{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidhpcnp3a7q2lkbfrznxrmzrjs2idxdvkt573g6232rne4ywhr5qu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlh5zxf5ihe2"
  },
  "path": "/t/v1-images-edits-rejects-gpt-image-2-hardcoded-to-dall-e-2-only/1380585#post_3",
  "publishedAt": "2026-05-09T20:09:46.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@input.png"
  ],
  "textContent": "Hi and welcome to the community!\n\nThis is likely caused by the documentation. The docs mix several image surfaces and model families, so it is easy to combine parameters from different paths.\n\nFor gpt-image-2 image input, use:\n\n\n    curl https://api.openai.com/v1/images/edits \\\n      -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n      -F \"model=gpt-image-2\" \\\n      -F \"image[]=@input.png\" \\\n      -F \"prompt=Edit this image by ...\"\n\n\nOr with the Python SDK:\n\n\n    from openai import OpenAI\n\n    client = OpenAI()\n\n    result = client.images.edit(\n        model=\"gpt-image-2\",\n        image=open(\"input.png\", \"rb\"),\n        prompt=\"Edit this image by ...\"\n    )\n\n\nPlease note:\n\n  * /v1/images/edits is the correct endpoint for GPT Image with reference-image or edit workflows.\n  * /v1/images/variations is DALL-E 2 only. It does not support gpt-image-2.\n  * response_format is a DALL-E-era parameter. GPT Image models return base64 image data and use GPT-image-specific parameters like output_format, output_compression, quality, etc.\n\n",
  "title": "/v1/images/edits rejects gpt-image-2 — hardcoded to dall-e-2 only"
}