API Overview

GPT Image 2 API overview

Use the API when you want the same image workflow inside your own app, script, or automation.

Endpoints

• Main image endpoint: POST /v1/images/generations
• Compatible endpoint: POST /v1/chat/completions

Available models

• gpt-image-1.5-all
• gpt-image-2-all

What you can send

• A text prompt
• Output size, such as 1024x1024
• Image count
• An optional reference image for image-to-image flows

Example request

curl https://your-api-host/v1/images/generations   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "gpt-image-2-all",
    "prompt": "A premium skincare bottle on a warm beige pedestal, studio light, realistic shadows",
    "size": "1024x1024",
    "n": 1
  }'

Next step

Start on the web generator first if you want to test prompts quickly, then move to the API when you need a repeatable workflow.