LightweightAmazon

Nova Micro

Nova Micro is Amazon's lightweight text model in the Nova family, designed for fast, cost-effective tasks with a 128K token context window.

Context 128K
Tier Lightweight
Input from
$0.018 / 1M tokens
across 2 providers
Compare Prices

API Pricing

Cheapest on Amazon AWS — 40% below avg
ProviderInput / 1MOutput / 1MSpeedTTFTUpdated
Amazon AWS logo
Amazon AWSBatch
$0.018$0.070325 t/s608ms4/14/2026
Amazon AWS logo
Amazon AWS
$0.035$0.140325 t/s608ms4/14/2026
OpenRouter logo
OpenRouter
$0.035$0.140325 t/s608ms4/14/2026

Prices updated daily. Last check: 4/14/2026

Model Details

General

Creator
Amazon
Family
Nova
Tier
Lightweight
Context Window
128K
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No

Strengths & Limitations

  • Fast inference speed at 173.71 output tokens per second
  • Quick response initiation with 404ms time to first token
  • 128K token context window for processing lengthy documents
  • Lightweight architecture optimized for cost efficiency
  • Integration with Amazon Bedrock ecosystem
  • Suitable for high-volume automated workflows
  • Low latency for real-time applications
  • No tool calling or function execution capabilities
  • Text-only input - no image or multimodal support
  • Proprietary model with no open source weights available
  • Limited reasoning capabilities compared to higher-tier Nova models
  • No advanced features like structured output modes

Key Features

•128K token context window
•Text-only input and output
•Streaming response support
•Amazon Bedrock API integration
•Batch processing capabilities
•Real-time inference optimization
•UTF-8 text encoding support
•JSON API response format

About Nova Micro

Nova Micro is Amazon's entry-level model in the Nova family, positioned as a lightweight option for high-volume, cost-sensitive applications. As part of Amazon's proprietary model lineup, it sits at the foundation tier below more capable Nova variants, focusing on speed and efficiency over advanced reasoning capabilities. The model supports a 128K token context window and handles text-only interactions, making it suitable for straightforward language tasks. With benchmark speeds of 173.71 output tokens per second and a time to first token of 404ms, Nova Micro prioritizes rapid response times. However, it lacks tool calling functionality and multimodal capabilities, reflecting its positioning as a streamlined model for basic text processing. Nova Micro targets use cases where speed and cost efficiency matter more than complex reasoning or advanced features. Organizations typically deploy it for high-volume text classification, content moderation, simple Q&A, and other automated workflows where faster, more capable models would be unnecessary overhead.

Common Use Cases

Nova Micro excels in high-volume, cost-sensitive applications where basic language understanding is sufficient. Its fast inference speed and lightweight design make it ideal for content moderation pipelines, simple chatbots, text classification systems, and automated customer service responses. Organizations use it for sentiment analysis, basic summarization, simple Q&A systems, and content filtering where the 128K context window provides adequate document processing capability. The model's speed optimization makes it particularly valuable for real-time applications requiring immediate responses, such as live chat systems or automated email routing, where complex reasoning is unnecessary but consistent, fast text processing is essential.

Frequently Asked Questions

How much does Nova Micro cost per million tokens?

Nova Micro pricing varies by provider and usage type (standard vs batch processing). Check the pricing table above for current rates across all available providers offering Nova Micro access.

What is Nova Micro best used for?

Nova Micro is best suited for high-volume, cost-sensitive text processing tasks like content moderation, simple classification, basic Q&A, and automated responses. Its fast inference speed and lightweight design make it ideal when you need quick, consistent text processing without complex reasoning or multimodal capabilities.

Does Nova Micro support tool calling or function execution?

No, Nova Micro does not support tool calling or function execution capabilities. It's designed as a lightweight text model focused on speed and cost efficiency. For tool calling features, you would need to use higher-tier models in the Nova family or other providers that offer function calling support.