Amazon

Amazon Nova Lite

Amazon's low-cost multimodal Nova Lite for fast image, video, and text processing on AWS Bedrock.

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, Amazon Bedrock model card

Price per 1M tokens
$0.06 in / $0.24 out
Context window300,000
Max output5,000
Min cache prefix1,000 tokens
Cache lifetime5 min
Batch discount-50%
Input
  • Text
  • Image
  • Video
Output
  • Text

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRateBatch
Input$0.06 / M$0.03 / M
Output$0.24 / M$0.12 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Estimated monthly cost
$16.80
at current list prices
Fresh input$12.00
Output$4.80
Track this automatically →

Provider

Where this model runs, and what it charges.

PlatformRegionInput / MOutput / MBatchAccess
AWS Bedrock
$0.06$0.24Direct

Some hosts price by region. Shown rates match the selected region.

Price history

Has this model gotten cheaper or more expensive?

EffectiveInput / OutputStatus
May 6, 2026 – July 10, 2026$0.06 / $0.24past
July 10, 2026$0.06 / $0.24current

More from Amazon

Other models from the same provider.

Stop estimating. Track it.

SuperPenguin meters every Amazon Nova Lite call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.