering path to achieve this order-of-magnitude leap.

Speed is the primary bottleneck for agentic workflows where models reason through multiple steps. This performance push builds on recent efforts to enable unattended engineering automations that execute long-running tasks without constant human intervention. A 10x improvement would move the user experience from waiting on an agent to real-time collaboration.

Currently, you can access the performance ceiling by using the /fast command in the Codex CLI. This roadmap extends OpenAI's focus on developer experience, following the release of tools for visualizing agent logs to help debug complex sessions. Learning the platform now prepares you for these upcoming speedups.

View the full update on openai.com
Tibo
Tibo
@thsottiaux
X

If you think Codex with GPT-5.4 is /fast already… we have line of sight for at least an order of magnitude in speedups this year. Good engineering compounds and it’s never been a better time to learn Codex.

18retweets562likes
View on X

Still wondering? A few quick answers below.

Currently, OpenAI Codex running on the GPT-5.4 model offers a /fast mode that delivers a 1.5x increase in token velocity compared to standard generation. However, OpenAI has announced a roadmap to achieve at least a 10x speedup—an order of magnitude—later this year as engineering improvements compound across the platform's infrastructure.

OpenAI expects to deliver the 10x performance increase for Codex within the 2026 calendar year. While the current /fast mode provides immediate incremental gains of 1.5x, the team has confirmed they have a clear line of sight for much larger speedups as they optimize the engineering behind the GPT-5.4 model integration.

The /fast mode is a performance toggle for OpenAI Codex that increases token generation speed by 1.5x without reducing the model's intelligence or reasoning capabilities. It is specifically designed for the GPT-5.4 model to help developers maintain their flow state during complex agentic coding tasks, though it consumes credits at a higher rate.

Share this update