{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreier5gvpxq3pluvfwbakqruavc4yw43nwdiuv7bsfr2goycrm3ecwu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmuxwxmc2ip2"
  },
  "path": "/t/may-2026-chatgpt-api-image-gallery-prompt-tips-and-help-generative-art-theme-science/1378298?page=62#post_1249",
  "publishedAt": "2026-05-28T02:22:24.000Z",
  "site": "https://community.openai.com",
  "textContent": "_j:\n\n> gpt-image-whatever is a multimodal language model, trained the same as gpt-4o was with a native (and unreleased for the longest time) ability to produce audio and imagery outputs. It can understand and produce in world languages, just as it can talk.\n\nInteresting. Does OpenAI have published information on gpt-image-whatever’s multimodal capabilities? Or is this something that will be revealed someday when the SuperApp is released?",
  "title": "May 2026 — ChatGPT / API Image Gallery, Prompt Tips, and Help: Generative Art Theme: Science"
}