modelgrep
A

Amazon: Nova Lite 1.0

amazon/nova-lite-v1

156th smartest of 178Cheaper than 91% of paidToolsVision
Use via OpenRouter ↗
Intelligence
12.7
156th of 178
Design Elo
Speed
87
81st fastest
Latency
529ms
first token
Input price
$0.060
26th cheapest
Context
300K
5K max out

How it compares

Smarter than12%
of all ranked models
Faster than73%
of all ranked models
Cheaper than91%
of all ranked models

Overview

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

Benchmarks

independent · via OpenRouter
Artificial Analysis13th percentile
Intelligence Index
12.7
Coding Index
5.1
Agentic Index
5.8
GPQA Diamond
43%
Humanity's Last Exam
5%
SciCode
14%
Tau²-Bench (agentic)
18%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Amazon Bedrock$0.060$0.24098.8%
Amazon Bedrock$0.060$0.24099.6%

Specifications

Context window300K
Max output5K
Knowledge cutoffOct 2024
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

Nova Lite 1.0 FAQ

How much does Nova Lite 1.0 cost?

Nova Lite 1.0 costs $0.060 per million input tokens and $0.240 per million output tokens via OpenRouter, making it 26th cheapest of 298 paid models.

How smart is Nova Lite 1.0?

Nova Lite 1.0 scores 12.7 on the Artificial Analysis Intelligence Index, ranking 156th of 178 benchmarked models, with a GPQA Diamond score of 43%.

How fast is Nova Lite 1.0?

Nova Lite 1.0 generates around 87 tokens per second with 529ms time-to-first-token (p50), the 81st fastest tracked model.

What is Nova Lite 1.0's context window?

Nova Lite 1.0 supports a 300K-token context window and can output up to 5K tokens. It accepts text, image input.

Compare head-to-head