Today's price · per 1M tokens
Input
$0.300
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$0.850
blended $/1M — 3:1 weighted input:output
How this price is scoped: We publish the Standard tier on Bedrock's global cross-Region inference profile (global.amazon.nova-2-lite-v1:0), as AWS's own Nova pricing page lists it for US East (N. Virginia): $0.30 / 1M input and $2.50 / 1M output tokens. On the same global profile the Priority tier costs $0.525 / $4.375 and the Flex and Batch tiers $0.15 / $1.25. The geo (us.) profile and in-Region calls cost 10% more on every tier, $0.33 / $2.75 on Standard. AWS says cache reads cost 75% less than the input rate; that rate is not published here.
Price receipt
We read Amazon's own pricing page on and found Nova 2 Lite $0.30 $2.50 listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 2f70dce8b9.
Overview
Amazon's second-generation Lite model on Bedrock, a separate model from the original Nova Lite: it takes text, images and video, has a 1M-token context window and up to 64K output tokens, and can reason step by step when you switch that on. $0.30 per 1M input tokens and $2.50 per 1M output tokens on the Standard tier through Bedrock's global cross-Region profile.
Capabilities
struck through = not supportedSpecifications
- Provider
- Amazon
- Context window
- 1M tokens
- Modality
- text, image, video
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Status
- Current
- Last updated
- Tags
Availability verified: — listed on Amazon's own page