How to enable 1M context window in Codex
soumitrashukla9 · x · 2026-08-17
Guide on enabling a 1M-token context window in Codex for GPT-5.6 Sol by setting modelcontextwindow = 1000000 in the config file. Note that tokens beyond the default limit count double against usage limits.
Related event: Codex Tutorial: Enable 1M Token Context(2 posts)→
More from coding & agent
- Using Claude to Analyze 10k Support Emails for Feature Requests — mhmazur · 2026-08-17
- "Assume Author is an Idiot": Prompt Engineering Stricter Code Agents — aronchick · 2026-08-17
- Multi-Agent Workflow: Grok Bot Playtests and Fixes Cursor-Built Game — DeryaTR_ · 2026-08-17
- AI agents make coding non-linear: idle waits vs overload bursts — StewartalsopIII · 2026-08-17
- Hands-on with Qwen 3.8 27B: Default 'xhigh' reasoning causes hilarious over-thinking — Simon Willison · 2026-08-17
- Open-source tutorial: Build an AI telephony agent with VideoSDK and SIP trunking for inbound/outbound calls — tom_doerr · 2026-08-17