Amazon Nova Lite
Amazon · December 2024
● activeCloseddecoder onlymultimodalAPI Available
Context Window300K tokens
Description
A budget-friendly multimodal model that can process images, video, and text together. Designed as the cost-effective option for applications that need to understand visual content without requiring the highest accuracy — like content moderation, image captioning, or video summarization at scale.
Key Innovations
Multimodal
MultimodalProcessing multiple types of input (text, images, audio, video) in a single model.
Distillation
DistillationTraining a smaller 'student' model to mimic a larger 'teacher' model, preserving capability at lower cost.