TPSTokens Per Second

Amazon Nova 2 Lite

Amazon AWS🇺🇸 United States
active
Compare with other models →
Context window1000K tokens

Version History

nova-2-liteminor

Amazon Bedrock now enables supervised fine-tuning, reinforcement fine-tuning, and model distillation for Nova 2 Lite. Fine-tuned models deploy on-demand at standard inference pricing without provisioned capacity.

2.0major

Nova 2 Lite expands context from 300K to 1M tokens, adds extended thinking with developer controls, native tool use, web grounding, and code interpreter. Recommended as upgrade path for all Nova 1 tiers with claims of 7x lower cost and 5x faster inference on reasoning tasks.

Coverage

product updateAmazon Web Services

Amazon Bedrock now supports fine-tuning for Nova models with three customization approaches

Amazon Bedrock now enables fine-tuning of Amazon Nova models using supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and model distillation. The service automates infrastructure provisioning and training orchestration, requiring only data upload to S3 and a single API call. Fine-tuned models run on-demand at standard inference pricing without provisioned capacity requirements.

2 min read
Amazon BedrockAmazon Novafine-tuning