Model Tracker
DALL·E
DALL·E is an AI model made by OpenAI. OpenAI released it on 5 January 2021. It takes text, image and returns image.
- Released
- 5 January 2021 — openai.com, read 16 October 2026
- Status
- Not confirmed: The maker's page introduces the research model but does not state its current status or say that this original model is currently served or retired.
- Takes
- Text, Image — openai.com, read 16 October 2026
- Returns
- Image — openai.com, read 16 October 2026
- Open weights
- Not confirmed: The maker's page does not state whether the model weights are open or downloadable.
- Licence
- Not confirmed: The maker's page does not name a licence for the model.
- Context window
- Not confirmed: The maker's page is not a model card or API documentation, the sources specified for this field.
- Longest answer
- Not confirmed: The maker's page does not print a standard maximum output-token limit.
- Knowledge cutoff
- Not confirmed: The maker's page does not state a knowledge cutoff.
- API price, input
- Not confirmed: The maker's page does not list a standard API input-token price for the original DALL·E model.
- API price, output
- Not confirmed: The maker's page does not list a standard API output-token price for the original DALL·E model.
- Where
- Not confirmed: The maker's page does not specify availability through the register's categories: API, consumer app, downloadable weights, or cloud marketplaces.
- Parameters
- 12,000,000,000 parameters — openai.com, read 16 October 2026
- Model card
- Not confirmed: The maker's page links to a research paper, but does not identify a model card or system card for the original DALL·E model.
Questions
When was DALL·E released?
OpenAI released DALL·E on 5 January 2021.
What does DALL·E take and return?
DALL·E takes text, image and returns image.
How many parameters does DALL·E have?
DALL·E has 12,000,000,000 parameters parameters, as OpenAI publishes it.
More from OpenAI
- ada
- babbage
- babbage-002
- code-davinci-002
- computer-use-preview
- curie
- dall-e-3
- DALL·E 2
- davinci
- davinci-002
- GPT-3.5 Turbo
- GPT-3.5 Turbo Instruct
- GPT-4
- GPT-4 Turbo
- GPT-4.1
- GPT-4.1 mini
- GPT-4.1 nano
- GPT-4.5
- GPT-4.5 Preview
- GPT-4o
- GPT-4o mini
- GPT-4o Mini Search Preview
- GPT-4o Mini Transcribe
- GPT-4o Mini TTS
Sources
- DALL·E: Creating images from text (read 16 October 2026)