Nova 2 Lite

Amazon · Active · available in 14 of 16 regions

VisionPrompt cachingBatch inferenceStreaming Tool useEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.300
us-east-1
Output / 1M
$2.50

Model & inference profile IDs

Base model ID — direct on-demand invoke

Cross-region inference profiles (4)

Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
us-east-1 US East (N. Virginia) $0.300 $2.50 $0.075 $0 $0.150 $1.25 API
us-east-2 US East (Ohio) $0.300 $2.50 $0.075 $0 $0.150 $1.25 API
us-west-2 US West (Oregon) $0.300 $2.50 $0.075 $0 $0.150 $1.25 API
ca-central-1 Canada (Central) $0.320 $2.67 $0.080 $0 $0.160 $1.33 API
eu-west-1 EU (Ireland) $0.340 $2.87 $0.085 $0 $0.170 $1.44 API
eu-west-2 EU (London) $0.420 $3.52 $0.105 $0 $0.210 $1.76 API
eu-west-3 EU (Paris) $0.440 $3.69 $0.110 $0 $0.220 $1.84 API
eu-central-1 EU (Frankfurt) $0.390 $3.27 $0.098 $0 $0.195 $1.64 API
eu-north-1 EU (Stockholm) $0.330 $2.72 $0.083 $0 $0.195 $1.36 API
ap-southeast-1 Asia Pacific (Singapore) $0.410 $3.39 $0.102 $0 $0.205 $1.69 API
ap-southeast-2 Asia Pacific (Sydney) $0.320 $2.63 $0.080 $0 $0.160 $1.31 API
ap-northeast-1 Asia Pacific (Tokyo) $0.360 $3.01 $0.090 $0 $0.180 $1.51 API
ap-northeast-2 Asia Pacific (Seoul) $0.360 $2.96 $0.090 $0 $0.180 $1.48 API
ap-south-1 Asia Pacific (Mumbai) $0.350 $2.95 $0.087 $0 $0.175 $1.47 API

Region availability

TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.

Nova 2 Lite compared

Common questions

How much does Nova 2 Lite cost on Amazon Bedrock?
$0.300 per 1M input tokens and $2.50 per 1M output tokens in us-east-1. Cached input reads at $0.075, roughly a tenth of the input rate, which dominates the bill on agentic workloads that re-send a long prefix.
Which AWS regions support Nova 2 Lite?
14 of 16 regions: us-east-1, us-east-2, us-west-2, ca-central-1, eu-west-1, eu-west-2, eu-west-3, eu-central-1, eu-north-1, ap-southeast-1, ap-southeast-2, ap-northeast-1, ap-northeast-2, ap-south-1. Regions marked profile-only need a cross-region inference profile ID such as eu.amazon.nova-2-lite-v1:0 rather than the bare model ID.
What is the model ID for Nova 2 Lite on Bedrock?
amazon.nova-2-lite-v1:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: eu.amazon.nova-2-lite-v1:0, global.amazon.nova-2-lite-v1:0, jp.amazon.nova-2-lite-v1:0.

Other Amazon models