{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigeoxtrr5u6kkrwbj6zzn7kvse4t5oebkksf7icvrv4ydglpk7tty",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3moigvbxu3jk2"
  },
  "path": "/t/codex-main-quota-exhaustion-blocks-gpt-5-3-codex-spark-despite-available-spark-quota/1383842#post_5",
  "publishedAt": "2026-06-17T13:03:20.000Z",
  "site": "https://community.openai.com",
  "textContent": "To convert existing conversations to Spark, you must first compress the context into a generic model. However, switching to Spark may become impossible once the generic model limits are exhausted. In other words, you must have generic model capacity to switch to and use Spark models. It appears advisable to utilize Spark model limits first before using generic models..",
  "title": "Codex main quota exhaustion blocks GPT-5.3-Codex-Spark despite available Spark quota"
}