{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicojf3ayegjl3vxxwctiyjmwj6idzhpleqbaebgxqs35u7e46r5di",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mg6htzclnpm2"
  },
  "path": "/t/api-model-gpt-5-3-chat-latest-available-aka-instant-on-chatgpt/1375606#post_1",
  "publishedAt": "2026-03-03T19:06:06.000Z",
  "site": "https://community.openai.com",
  "textContent": "No API-only model specifically yet, but you get what was just released to ChatGPT, “experiment with the latest version with less feature support”:\n\n`gpt-5.3-chat-latest` Supports:\ntemperature: no\ntop_p: no\nReal system role: no\n\n  * Unlike prior models of “chat”, currently supports sending reasoning_effort, internally: ‘minimal’:5, ‘low’:16, ‘medium’:64, and ‘high’:200.\n(all ineffective to get lots of thinking done for minimal tasks, but at high, up to 700/700 split of reasoning-to-seen tokens for increasing question).\n  * “verbosity” does have an effect: “low” is extremely low output (internal “oververbosity” of 1)\n\n\n\nNo pricing yet, but probably follows 5.3 codex, along with no cache discount for running on service_tier or batch.",
  "title": "API model: gpt-5.3-chat-latest available (aka \"instant\" on ChatGPT)"
}