{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreig4mztaznlx3lksn4iel7bs5enoh4puxtpf2cs35g4cwfnjngzfoq",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3minuapm556n2"
},
"path": "/t/current-usage-limits-make-codex-unusable/1378497#post_3",
"publishedAt": "2026-04-04T08:31:07.000Z",
"site": "https://community.openai.com",
"textContent": "Yeah, i have also opened another topic regarding this matter, thread: “codex-limits-finally-good-after-april-1st-reset” floating in newest topics.\n\nIts going nuts now. I am running Business accounts with multiple user for multiple devs.\n\nYesterday and today the workflow is basically this:\n\n * Dev logins into CODEX on IDE\n * Sends 3 tasks\n * Dev must logout, ask me for new login approval\n * Dev then does again 3 tasks, logs out\n * To infinity this loop…\n\n\n\nWeekly limits seems like fair and ok IMO. But 5H its going absolute nuts. Each task eats 20-30% of 5H range.\n\nYou can actually test it by just writing something simple, just talking with it and you gonna see that it will suck 10% to answer\n\nAlso i have noticed the quality of the work went down from codex\n\nBut yes, its is becoming absolutely unusable at this point.\n\nIm running GPT 5.4, Medium, Full access, Locally - no MCP connectors, nothing just purely controlled by core agent. So my tasks are super efficient and accurate.\n\nWe tired working on GPT5.3-codex, little better situation - you can produce just a little more but still same - 5H gets wiped off super fast.\n\nThe only choice is API or new Codex account credits at this point but budget must be super high, you can easily spend 50-100$ a day.",
"title": "Current usage limits make Codex unusable"
}