{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidchyt2ifauxunmudpoksxzxdeqnuvumfmzajzsxjd5b26njmnzvy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmyxlly3tld2"
  },
  "path": "/t/the-half-penny-gpt-image-2-challenge-api-only-gallery/1381388#post_17",
  "publishedAt": "2026-05-29T15:58:58.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@sergeliatko"
  ],
  "textContent": "From what I can see in the official OpenAI Playground, for me the usage is reported under Responses and Chat Completions for everything I’ve ever tested, including image generation. So even when I lock size/quality for gpt-image-2, the dashboard still shows that activity there. (This is what it shows for **me** on my dashboard, not claiming anything universally)\n\nIn _Images_ in OpenAI playground, you can choose between these tool parameters (plus advanced settings):\n\nIf you choose size:auto, apparently the model can choose something else even when the prompt includes a resolution. In @sergeliatko example, the prompt asked for 780x640px, but the supplied image was 1384x1136, probably because size was still auto.\n\n* * *\n\nI tested in the official OpenAI Playground with:\n\n  * model: gpt-image-2\n\n  * size: 1024x1024\n\n  * quality: low\n\n  * prompt: Sparkling shell with a pearl\n\n\n\n\nThe Usage dashboard reported it under Responses and Chat Completions, with:\n\n  * input: 12 tokens\n\n  * output: 196 tokens\n\n\n\n\nUsing the listed gpt-image-2 pricing:\n\n  * text input: 12 × $5 / 1M = $0.00006\n\n  * image output: 196 × $30 / 1M = $0.00588\n\n\n\n\nTotal: about $0.00594, so basically $0.006. (No this does not meet the budget $0.005, but that’s the closet I can come with official OpenAI Playground).",
  "title": "The Half-Penny gpt-image-2 Challenge - API-only Gallery"
}