Amazon Nova Micro
Amazon
Amazon's text-only, lowest-latency Nova model (November 2024) on AWS Bedrock, delivering the fastest responses at the lowest cost per inference. Nova Micro suits high-throughput text tasks like classification, routing, and simple generation with a 128K context window.
Strengths
- Lowest latency and cost per inference in the Nova family
- 128K-token context window
- Ideal for classification, routing, and simple generation
- AWS Bedrock integration
Caveats
- Text-only (no image, video, or audio input)
- Lowest capability tier in the Nova family
- Proprietary - AWS Bedrock only
- Vendor
- Amazon
- Context Window
- 128,000 tokens
- License
- Proprietary
- Release Date
- 2024-11-20
- Modalities
- text
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
$0.035 per 1M input tokens, $0.14 per 1M output tokens via AWS Bedrock - the lowest-cost Nova tier. 128K-token context.