Skip to main content
POST
GPT-Image-2

Introduction

GPT-Image-2 uses POST /v1/images/generations for both text-to-image and image-to-image: omit image for T2I; include image (URL or Base64) for I2I. Responses use b64_json with usage token stats. For full parameters and other image models, see Image generation.

Authentication

string
required
Bearer Token, e.g. Bearer sk-xxxxxxxxxx

Supported models

Request examples

Common parameters

  • model: gpt-image-2
  • prompt: Description or edit instruction
  • image: Reference image for I2I
  • size: e.g. 1024x1024, 1024x1536, 2880x2880 (dimensions multiple of 16)
  • quality: low, medium, high
  • n: Number of images (1–10)
See Image edits for multipart and more examples; Image generation for the full overview.