Nova Micro vs Nova Pro on Amazon Bedrock

In us-east-1, Nova Micro costs $0.035 per 1M input tokens against $0.800 — a 22.9× difference. Prices, context, capabilities and region coverage below.

amazon.nova-micro-v1:0
Input / 1M
$0.035
Output / 1M
$0.140
Context
128K
Est. / month
$37.80
Nova Pro Amazon
amazon.nova-pro-v1:0
Input / 1M
$0.800
Output / 1M
$3.20
Context
300K
Est. / month
$864.00

Capabilities

Capability Nova Micro Nova Pro
Tool use
Vision
Prompt caching
Batch inference
Streaming

Region availability

Region Nova Micro Nova Pro
us-east-1 US East (N. Virginia) On-demand On-demand
us-east-2 US East (Ohio) Inference profile only Inference profile only
us-west-2 US West (Oregon) Inference profile only Inference profile only
eu-west-1 EU (Ireland) Inference profile only Inference profile only
eu-west-2 EU (London) On-demand On-demand
eu-west-3 EU (Paris) Inference profile only Inference profile only
eu-central-1 EU (Frankfurt) Inference profile only Inference profile only
eu-north-1 EU (Stockholm) Inference profile only Inference profile only
ap-southeast-1 Asia Pacific (Singapore) Inference profile only Inference profile only
ap-southeast-2 Asia Pacific (Sydney) On-demand On-demand
ap-northeast-1 Asia Pacific (Tokyo) Inference profile only Inference profile only
ap-northeast-2 Asia Pacific (Seoul) Inference profile only Inference profile only
ap-south-1 Asia Pacific (Mumbai) Inference profile only Inference profile only

13 of 16 regions support both models.

Common questions

Is Nova Micro or Nova Pro cheaper on Amazon Bedrock?
Nova Micro is cheaper on input tokens: $0.035 against $0.800 per 1M in us-east-1, a 22.9× difference. At 2,000 runs a day with 12,000 input and 1,500 output tokens each, that is $37.80 against $864.00 a month before any caching or batch discount.
Does Nova Micro or Nova Pro have the larger context window?
Nova Pro, at 300K tokens against 128K.
Which regions support Nova Micro and Nova Pro?
Nova Micro runs in 13 of the 16 AWS regions tracked here and Nova Pro in 13. 13 regions support both, so a workload that may switch between them should target one of those.