Models

Very low-cost multimodal model that processes text, images and video quickly. A strong default for high-volume workloads.

amazon/nova-lite300K context$0.06/M input$0.24/M output

Text-only model optimized for the lowest latency and cost. Great for classification, routing, extraction and short chat turns.

amazon/nova-micro128K context$0.035/M input$0.14/M output

Highly capable multimodal model with the best balance of accuracy, speed and cost across a wide range of tasks.

amazon/nova-pro300K context$0.8/M input$3.2/M output