DALL-E
Also known as: DALL·E, DALL-E 3, GPT Image, GPT Image 1, GPT Image 1.5, GPT Image 2, ChatGPT Images
DALL-E introduced a lot of people to AI image generation. DALL-E 3, available inside ChatGPT from late 2023, was notable for how closely it followed natural language prompts, something earlier text-to-image tools often failed at. You could write a long, descriptive sentence and get a result that actually matched what you meant.
In March 2025, OpenAI replaced DALL-E 3 with GPT Image 1, a fundamentally different architecture where image generation is a native capability of the language model itself rather than a separate pipeline. GPT Image 1.5 followed in December 2025, and DALL-E 2 and 3 were officially retired on May 12, 2026. The current model as of mid-2026 is in the GPT Image 2 line, which OpenAI describes as the first image model with native reasoning, strong text-in-image rendering, and 2K resolution.
If you encounter references to DALL-E in tutorials or code, the underlying API endpoint has changed. Developers previously using the DALL-E API need to migrate to GPT Image endpoints. The user experience inside ChatGPT is similar, but the model beneath it is substantially newer.