Imagegpt Small
OpenAI's ImageGPT Small is a transformer decoder model pretrained on 14 million images from ImageNet ILSVRC 2012 at a resolution of 32x32 pixels, learning to predict the next pixel value given the previous ones. It is genuinely best at learning an inner representation of images for downstream tasks such as feature extraction and unconditional image generation.
Input
Output
Context
1K
Max Output
1K
Parameters
-
Technical Specifications
Model TypeImage
Context Window1,024 tokens
Max Output Tokens1,024 tokens
ParametersNot available
Release DateMar 2, 2022
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Image
Output Modalities
ImageEmbedding
Capabilities
Resources & Links
More Models by OpenAI
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.