OpenAI · image model · Released Nov 6, 2023DALL·E 3
DALL·E 3 is an image model from OpenAI, released Nov 6, 2023. It handles text to image.
- Arena score
- 967#79 of 82 · text to image
- Starting price
- —Not published
- Largest size
- —Not published
- References
- —Text prompts only
How it rates and what it costs
- Text to image arena
- 967 ±4#79 of 82 · 238,731 votes
Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Oct 26, 2026.
The details
- Lab
- OpenAI
- Type
- Image model
- Released
- Nov 6, 2023
- Inputs
- Text prompts
- Output
- Images
- Can do
- Text to image
- Weights
- Proprietary
- Availability
- 1 API host
More image models from OpenAI
About DALL·E 3
How good is DALL·E 3?
In blind side-by-side votes, DALL·E 3 scores 967 for text to image (#79 of 82). Higher is better; scores within about 8 points of each other are effectively tied.
Who makes DALL·E 3?
DALL·E 3 is an image model from OpenAI, released Nov 6, 2023.
What can DALL·E 3 do?
DALL·E 3 accepts text prompts and produces images. In practice: text to image.
Is DALL·E 3 open source?
No. DALL·E 3 is proprietary; you use it through an API or partner apps.
Where can I use DALL·E 3?
It is listed by 1 API host we track.
What are the alternatives to DALL·E 3?
The closest image models from other labs, by release date, are Stable Diffusion XL (Stability AI, Jul 9, 2023), Recraft V2 (Recraft, Mar 13, 2024), Ideogram (Ideogram, Apr 3, 2024) and FLUX.1 [dev] (Black Forest Labs, Aug 1, 2024).