You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
1m context window gone after Gpt 5.5 Release. #19208
What version of the Codex App are you using (From “About Codex” dialog)?
26.422.20832
What subscription do you have?
Pro plan
What platform is your computer?
Mac os
What issue are you seeing?
I've enable 1m context window via codex config since the release of GPT 5.4 and it was working exceptionally well. today Codex announces GPT 5.5 stating it supports 1m Context window but weirdly thought it's gone in the codex app.
What steps can reproduce the bug?
Just launch the codex app and enable 1m context window in config.toml file
In Codex, GPT‑5.5 is available for Plus, Pro, Business, Enterprise, Edu, and Go plans with a 400K context window. GPT‑5.5 is also available in Fast mode, generating tokens 1.5x faster for 2.5x the cost.
Which 400K context window is fine for me, and it can keep good proformance. However, 258K is not 400K.
Could Codex fix this ASAP?
The 400K context window includes space for 272K of input + 128K of output. The 258K value is somewhat less than the full 272K to guarantee that compaction is possible. These are the same default values that have been in place for gpt 5.4, gpt 5.3-codex and gpt 5.2.
Reacted by Teneko and Lam Nguyen
Reacted by BuYoungLee, Joshua Angulo González, Ross Cawston, Yitao Jiang, abyss, Muhammad Zia, Node Network, 箱庭XTer, JoyLin, Jtsgxh and 29 more
The 400K context window includes space for 272K of input + 128K of output. The 258K value is somewhat less than the full 272K to guarantee that compaction is possible. These are the same default values that have been in place for gpt 5.4, gpt 5.3-codex and gpt 5.2.
Sorry, but why did you closed the issue, if the main problem is that 1m tokens context is gone?
Reacted by Yvan, Julien Renouard, Patrick Fu, AX, Anton Standrik, HarryPitsillides, Hugh Hoang, MeXenon, Akatum, Violet and 3 more
Activity
github-actions commentedon Apr 23, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
BillDuke13 commentedon Apr 23, 2026
cli v0.124.0 has this issue too
cccat6 commentedon Apr 23, 2026
I read the release page https://openai.com/index/introducing-gpt-5-5/ it says
Which 400K context window is fine for me, and it can keep good proformance. However, 258K is not 400K.
Could Codex fix this ASAP?
etraut-openai commentedon Apr 23, 2026
The 400K context window includes space for 272K of input + 128K of output. The 258K value is somewhat less than the full 272K to guarantee that compaction is possible. These are the same default values that have been in place for gpt 5.4, gpt 5.3-codex and gpt 5.2.
Cinea4678 commentedon Apr 24, 2026
gpt 5.5 supports 1M context window. Please reopen issue
IlyaShorin commentedon Apr 24, 2026
Sorry, but why did you closed the issue, if the main problem is that 1m tokens context is gone?
jrenouard commentedon Apr 24, 2026
HarryPitsillides commentedon Apr 24, 2026
Wtf why is this closed? Is this OpenAI stance now no 1M context? Then why use this vs Claude were 1M is the default?
defteame commentedon Apr 24, 2026
why is this closed? this is clear regression
AlchemistChaos commentedon Apr 25, 2026
only see 258k in the codex app... is it 400k or 1M? very unclear
2-fly-4-ai commentedon Apr 25, 2026
Why is this closed? Mayor regression with no announcement. Wasting everyones time. Must we just guess what's gonna happen?
etraut-openai commentedon Apr 25, 2026
Let's continue the discussion in #19464.