Nova Lite

Amazon · Active · available in 14 of 16 regions

Tool useVisionPrompt cachingBatch inferenceStreaming EmbeddingsFine-tuning
Context window
300K
300,000 tokens
Max output
Input / 1M
$0.060
us-east-1
Output / 1M
$0.240

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) $0.060 $0.240 $0.015 $0 $0.030 $0.120 API
us-east-2 US East (Ohio) $0.060 $0.240 $0.015 $0 $0.030 $0.120 API
us-west-2 US West (Oregon) $0.060 $0.240 $0.015 $0 $0.030 $0.120 API
ca-central-1 Canada (Central) $0.064 $0.256 $0.016 $0 $0.032 $0.128 API
eu-west-1 EU (Ireland) $0.069 $0.276 $0.017 $0.034 $0.138 API
eu-west-2 EU (London) $0.084 $0.336 API
eu-west-3 EU (Paris) $0.088 $0.352 $0.022 $0.044 $0.176 API
eu-central-1 EU (Frankfurt) $0.078 $0.312 $0.019 $0.039 $0.156 API
eu-north-1 EU (Stockholm) $0.065 $0.260 $0.016 $0.032 $0.130 API
ap-southeast-1 Asia Pacific (Singapore) $0.081 $0.324 $0.020 $0.041 $0.162 API
ap-southeast-2 Asia Pacific (Sydney) $0.063 $0.252 $0.016 $0.032 $0.126 API
ap-northeast-1 Asia Pacific (Tokyo) $0.072 $0.288 $0.018 $0.036 $0.144 API
ap-northeast-2 Asia Pacific (Seoul) $0.071 $0.284 $0.018 $0.036 $0.142 API
ap-south-1 Asia Pacific (Mumbai) $0.071 $0.284 $0.018 $0.036 $0.142 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 Lite compared

Common questions

How much does Nova Lite cost on Amazon Bedrock?
$0.060 per 1M input tokens and $0.240 per 1M output tokens in us-east-1. Cached input reads at $0.015, 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 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 apac.amazon.nova-lite-v1:0 rather than the bare model ID.
What is the context window of Nova Lite?
300,000 tokens (300K).
What is the model ID for Nova Lite on Bedrock?
amazon.nova-lite-v1:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: apac.amazon.nova-lite-v1:0, ca.amazon.nova-lite-v1:0, eu.amazon.nova-lite-v1:0.

Other Amazon models