텍스트와 생성된 이미지를 모두 출력하는 대화형 API가 있습니까?

curl https://api.apiyi.com/v1/images/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "An orange cat sitting on a blue sofa, simple line-art style",
    "size": "1024x1024"
  }'

cand = (resp.get("candidates") or [{}])[0]
parts = (cand.get("content") or {}).get("parts") or []
images = [p["inlineData"] for p in parts if "inlineData" in p]
texts  = [p["text"] for p in parts if "text" in p]          # commentary lives here
if not images:
    raise RuntimeError(f"No image returned, finishReason={cand.get('finishReason')}")
final = images[-1]                                          # last image is the final one

{
  "model": "gpt-5.5",
  "input": "Draw a key visual poster for a product launch event",
  "tools": [{ "type": "image_generation" }]
}