Three-line config unlocks 1M context in Codex for GPT-5.6 Sol, but pricing doubles past 272K tokens

Developers can enable a 1 million token context window for the GPT-5.6 Sol model in the Codex client by tweaking a config file — a feature Teknium says is now open to all users.

Confirmed

• Developer Tibo shared the unlock method: simply add three lines at the top of /.codex/config.toml — including model and setting modelcontextwindow to 1000000 — then restart.
• While OpenAI's official documentation has long supported this, Codex previously imposed a default limit; Teknium now confirms it is available to everyone.

2026-08-17 ~ 2026-08-17 · 9 related posts

• [source] How to enable 1M-token context window in Codex — kimmonismus · 2026-08-17
• OpenAI Codex now supports 1M token context window — Moh1tAgarwal · 2026-08-17
• Unlock 1M Context for GPT-5.6Sol in Codex with Simple Config — 量子位 · 2026-08-17
• [source] Codex Opens 1 Million Context to All After Technical Discussion — Teknium · 2026-08-17
• ChatGPT Extended to 1M Context Window — heypearlai · 2026-08-17
• [source] Unlocking ChatGPT's 1M Context Window: Costs Double After 272K Tokens — eyishazyer · 2026-08-17
• Debate on 1M context: Utility vs. double cost tradeoff — eyishazyer · 2026-08-17

2 near-duplicate retellings: soumitrashukla9 · SimplyAnnisa