DALL-E Models by OpenAI
OpenAIProprietary
This model family is considered obsolete. Consider newer alternatives in Related Model Families below.
2 models2022–2023
Last refreshed 2026-05-09. Next refresh: weekly.
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models2
Released2022–2023
Capabilities
VisionAll models
MultimodalAll models
Links
WebsiteAbout
OpenAI's DALL-E family is the diffusion-based predecessor to the GPT Image series. DALL-E 2 (April 2022) enabled inpainting and outpainting for editing specific image regions. DALL-E 3 (October 2023) dramatically improved prompt adherence via integration with ChatGPT's instruction-following. Both models are deprecated with OpenAI API shutdown scheduled for May 12, 2026 in favor of the autoregressive gpt-image series.
Decision facts
Archived Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view2 retired
DALL-E 3Archived
Keep only for existing workloads; choose a current variant for new builds.
2023-10image generationmultimodal inputs
DALL-E 2Archived
Keep only for existing workloads; choose a current variant for new builds.
2022-04image generationmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| DALL-E 3 | Keep only for existing workloads; choose a current variant for new builds. | 2023-10 | image generationmultimodal inputs | Archived |
| DALL-E 2 | Keep only for existing workloads; choose a current variant for new builds. | 2022-04 | image generationmultimodal inputs | Archived |
