Amazon: Nova Micro 1.0

Text input Text output
Author's Description

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

Key Specifications
Cost
$$
Context
128K
Released
Dec 05, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Top P Temperature Stop Max Tokens
Features

This model supports the following features:

Tools
Performance Summary

Amazon Nova Micro 1.0 consistently performs among the fastest models, ranking in the 84th percentile across various benchmarks. It also offers highly competitive pricing, placing in the 89th percentile. The model demonstrates strong reliability with an 82% success rate, indicating consistent delivery of usable responses. In terms of performance across categories, Nova Micro 1.0 shows a notable strength in acknowledging uncertainty, achieving 94% accuracy in hallucination tests. It also performs well in ethics (98% accuracy) and coding (82% accuracy). However, its performance in general knowledge (95% accuracy) and mathematics (39% accuracy) is average to below average compared to other models. Significant weaknesses are observed in instruction following (14% accuracy) and complex reasoning (2% accuracy), where it ranks in the lower percentiles. While its speed and cost efficiency are excellent across the board, the duration for general knowledge and ethics benchmarks was notably high.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.035
Completion $0.14

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Amazon Bedrock
Amazon Bedrock | amazon/nova-micro-v1 128K $0.035 / 1M tokens $0.14 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by amazon