gpt5.4 uses more limits than 5.3codex. #13609

Activity

1. Alfredo-Sandoval

   added

   bugSomething isn't workingSomething isn't working

   on Mar 5, 2026
2. github-actions

   added

   CLIIssues related to the Codex CLIIssues related to the Codex CLI

   rate-limitsIssues related to rate limits, quotas, and token usage reportingIssues related to rate limits, quotas, and token usage reporting

   on Mar 5, 2026
3. github-actions commented on Mar 5, 2026

   

   github-actionsbot

   on Mar 5, 2026 – with GitHub Actions

   Contributor

   More actions

   Potential duplicates detected. Please review them and close your issue if it is a duplicate.

   • Usage dropping too quickly #13568
   • The week limit moved from March 9 to March 11 and usage did not get recalculated properly #13567
   • Drain Faster 5 hour usage limit Weekly usage limit #13317
   • Possible Codex usage metering anomaly on Plus (very small tasks consuming large 5h + weekly quota) #13186
   • Codex usage got decreased by 2-4 times. #13167

   Powered by Codex Action
4. etraut-openai commented on Mar 5, 2026

   

   etraut-openai

   on Mar 5, 2026

   Contributor

   More actions

   Is this just based on vibes? Can you provide any concrete details or side-by-side comparisons?

   👎React with 👎3Reacted by 2xmvr, Evgeniy Belkovich and Önder Ertan
5. jcastilloa commented on Mar 5, 2026

   

   jcastilloa

   on Mar 5, 2026

   More actions

   Even more? This is crazy, thanks for the heads up. And yeah, it seems like they're so busy with launches that they don't have time to address the bugs that make the product unusable.

   👍React with 👍2Reacted by 2xmvr and Önder Ertan
6. jcastilloa commented on Mar 5, 2026

   

   jcastilloa

   on Mar 5, 2026

   More actions

   Is this just based on vibes? Can you provide any concrete details or side-by-side comparisons?

   Any news on this? #13186, we can't work.

   👍React with 👍1Reacted by 2xmvr
7. maxjendrall commented on Mar 5, 2026

   

   maxjendrall

   on Mar 5, 2026

   More actions

   I am also seeing accelerated usage on the same workload from a couple hours ago.

   Just did two test tasks with maybe total 300k tokens, of which 20k were output tokens and my pro usage jumped by 4% of my pro account. Usually that was <1%. No fast mode and no 1m+ context enabled.
8. etraut-openai commented on Mar 5, 2026

   

   etraut-openai

   on Mar 5, 2026

   Contributor

   More actions

   I just confirmed that 5.4 does have a higher cost, and therefore a higher usage multiplier than 5.3-codex. Apologies — I wasn't aware of this until just now.

   We've updated our documentation here to reflect this.

   You can choose to stick with 5.3-codex if you find that 5.4 does justify the additional cost.
9. etraut-openai

   closed this as completedon Mar 5, 2026
10. Alfredo-Sandoval commented on Mar 5, 2026

    

    Alfredo-Sandoval

    on Mar 5, 2026

    Author

    More actions

    Vibes locked in.

    😄React with 😄2Reacted by Eric Traut and Önder Ertan
11. Danielalnajjar commented on Mar 6, 2026

    

    Danielalnajjar

    on Mar 6, 2026

    Last edited by Danielalnajjar

    More actions

    I'm noticing the same issue. I'm on the Pro plan. I went through almost 70% of my usage in one day. I usually end the week with at least 10% or more remaining, and I don't feel I had an abnormal workflow that day in comparison to other days. My limits just reset on the 4th at 3:30 PM.

    User ID: user-lkqg4raupjouznjF0npCN8cK

    Based on an analysis I've done of the logs and the token usage, I believe this is largely related to the fork_context feature on spawn_agent.

    ---

    What happened

    A single session consumed 1.16B tokens (~50% of my weekly limit). The session started as "run e2e tests" (tests passed in 40s), then continued with follow-up tasks across 50+ user messages.

    The model spawned 22 subagents, 12 with fork_context=true. The ones spawned with fork_context=true consumed 70-220M tokens each. The ones with fork_context=false were all under 2M.

    Token breakdown

    Agent	fork_context	Tokens	Duration
    Parent thread	—	230M	—
    Dewey (worker)	true	219M	5 min
    Avicenna (explorer)	true	157M	6 min
    Arendt (explorer)	true	142M	5 min
    Pasteur (explorer)	true	78M	5 hrs
    Boyle (explorer)	true	78M	4.8 hrs
    Aquinas (explorer)	true	77M	6 min
    Raman (explorer)	true	77M	5 min
    Nash (explorer)	true	69M	5 min
    Godel (worker)	true	23M	13 min
    12 others	false	<2M each	—
    Total		1.16B

    The model's fork_context decisions

    The first 3 spawns correctly used fork_context=false. Starting at spawn #4, the model began using fork_context=true for tasks that don't appear to need full session history:

    [937]   fork_context=True  "Implement the dedicated organizations CRUD E2E setup helper..."
    [3880]  fork_context=True  "Inspect apps/web/src/components/calculator/sales-entry-form.test.tsx..."
    [3881]  fork_context=True  "Inspect apps/web/src/components/calculator/calculator-page.test.tsx..."
    [7955]  fork_context=True  "Audit apps/web/src/components/calculator/calculator-page.pending-shield.test.tsx..."
    [7958]  fork_context=True  "Audit apps/web/src/components/calculator/calculator-page.test.tsx..."
    [11309] fork_context=True  "Audit the current Convex timeout cluster in this repo without editing files..."
    [11310] fork_context=True  "Inspect the current quality-gates / Turbo orchestration..."
    

    The forked subagents inherited the full session state (79 user messages, thousands of tool results). Dewey's rollout shows 84 turns, 16 compactions, and 1,061 tool calls in 5 minutes.

    Config at the time

    • Codex CLI v0.111.0
    • Model: gpt-5.4, reasoning effort: high/xhigh
    • max_threads = 8, max_depth = 2

    Session details

    • Session ID: 019cbfdd-a496-7b31-b017-a0c1e1467051
    • Rollout available if needed for investigation

    👍React with 👍2Reacted by Matthew (Gliktch) and Önder Ertan