OpenAI Codex: 500K context, next-message prediction, Dots agents, usage limits
The default context of GPT-6.1 Sol in Codex and ChatGPT Work has risen to 500,000 tokens, and Pro users have gained next-message prediction. Codex usage limits can include weekly caps alongside 5-hour windows.
Who is affected and how
- senior developer
- On large codebases you can try the larger context, but watch how quickly the limits are used up.
- CTO
- Factor in the weekly and 5-hour limits if your team plans heavy Codex use.
Sources
- GPT-6.1 Sol default context jumps to 500K tokens in Codex and ChatGPT Workcws-ai-news.beehiiv.com · Oct 12, 2026
- Codex Raises GPT-6.1 Sol Default Context to 500kcodeandchain.com · Oct 13, 2026
- OpenAI увеличила аудиторию ИИ-агентов Codex и ChatGPT Work в ЕС более чем в 8 раз с мая | vestkavestka.tech · Oct 14, 2026
- OpenAI Codex产品负责人：我们对，Codex 和，Work 进行了改进，以增加您获得的实际使用效果。我们通过在子代理之间重用上下文、更长时间地保持上下文缓存，以及改进请求路由来实现这一点，这些措施使我们能够提高缓存命中率。-虎嗅网huxiu.com · Oct 16, 2026
- OpenAI Adds Next-Message Predictions to Codex for Pro Users | AI Industry Todayaiindustrytoday.com · Oct 12, 2026
- OpenAI Dots: What Are OpenAI's Always-On AI Agents? - CometAPIcometapi.com · Oct 13, 2026
- OpenAI's Dots agents take over Slack on-call triage in Codex | Pivot Newspivotnews.ai · Oct 17, 2026
- Codex Pricing and Usage Limits Explained (2026) | Mintive Blogmintive.com · Oct 14, 2026
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article.