AI Model Watch
Models / Amazon

Amazon Nova Pro

GA

Balanced multimodal (text, image, video input; text output). Lifecycle: Active. Model card states 'Model EOL date: No sooner than 12/4/2025' (floor). Supports Standard, Priority and Flex service tiers. Geo inference IDs us./eu.amazon.nova-pro-v1:0. Per-1K: input $0.0008, output $0.0032 — input/output confirmed on AWS blog 'Demystifying Amazon Bedrock Pricing' (2025-08-11). Cached input (cache read) = 25% of input = $0.0002/1K (= $0.20/M); cache-WRITE is priced at a premium (reported ~$1.00/M vs $0.80/M input). Cache-read figure derived from AWS Nova cache ratio, not separately fetched from a p

Provider
Amazon
Status
GA
Input price
$0.8 / 1M tokens
Output price
$3.20 / 1M tokens
Cached input
$0.2 / 1M tokens
Blended price
$1.40 / 1M tokens
Context window
300,000 tokens (300K)
Max output
5,000 tokens
Modality
text, image, video
Knowledge cutoff
2024-10
Released
5 Dec 2024
API string
amazon.nova-pro-v1:0

Source: Amazon official documentation ↗

See also

Compare Amazon Nova Pro with…

Amazon Nova Pro vs Claude Opus 4.8→

$1.40 vs $10 blended /M

Amazon Nova Pro vs Claude Opus 4.7→

$1.40 vs $10 blended /M

Amazon Nova Pro vs Claude Opus 4.6→

$1.40 vs $10 blended /M

Amazon Nova Pro vs Claude Opus 4.5→

$1.40 vs $10 blended /M