{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreidbp5yfqpu4mghnlb5vtv6eu44ilpfq6whxababum7j7lapsiovem",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mhcs73lopye2"
},
"path": "/t/bug-codex-app-blocks-gpt-5-3-codex-spark-even-though-spark-weekly-usage-remains/1377045#post_1",
"publishedAt": "2026-03-18T05:34:22.000Z",
"site": "https://community.openai.com",
"textContent": "I think I’ve hit a quota/account-state bug in the Codex app.\n\nWhat I’m seeing:\n\n * Standard Codex weekly usage limit: 0% remaining\n * Standard Codex 5-hour usage limit: 100% remaining\n * GPT-5.3-Codex-Spark weekly usage limit: 55% remaining\n * GPT-5.3-Codex-Spark 5-hour usage limit: 100% remaining\n\n\n\nHowever, the Codex app still shows:\n“You’re out of Codex messages”\nand blocks the composer, even when GPT-5.3-Codex-Spark is selected.\n\nWhy this looks wrong:\nMy understanding is that GPT-5.3-Codex-Spark is supposed to have its own separate usage bucket. But in the app, the exhausted standard Codex weekly limit seems to hard-lock the whole composer and prevents Spark from being used as well.\n\nExpected behavior:\nIf GPT-5.3-Codex-Spark still has remaining weekly/5-hour quota, I should still be able to use it after switching the model selector to GPT-5.3-Codex-Spark.\n\nActual behavior:\nThe app appears to apply the exhausted standard Codex weekly limit globally and blocks Spark too.\n\nSteps to reproduce:\n\n 1. Use up the standard Codex weekly usage limit.\n 2. Leave GPT-5.3-Codex-Spark weekly quota still available.\n 3. Open the Codex app and select GPT-5.3-Codex-Spark in the composer.\n 4. The app still shows “You’re out of Codex messages” and disables usage.\n\n\n\nWhat I already checked:\n\n * The usage dashboard clearly shows remaining GPT-5.3-Codex-Spark quota.\n * The app UI still refuses input.\n * I have screenshots of both the dashboard and the blocked composer state.\n\n\n\nEnvironment:\n\n * Plan: Pro\n * Platform: [Mac app]\n * Version: 26.313.41514\n\n\n\nQuestion:\nIs this a known bug in the Codex app quota gating logic, or is there some hidden rule where remaining GPT-5.3-Codex-Spark quota still cannot be used once the standard Codex weekly pool is exhausted?\n\nI’m mainly posting to confirm whether others can reproduce this and whether OpenAI can fix the quota-state check in the app.",
"title": "Bug: Codex app blocks GPT-5.3-Codex-Spark even though Spark weekly usage remains"
}