← Back to glossary
+Suggest a term
Tool·AI Models & Capabilities·Added 1 day ago

DALL-E

Also known as: DALL·E, DALL-E 3, GPT Image, GPT Image 1, GPT Image 1.5, GPT Image 2, ChatGPT Images

OpenAI's image generation model family. DALL-E 3 was the widely used version through 2024; it was replaced by the GPT Image series starting in March 2025. As of May 2026, DALL-E 2 and 3 are retired and GPT Image is the current line.

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.

This definition is AI-generated and refreshed weekly. It may contain inaccuracies. Use your own judgment, especially for production decisions.
Related terms
Text-to-imageMidjourneyFluxNano BananaGoogle Imagen