How to enable a 1M-token context window in Codex with GPT-5.6 Sol
SIGKITTEN · x · 2026-09-07
A documented config walkthrough shows how to lift Codex's default (performance/cost-tuned) context limit: GPT-5.6 Sol supports a documented 1,050,000-token window, letting Codex retain more code, tool output, and conversation history before auto-compaction.
Add to the top of /.codex/config.toml (before any [section]):
toml
model = "gpt-5.6-sol"
modelcontextwindow = 1000000
modelautocompacttokenlimit = 900000
Requires a model that actually supports the larger window.
More from coding & agent
- OpenAI Hits "Automated Research Intern" Milestone, Agents Log 3.1x Human Workdays — rohanpaul_ai · 2026-09-07
- A 7-Step Roadmap for Building OmniScientist, an Omni-Modal Multi-Agent Research Automation System — MaryamMiradi · 2026-09-07
- High-bandwidth error feedback to models matters more than raw model intelligence — akbirthko · 2026-09-07
- Should you learn to code in the AI era? Learn fundamentals, skip the rest until needed — dbasch · 2026-09-07
- FrankenTerm brings FrankenTUI terminal interfaces to the browser via WebAssembly — doodlestein · 2026-09-07
- Do code quality norms built for human maintainers still hold as models approach superhuman coding? — burny_tech · 2026-09-07