Amazon
AmazonAmazon Nova Micro
Amazon's text-only Nova Micro, the lowest-latency and lowest-cost model in the Nova family, with first-party AWS Bedrock on-demand rates.
ActiveReleased December 5, 2024Knowledge cutoff October 1, 2024
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).
Source: Amazon Nova pricing, Amazon Bedrock pricing, Amazon Nova overview
Price per 1M tokens
$0.035 in / $0.14 out
Context window128,000
Max output5,000
Batch discount-50%
ModalitiesText → Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate | Batch |
|---|---|---|
| Input | $0.035 / M | $0.0175 / M |
| Output | $0.14 / M | $0.07 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Estimated monthly cost
$9.80
at current list prices
Fresh input$7.00
Output$2.80
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Batch | Access |
|---|---|---|---|---|
AWS Bedrock | $0.035 | $0.14 | ✓ | Direct |
Price history
Has this model gotten cheaper or more expensive?
No changePriced at $0.035 / $0.14 per 1M since August 5, 2026.
More from Amazon
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Amazon Nova Micro call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.