GPT-5.5 reports 258400 context window in Codex despite published 400K window

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

• #19306
• #19185
• #19208

Powered by Codex Action

### Summary Codex reports GPT-5.5 as having a 258400 token context window in live session events, while OpenAI's GPT-5.5 launch page says GPT-5.5 in Codex has a 400K context window. Official source: https://openai.com/index/introducing-gpt-5-5/ ### Environment Codex CLI: 0.124.0 Model: gpt-5.5 Plan: Pro Platform: macOS ### Observed Live session JSONL events contain: {"type":"task_started","model_context_window":258400} and token count events also report: {"type":"token_count","info":{"model_context_window":258400}} The context-window-size status line showed about 258k for GPT-5.5 after a turn, even though it had previously shown 400k and there is a separate available-context metric. ### Local evidence codex debug models reported this before a local hotfix: { "slug": "gpt-5.5", "context_window": 272000, "max_context_window": 272000, "effective_context_window_percent": 95 } That exactly explains the emitted window: `` 272000 * 0.95 = 258400 ` Local config already specified: model = "gpt-5.5" model_context_window = 400000 model_auto_compact_token_limit = 370000 ### Expected For GPT-5.5 in Codex, the total model context window displayed and emitted as model_context_window should be 400000, matching the published Codex window. Available/remaining context should be shown separately and may change with usage. ### Suspected cause The Codex model catalog appears to encode 272000 as the total GPT-5.5 Codex context window and then applies the 95% effective-window multiplier, producing 258400. The 272000 value looks like the input portion of a 400K split (272k input + 128k output`) rather than the full Codex model window.

Hi, have you found a fix for this problem

I’m seeing the same behavior as reported here: Codex / ChatGPT GPT-5.5 is showing about 258K available context instead of the published 400K Codex context window.

This appears to match the calculation in the issue body:

272000 × 0.95 = 258400

So it is not clear from the UI whether Codex is showing:

1. the true model context window,
2. an effective usable input budget after reserving output/headroom, or
3. a model-catalog/runtime mismatch.

Could the maintainers clarify whether the advertised 400K context window should appear as 400K in Codex, or whether ~258K is currently expected because of reserved output tokens and the effective-context safety margin?

If useful, I can provide local codex debug models output and session event snippets from my setup as well.

oh that might make sense, if 272 is only the input token?
then 272 input + 128 output = 400k, and it report only the input token?
and trigger the auto compact only on the input token limit?