Testing 400K context with GPT-6 Astra in Codex: no extra usage for long input

daniel_mac8 · x · 2026-09-09

Daniel Mac shares a working config for pushing higher context limits in Codex:

toml

model = "gpt-6-astra"

modelcontextwindow = 400000

modelautocompacttokenlimit = 360000

A concrete, copy-paste tweak for anyone running Codex with long-context workflows.

Related event: Developers Test GPT-6 Astra's 400K Context Window in Codex(2 posts)→

Original post →

More from coding & agent

coding & agent channel →