Documented 1M context window is unavailable in Codex CLI or Desktop App

Resolved 💬 5 comments Opened Aug 17, 2026 by jrf1001 Closed Aug 19, 2026

💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What is the type of issue?

Documentation is incorrect

What is the issue?

As clearly explained by Tibo, GPT-5.6 Sol within Codex supports a 1M context window:
https://x.com/thsottiaux/status/2089082893804896524

Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. ... model_context_window = 1000000 model_auto_compact_token_limit = 900000

This runs directly contrary to the written changes made in the Codex CLI 0.144.6 changelog where it explicitly states:

Refreshed bundled instructions for GPT-5.6 Sol, Terra, and Luna, and corrected their context windows to 272,000 tokens. (https://github.com/openai/codex/pull/33972, https://github.com/openai/codex/pull/34009)

Tibo's suggestion of model_context_window USED to work before that patch, but as it stands what Tibo suggested is simply not true and does not work in the Codex App or CLI, making this change does not increase the context window. If you boot the CLI with that and run /status it reports 1M, but after your first message it reports the real capped limit.

This can be replicated with the codex CLI via codex debug models --bundled reporting {"slug":"gpt-5.6-sol","context_window":272000,"max_context_window":272000}.

There is clearly a gap in understanding between what OpenAI believe can be accessed, versus what is publicly documented and available. Please help us understand.

Where did you find it?

_No response_

View original on GitHub ↗

5 Comments

github-actions[bot] contributor · 11 days ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

#37730

Powered by Codex Action

jrf1001 · 11 days ago

In the last 30 minutes after opening this ticket Tibo has posted that he just now "flipped the switch and works for usage through ChatGPT accounts now too"

VolkumDev · 11 days ago

In the last 30 minutes after opening this ticket Tibo has posted that he just now "flipped the switch and works for usage through ChatGPT accounts now too"

Yes the Codex team is disconnected as fuck, we have had this issue since APRIL (https://github.com/openai/codex/issues/19464) and only now we are finally allowed to use 1M?

"I'll provide updates when available" they said, quiet since. It took Tibo's finding out MONTHS after to "flip the switch", it was as easy as that?

Goes to show how capable OpenAI team is /s

loveritsu929re · 10 days ago

Any update? This can be easily verified:

codex -m gpt-5.6-sol -c model_context_window=1000000 -c model_auto_compact_token_limit=900000
/status
hello
/status

torrestomas-3f · 10 days ago

I have a related but distinct report: #39144.

On the same fresh /models response and ETag, Terra and Luna receive max_context_window = 872000, while Sol remains at 272000. This may help distinguish a general override/config issue from a Sol-specific rollout or catalog-entitlement mismatch.