modelgrep
A

Amazon: Nova 2 Lite

amazon/nova-2-lite-v1

99th smartest of 181ReasoningToolsVision
Use via OpenRouter ↗
Intelligence
24.6
99th of 181
Design Elo
Speed
120
39th fastest
Latency
504ms
first token
Input price
$0.300
133rd cheapest
Context
1M
66K max out

How it compares

Smarter than45%
of all ranked models
Faster than87%
of all ranked models
Cheaper than55%
of all ranked models

Overview

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

Benchmarks

independent · via OpenRouter
Artificial Analysis42th percentile
Intelligence Index
24.6
Coding Index
13.6
Agentic Index
27.8
GPQA Diamond
70%
Humanity's Last Exam
4%
SciCode
33%
Tau²-Bench (agentic)
72%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Amazon Bedrock$0.300$2.5099.8%
Amazon Bedrock$0.300$2.5099.5%

Specifications

Context window1M
Max output66K
Knowledge cutoff
Input modalitiestext, image, video, file
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

Nova 2 Lite FAQ

How much does Nova 2 Lite cost?

Nova 2 Lite costs $0.300 per million input tokens and $2.50 per million output tokens via OpenRouter, making it 133rd cheapest of 298 paid models.

How smart is Nova 2 Lite?

Nova 2 Lite scores 24.6 on the Artificial Analysis Intelligence Index, ranking 99th of 181 benchmarked models, with a GPQA Diamond score of 70%.

How fast is Nova 2 Lite?

Nova 2 Lite generates around 120 tokens per second with 504ms time-to-first-token (p50), the 39th fastest tracked model.

What is Nova 2 Lite's context window?

Nova 2 Lite supports a 1M-token context window and can output up to 66K tokens. It accepts text, image, video, file input.

Compare head-to-head