GPT Image is OpenAI's current family of image models, which create new pictures from text and edit existing ones.
In plain words
GPT Image took over from DALL·E in OpenAI's API. You can ask for a picture from scratch or give an existing image and describe changes. Used inside a conversation, it can keep refining the same picture over several turns. In September 2026 the models on offer are gpt-image-2.5-sunburst, aimed at precise editing, and gpt-image-2.5-flare, aimed at fast everyday images. It still has limits: complex prompts can be slow and exact text placement can go wrong.
A quick example
Imagine a shop that uploads a product photo and asks for the background to be swapped for a beach. It then asks, in the next turn, for warmer light, and the model edits the same image again.
Where you'll meet it
- Apps built on the OpenAI API.
- Editing images step by step inside a chat.
Related
Sources
- DocsImage generation, OpenAI API docs · read 29 Sept 2026
- DocsDeprecations, OpenAI API docs · read 12 Nov 2026
Checked by WhatIsAI against the sources above · 12 Nov 2026. Spotted an error? Report it.