Codex CLI: Plus users hitting usage limits extremely quickly compared to competitors

[zgqq]

Issue Summary

ChatGPT Plus users are hitting usage limits for Codex CLI very quickly, sometimes after just 1-2 requests, making the service nearly unusable for practical development work.

Installation Method

npm install -g @openai/codex

Current Behavior

• Plus users report hitting usage limits after minimal usage (sometimes just 1-2 coding requests)
• Limits seem to reset but the allowance is extremely small
• Usage limits appear to be much more restrictive than what's advertised or expected for a paid plan
• Users are forced to interrupt their development workflow frequently

Expected Behavior

• Plus users should have reasonable usage limits that allow for meaningful development sessions
• Usage limits should be clearly communicated to users
• The service should be competitive with other AI coding solutions

Comparison with Competitors

Claude Code Pro users can typically:

• Run extended coding sessions throughout the day
• Handle complex multi-file projects without hitting limits
• Complete substantial development tasks without interruption

Meanwhile, Codex CLI Plus users are hitting limits after very basic requests, making it practically unusable for real development work.

Impact

This severely limits the usefulness of Codex CLI for Plus subscribers who:

• Cannot complete basic coding tasks
• Experience frequent interruptions during development
• May consider switching to competitor services that offer more generous usage allowances
• Lose context and momentum when forced to stop mid-task

Environment

• Platform: Codex CLI (installed via npm)
• Installation: npm install -g @openai/codex
• Subscription: ChatGPT Plus
• Authentication: Sign in with ChatGPT

Additional Context

While I see issue #2022 discusses similar problems and some improvements have been made (v0.21 with better caching), the usage limits are still extremely restrictive for Plus users.

For a paid service competing with solutions like Claude Code Pro, the current usage limits make Codex CLI nearly unusable for practical development work, despite the quality of GPT-5 model.

Suggested Solutions

1. Increase usage limits for Plus users to competitive levels
2. Provide transparency about current limits and when they reset
3. Consider usage-based tiers rather than hard cut-offs that interrupt development workflows
4. Better limit indicators so users can plan their usage accordingly
5. Show current usage status in CLI (similar to /status command but with limit information)

This issue significantly impacts user experience and competitive positioning of Codex CLI, especially when users pay for Plus expecting reasonable usage allowances.

[qunahui]

Allow us to use gpt-5-mini in Codex CLI with ChatGPT Plus subscription, gpt-5 hit the usage limit really fast.

Edit: Why am I getting dislike and meh ? GPT-5-Mini only available for pay-as-you-go apiKey, not with ChatGPT Plus subcription. Trying to get more usages out of this.

[rTiGd2]

This was new today me me - It has been 15 hours and my Plus usage hasn't reset, 1 or 2 prompt would be an improvement for me right now.

[epasEltronix]

Plese make a transparent usage statistic and when to expect to reset them. We clearly need more time to use.

[S-Gr4y]

Same I've been blocked for more than 24h now :'(

[AdsQnn]

For example, Gemini CLI gives you 1,000 queries per day — for free.

[radoslawcz]

I also hit the weekly limit too quickly on Plus. I’ve only been using it for about 3 days, and I never even once hit the 5-hour session limit. But now I can’t use it anymore because the weekly limit was reached (since 5 hours total already passed). So I never actually used a full 5-hour slot, but it still counts as too much for the week. I think that’s too harsh.

We also need more statistics - like when exactly the limit will be lifted - so users can plan their usage better.

[FreddyE1982]

I just hit the limit according to CLI..but I can still use the web version. It seems to me that CLI and web actually have seperate limits. This needs to be clarified in the readme or better: CLI should share the limit of the web version.

[FreddyE1982]

okay...this is weird. now I can use the cli again...no "ran into limit" message anymore.

[adamsvoboda]

I've been using gpt-5-high with codex and the Plus plan, I hit the usage limits after about ~1.6M tokens. I assume gpt-5-high might contribute to hitting the limits faster, but I haven't tested it to confirm.

[bstag]

Yep after 4 - 5 hour limits this week. I have hit my weekly limit. Not that I used it for the full 5 hours of those sessions. Glad this was just a test to see if this would work and have other options.

[radoslawcz]

Allow us to use gpt-5-mini in Codex CLI with ChatGPT Plus subscription, gpt-5 hit the usage limit really fast.

Edit: Why am I getting dislike and meh ? GPT-5-Mini only available for pay-as-you-go apiKey, not with ChatGPT Plus subcription. Trying to get more usages out of this.

From what I saw in the /model selection you can choose gpt-5 minimal.

[FreddyE1982]

the thing about the modes below medium: they make codex WAY to dumb by comparison. It actually needs to work MORE to accomplish stuff that way, and needs more user guidance for it. this totally negates the "advantage" that the lower reasoning modes need less tokens.