Users Claim OpenAI Secretly Cut Codex Usage Limits by Half

Some OpenAI Codex users are raising reservations concerning how rapidly their weekly usage allowances are being consumed, with developers calling for clearer information concerning exactly how individual coding tasks affect their limits.

Key points

• The user remarked they had upgraded from ChatGPT Plus to Pro 5x and afterwards Pro 20x while using Codex for professional software engineering.
• As the report notes, 75.25 million tokens consumed around 26% of the user's weekly allowance shortly after the August 1 reset.
• Add ProPakistani to Preferred Sources and see more of our stories in Google Search and Top Stories.
• One of the more detailed reports appeared in GitHub matter #36468 on the official openai/codex repository.
• Another forum user, DerDerErIst, documented that a single substantial prompt consumed around 50% of their five-hour allowance and approximately 20% of their weekly allowance.

For context, the complaints do not prove that OpenAI has secretly reduced Codex allowances. Nevertheless, reports posted on OpenAI's Developer Community forum and the official OpenAI Codex GitHub repository show that some paying users are finding it challenging to predict how much work their subscriptions will cover. Developers Build Their Own Codex Usage Tracker.

One response to the matter is NerfTrack, an open-source desktop application created by developer Ayaan Lashari.

According to the project's GitHub repository, NerfTrack is a local Tauri-based app that reads Codex usage records and estimates their API-equivalent weekly value.

In practice, the tool does not prove that OpenAI has reduced Codex quotas. Instead, it gives users another way to examine their own usage and estimate how much value their Codex activity represents.

OpenAI additionally publishes a token-based Codex rate card that explains how further credits are consumed based on input, cached input, and output tokens.

OpenAI's official Codex pricing documentation provides estimated usage ranges for five-hour windows and explains that more complicated tasks can consume limits faster.

Notably, the firm additionally states that extra weekly limits may apply. Users can check their current allowance through the Codex Usage Dashboard or employ the /status command during an active Codex CLI session.

Nevertheless, OpenAI does not publish one fixed weekly allowance that applies to every user and workload.

That lack of a simple task-by-task breakdown has become one of the main complaints among developers. GitHub Users Report Rapid Quota Consumption.

Meanwhile, a ChatGPT Pro 20x user posting as FlowTether remarked their weekly allowance reset to 100% on August 1 before falling to 91% during a single GPT-5.6 Sol engineering session lasting roughly 4.5 hours.

Meanwhile, the user additionally stated the previous weekly allowance had been almost exhausted within around one to one-and-a-half days and that they purchased another $40 in usage to continue working. Another user, zkhrvv, documented a similar concern in GitHub problem #36488.

As the report notes, 75.25 million tokens consumed around 26% of the user's weekly allowance shortly after the August 1 reset. The user remarked concerning 96% of those tokens were cached reads and estimated that the same workload appeared to provide significantly less effective capacity than before.

In practice, a third report appeared in GitHub matter #36481, where Plus user yanse216 stated their weekly usage indicator rose from 16% to 75% during five hours despite their local logs showing no model requests during that time.

These are individual user reports and do not establish that OpenAI deliberately reduced Codex limits. OpenAI Forum Users Report Similar Challenges. Complaints have additionally appeared on OpenAI's Developer Community forum.

In an April discussion titled "Understanding the New Codex Limit System After the April 9 Update, " forum user ZachA remarked asking Codex to summarize one method consumed 6% of their five-hour allowance. A follow-up request to modify the same method reportedly consumed another 5%.

Meanwhile, the user remarked this occurred in a relatively small project and argued that the rate of consumption produced sustained development tough.

Another forum user, DerDerErIst, documented that a single substantial prompt consumed around 50% of their five-hour allowance and approximately 20% of their weekly allowance. The user remarked the five-hour limit was reached after three substantial prompts.

Notably, a separate user, shasixz, remarked one basic prompt consumed roughly 22 credits and argued that even relatively small development tasks were using paid credits faster than anticipated. Pro User Notes Extra Credits Disappeared Swiftly.

Another detailed complaint came from OpenAI Developer Community user D_Anil_Reddy in July.

Meanwhile, the user remarked they had upgraded from ChatGPT Plus to Pro 5x and afterwards Pro 20x while using Codex for professional software engineering.

Despite those upgrades, they remarked they exhausted both their weekly Codex allowance and GPT-5.3-Codex-Spark allowance sooner than anticipated.

In practice, the user additionally noted purchasing around Rs. 2, 000 worth of extra Codex credits. It they stated were consumed within only a few substantial engineering prompts.

OpenAI Backing responded on July 23 that a complete per-task usage breakdown did not appear to be available. Backing instead pointed the user toward the Codex Usage Dashboard and the /status command and stated the request for more detailed task-level usage information would be passed along.

OpenAI's own Codex documentation demonstrates that usage can vary significantly depending on the model and workload.

More demanding models, larger contexts, longer outputs, tool calls, and extra agents can all rise resource consumption.

This means two prompts do not necessarily consume the same amount of a user's allowance, even if they appear similar in length.

OpenAI now provides more information regarding Codex consumption through its pricing pages, rate cards, and usage dashboard.

Still, the reports posted on GitHub and OpenAI's own developer forum show that some users want a much clearer breakdown showing exactly how much each Codex task consumes and why.

Obtain the latest news, tech updates, telecom insights, and business stories wherever you prefer.

Add as a preferredSource on Google Follow on Google News Join WhatsApp.

Technology and Automotive Specialist covering the latest cars, smartphones, AI breakthroughs, and.

Taken together, the developments around users Claim OpenAI Secretly Cut Codex Usage Limits by Half point to a situation that is still moving, and the coming days should bring more clarity.