Credit usage feels much higher than before and harder to sustain for real development work
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- rust
- Domain
- cli, developer-experience
Research direction
The report concerns Codex CLI 0.139.0 and credit consumption during audit, fix, and verification workflows; begin by reproducing and measuring comparable workflows against earlier versions. Done would require a concrete, agreed usage-control or predictability change, but this issue names no files, tests, or entry point.
Written by the indexing model from the issue text.
Description
What variant of Codex are you using?
0.139.0
What feature would you like to see?
I use Codex CLI heavily on a real development project, not just for testing. I use it for debugging, audits, fixes, code review, patching, and verification.
In recent versions, credit consumption feels much higher than before. For similar tasks, credits seem to run out much faster than they did a few versions ago.
This makes Codex harder to use as a stable development tool, especially on larger projects where a normal workflow requires multiple cycles of analysis, patching, and verification.
I am not asking for free usage. I have already purchased and spent a significant amount of credits. The issue is that the current consumption feels too aggressive and difficult to manage during real work.
I would like Codex to provide better control and predictability over credit usage, so independent developers can keep using it seriously without burning through credits too quickly.
Additional information
Codex is extremely useful and I want to keep using it, but the current credit usage feels much less sustainable than before.
The main problem is not paying for the tool. The problem is that, during real development work, credits can disappear very quickly before a complete audit/fix/verification cycle is finished.
This feedback comes from actual day-to-day usage on a complex project.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- Avg merge
- 1m
- Merged PRs (30d)
- 1k
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from openai/codex
-
enhancement remote
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
bug CLI windows-os
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
-
macOS sandbox blocks hw.optional.arm64 sysctl, causing Flutter to misdetect Apple Silicon as x64 Openbug CLI sandbox
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
bug CLI TUI
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
-
CLI config enhancement skills
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
kwakseongjae/auto-hwp#319 ·
-
area:cli bug filter-quality good first issue priority:medium
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
bevyengine/bevy#25861 ·
-
comp-datalake
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
ClickHouse/ClickHouse#121222 ·
-
A-linter
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
oxc-project/oxc#26863 ·