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.

Original post →

More from coding & agent

coding & agent channel →