Enable a 1M token context window in Codex with gpt-5.6-sol

dfinke · x · 2026-08-20

The author shares the exact config for a 1M token context window in Codex: in /.codex/config.toml set model = "gpt-5.6-sol", modelcontextwindow = 1000000, and modelautocompacttokenlimit = 900000. For a single session, you can pass the same flags via codex -m gpt-5.6-sol -c modelcontextwindow=1000000 -c modelautocompacttokenlimit=900000.

Original post →

More from coding & agent

coding & agent channel →