`--config model_reasoning_effort="high"` fails
Resolved 💬 4 comments Opened Nov 10, 2025 by estensen Closed Jan 24, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.57.0
What subscription do you have?
Business
Which model were you using?
gpt-5-codex high
What platform is your computer?
Darwin 25.0.0 arm64 arm
What issue are you seeing?
Trying to use high reason resulted in prompt to log out. Tried again and same message. Log out and log in resolved it and now able to use gpt-5-codex high
What steps can reproduce the bug?
❯ codex codex --config model_reasoning_effort="high"
╭────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.57.0) │
│ │
│ model: gpt-5-codex high /model to change │
│ directory: ~/Developer/conc │
╰────────────────────────────────────────────────╯
To get started, describe a task or try one of these commands:
/init - create an AGENTS.md file with instructions for Codex
/status - show current session configuration
/approvals - choose what Codex can do without approval
/model - choose what model and reasoning effort to use
/review - review any changes and find issues
› codex
■ Your access token could not be refreshed because your refresh token was already used. Please log out and sign in again.
What is the expected behavior?
_No response_
Additional information
_No response_
4 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Not duplicate, only seeing this trying to use
highreasoningRelated it looks like
codexis run twice when usinghighI think this bug is no longer relevant, so I'm going to close.