Excessive token consumption since mid-July

Codex Codex CLI
1

Hi everyone, since mid-July I’ve been experiencing a consumption of almost 5 times higher than my weekly consumption and credits using chatgpt 5.6 sol hight. Here’s just an example of my consumption. As you can see, between June and July I’ve gone from 300 credits to 1000 credits just for today. In 4 hours, it seems excessive to me.

24 lug 2026 Desktop App 1.012,616 crediti
21 lug 2026 Desktop App 138,212 crediti
21 lug 2026 Desktop App 111,357 crediti
21 lug 2026 Desktop App 0,112 crediti
20 lug 2026 Desktop App 773,004 crediti
12 lug 2026 Extension 1.063,578 crediti
18 giu 2026 Extension 315,002 crediti
17 giu 2026 Desktop App 116,859 crediti
17 giu 2026 Extension 212,885 crediti
16 giu 2026 Desktop App 229,112 crediti
2

Thanks for flagging this, @maxrita1996. A jump from roughly 300 to 1,000 credits in four hours definitely seems worth investigating.

Please email support@openai.com with the relevant request IDs and exact timestamps in UTC so the team can review the usage in detail. Feel free to share the case ID here afterward, and the team can help monitor the issue.

-Mark G.

4

Thanks for sharing this, @VeitB. At least it’s now clearer what’s been causing the unexpected token consumption, which should help others seeing the same issue.

-Mark G.

5

Agreed, since the combination of the CLI into the main repi, I have overused my credits, API usage and far exceeded parameters than prior to integration. The combination of the LLM and CLI makes sense in theory but what works within certain domains is not clear enough for me and has caused branches to become messy and a waste of time and credits. If the combination cannot be separated clearly for UX purposes than id rather go back to 5.