OpenAI Codex Update: 94% Faster Loading, 98% Fewer Requests
OpenAI's Codex performance update cuts long conversation loading from 27.6s to 1.7s, reduces requests by 98%, and lowers memory usage by 41%.
OpenAI showed the results of a major Codex performance update that is set to be released next week.
It should noticeably speed up the loading of very long conversations while reducing memory consumption and the number of requests.
In an extreme test with a conversation of 741 messages and a volume of 231 MB:
• loading time dropped from 27.6 to 1.7 seconds
• the number of requests decreased by 98%
• the number of loaded conversation items became 99.6% smaller
• the app's memory usage growth decreased by 41%
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesOpenAI Frontier Models and Codex Now Available on AWS via Bedrock
OpenAI’s frontier models and Codex are now on AWS through Amazon Bedrock, enabling secure, compliant adoption with existing AWS governance and future integrations.
OpenAI Codex Build iOS Apps: Run, Preview, Hot Reload in One Place
Codex Build iOS Apps plugin runs iOS apps in Codex, opens SwiftUI Preview, and hot reloads changes—ending the copy-paste, build, screenshot loop.
Oh-my-codex: A Workflow Layer That Supercharges Codex Sessions
Oh-my-codex adds a consistent clarification→execution flow, canonical skills, and persistent .omx/ state to make Codex sessions more powerful.