Codex App Tokens Burning Very Fast — Weekly Limit Exhausted in Single Day

What this error means

Burning tokens very fast — weekly limit drained ~70% in a single day on normal moderate usage is a OpenAI Codex failure pattern reported for developers trying to users trying to understand why their codex token usage spiked dramatically after extension update, preventing continued coding work. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue openai/codex#14593 with 258 👍 reactions; multiple Pro/Plus/Business subscribers report severe token overconsumption (70% weekly limit in one day) triggered by v26.311.21342 extension update; persists through March–May 2026 with recent active comments today. Strong commercial value: affects paid subscription tiers directly.

Common causes

• GitHub issue openai/codex#14593 with 258 👍 reactions; multiple Pro/Plus/Business subscribers report severe token overconsumption (70% weekly limit in one day) triggered by v26.311.21342 extension update; persists through March–May 2026 with recent active comments today. Strong commercial value: affects paid subscription tiers directly.

Quick fixes

1. Confirm the exact error signature matches Burning tokens very fast — weekly limit drained ~70% in a single day on normal moderate usage.
2. Check the OpenAI Codex account, local tool state, and provider configuration involved in the failing workflow.
3. Reduce request pressure, check quota or plan limits, and retry with backoff instead of immediate repeated requests.

Platform/tool-specific checks

• Verify the command, editor, extension, or API client that produced the error.
• Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
• Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

1. Capture the exact error message and the command, editor action, or request that triggered it.
2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
3. Review the source evidence below and compare it with your environment.
4. Apply one change at a time and rerun the smallest failing action.
5. Keep the working fix documented for the team or deployment environment.

How to prevent it

• Keep provider/tool configuration documented.
• Record non-secret diagnostics such as tool version, provider name, model name, and command path.
• Add a lightweight check before CI or production workflows depend on the tool.

Sources checked

• https://github.com/openai/codex/issues/14593

Evidence note: GitHub issue openai/codex#14593 with 258 👍 reactions; multiple Pro/Plus/Business subscribers report severe token overconsumption (70% weekly limit in one day) triggered by v26.311.21342 extension update; persists through March–May 2026 with recent active comments today. Strong commercial value: affects paid subscription tiers directly.

Related errors

• OpenAI API

FAQ

What should I check first?

Start with the exact Burning tokens very fast — weekly limit drained ~70% in a single day on normal moderate usage text and the smallest action that reproduces it.

Can I ignore this error?

No. Treat it as a failed OpenAI Codex workflow until the root cause is understood.

Is this guaranteed to have one fix?

No. The imported evidence supports the troubleshooting path above, but tool behavior can vary by account, plan, version, provider, and local configuration.

How do I know the fix worked?

Rerun the same command, editor action, or request. The fix is working when that action completes without Burning tokens very fast — weekly limit drained ~70% in a single day on normal moderate usage.