modelgrep
A

Amazon: Nova Micro 1.0

amazon/nova-micro-v1

168th smartest of 178Cheaper than 97% of paidTools
Use via OpenRouter ↗
Intelligence
10.3
168th of 178
Design Elo
Speed
79
96th fastest
Latency
299ms
first token
Input price
$0.035
8th cheapest
Context
128K
5K max out

How it compares

Smarter than6%
of all ranked models
Faster than67%
of all ranked models
Cheaper than97%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis8th percentile
Intelligence Index
10.3
Coding Index
4.1
Agentic Index
4.7
GPQA Diamond
36%
Humanity's Last Exam
5%
SciCode
9%
Tau²-Bench (agentic)
14%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Amazon Bedrock$0.035$0.14069.1%
Amazon Bedrock$0.035$0.140100%

Specifications

Context window128K
Max output5K
Knowledge cutoffOct 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

Nova Micro 1.0 FAQ

How much does Nova Micro 1.0 cost?

Nova Micro 1.0 costs $0.035 per million input tokens and $0.140 per million output tokens via OpenRouter, making it 8th cheapest of 298 paid models.

How smart is Nova Micro 1.0?

Nova Micro 1.0 scores 10.3 on the Artificial Analysis Intelligence Index, ranking 168th of 178 benchmarked models, with a GPQA Diamond score of 36%.

How fast is Nova Micro 1.0?

Nova Micro 1.0 generates around 79 tokens per second with 299ms time-to-first-token (p50), the 96th fastest tracked model.

What is Nova Micro 1.0's context window?

Nova Micro 1.0 supports a 128K-token context window and can output up to 5K tokens. It accepts text input.

Compare head-to-head