# Codex Rate Limits Discussion Thread

**URL:** <https://community.openai.com/t/codex-rate-limits-discussion-thread/1378553>\
**Category:** Codex\
**Tags:** rate-limit\
**Created:** [April 4, 2026, 10:54pm UTC](https://community.openai.com/t/codex-rate-limits-discussion-thread/1378553 "2026-04-04T22:54:52Z")\
**Posts on this page:** 1\
**Showing post:** 1020

<div class="post-metadata">

**Author:** ![merefield](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/merefield/32/14812_2.png) [@merefield](https://community.openai.com/u/merefield)\
**Post date:** [October 18, 2026, 12:13pm UTC](https://community.openai.com/t/codex-rate-limits-discussion-thread/1378553/1020 "2026-10-18T12:13:08Z")

</div>

I think it’s fair to say that compared to a few months ago subscription accounts are much less generous than before, but still represent great value compared to the alternative of using the API directly.

[Codexometer](https://community.openai.com/t/codexometer-track-your-quota-usage-orchestrate-sessions-benchmark-models/1389878/1) is currently reporting about $500 (API equivalent) of weekly available usage for a Pro 200 account. This doesn’t include the generous allocation of discretionary resets either. This was once $3.5k (a week!) though.

 ![image](https://us1.discourse-cdn.com/openai1/original/4X/b/4/2/b423af01c8af2b011c8e62a0104ba61aeb054146.png)

It’s worth noting that a direct comparison is hard as Codex and models have got more capable.

---

_[View the full topic](https://community.openai.com/t/codex-rate-limits-discussion-thread/1378553)._