Codex usage limit incorrectly reached after Pro subscription renewal
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- PR merge metrics
- PR metrics pending
Description
Issue
My ChatGPT Pro subscription expired and was successfully renewed today. The Usage page correctly shows:
- Active Pro plan ($100/month)
- General weekly usage remaining: 56%
- GPT-5.3-Codex-Spark weekly usage remaining: 100%
- General usage reset time: August 20, 2026 at 12:31
However, Codex still says that I have reached my usage limit and cannot run any task:
You've reached your usage limit. Upgrade your plan or purchase credits to continue, or try again after August 20, 2026 at 12:31.
Troubleshooting completed
- Signed out and signed back in
- Completely restarted the desktop app
- Confirmed that the app is up to date
- Created a new chat
- Tried different models
- Tried GPT-5.3-Codex-Spark, which shows 100% remaining
- The issue still occurs
When using GPT-5.6 Sol, I also received:
Error running remote compact task: {"detail":"The 'gpt-5.6-sol' model is not supported when using Codex with a ChatGPT account."}
The billing and Usage page appears correct, but the Codex execution service seems to treat my remaining quota as zero. This appears to be an entitlement or quota synchronization issue after subscription renewal.
Please investigate and refresh the Codex entitlement/usage quota associated with my account.
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.
Research direction
No source files or tests are identified. Start by reproducing the post-renewal state and comparing the Usage page quota with the Codex execution service response, including the unsupported gpt-5.6-sol model error. Done means a renewed Pro account with remaining quota can run supported Codex tasks without the stale usage-limit message.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100