docs: clarify context window vs total token budget #4858
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Resolves confusion about 272k vs 400k context window mentioned in openai#4728. - Clarify that model_context_window is INPUT tokens (272k for GPT-5-Codex) - Explain model_max_output_tokens is OUTPUT tokens (128k for GPT-5-Codex) - Document total token budget = 400k (272k input + 128k output) - Add FAQ entry explaining /status display vs platform docs Fixes openai#4728
|
All contributors have signed the CLA ✍️ ✅ |
|
I have read the CLA Document and I hereby sign the CLA |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Resolves the confusion reported in #4728 about whether GPT-5-Codex has a 272k or 400k context window.
After analyzing the codebase (
codex-rs/core/src/openai_model_info.rs), I confirmed that:model_context_windowvalue represents input tokens (272,000 for GPT-5-Codex)model_max_output_tokensis output tokens (128,000)Changes
docs/config.mdto clarify thatmodel_context_windowrefers to input tokensmodel_max_output_tokensdescription to explain it's separate from input/statusshows 272k while platform docs say 400kTesting
Documentation-only changes - no code modified.
Fixes #4728