Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Amazon - Closed weights

Amazon Nova Pro pricing and specs

Amazon Nova Pro is a closed-weights model from Amazon that costs $0.80 per 1M input tokens and $3.20 per 1M output tokens on the first-party API, with a 300K-token context window.

Last verified from aws.amazon.com. All sources

Input / 1M
$0.80
Output / 1M
$3.20
Context
300K tokens
Weights
Closed

Pricing per 1M tokens

ItemPrice / 1M tokens
Input$0.80
Output$3.20
Cache read$0.20
Batch inputBatch requests$0.40
Batch outputBatch requests$1.60
Fast mode inputFast mode requests$1
Fast mode outputFast mode requests$4

Note: Prices are US East (N. Virginia), Standard tier, Geo cross-Region inference and in-Region. No Global profile. fast mode pricing is the page row 'Amazon Nova Pro (w/ latency optimized inference)' at $1.00 / $4.00. Its regional availability was not checked. Other tiers: Priority $1.40 / $5.60, Flex $0.40 / $1.60. The $0.20 cache-read price is printed in the page's model-customization On Demand Inference table, which states custom models are priced the same as base models. No cache-write price is listed for Nova. The model card states '300K tokens' context and '10K' max output, recorded as 300,000 and 10,000. The release date is from the AWS What's New launch post (Dec 3, 2024). The Bedrock model card gives the launch date as Dec 05, 2024.

Specs

Context window
300,000 tokens
Max output
10,000 tokens
Release date
Provider
Amazon
API model id
amazon.nova-pro-v1:0
Vercel AI Gateway id
amazon/nova-pro
Weights
Closed weights

What Amazon Nova Pro costs in practice

Worked from the standard list rates above, with the math shown so you can swap in your own token counts.

One agent session

1M input tokens and 100K output tokens, no caching.

  • Input1M x $0.80 = $0.80
  • Output0.1M x $3.20 = $0.32

$1.12per session

A chat app

10,000 requests a day at 2K input and 500 output tokens each.

  • Input20M x $0.80 = $16.00
  • Output5M x $3.20 = $16.00

$32.00per day

$960.00 per 30-day month

The same session at a 90% cache hit

90% of the input is read from the prompt cache. The one-time cache write premium is not included.

  • Cached input0.9M x $0.20 = $0.18
  • Uncached input0.1M x $0.80 = $0.08
  • Output0.1M x $3.20 = $0.32

$0.58per session

Compare with

ModelInput / 1MOutput / 1M
Amazon Nova Pro (this page)$0.80$3.20
GLM-5Z.ai$1$3.20
Qwen3.5-122B-A10BAlibaba Cloud (Qwen)$0.40$3.20
ERNIE 5.0Baidu$0.84$3.38
Gemini 3 Flash PreviewGoogle$0.50$3
Amazon Nova 2 LiteAmazon$0.30$2.50
Amazon Nova LiteAmazon$0.06$0.24
Amazon Nova MicroAmazon$0.035$0.14
Amazon Nova PremierAmazon$2.50$12.50

FAQ

How much does Amazon Nova Pro cost per million tokens?

Amazon Nova Pro costs $0.80 per 1M input tokens and $3.20 per 1M output tokens on Amazon's first-party API, per aws.amazon.com on October 17, 2026. Per 1M tokens, cache reads cost $0.20, and the batch rate is $0.40 input and $1.60 output.

What is Amazon Nova Pro's context window?

Amazon Nova Pro has a 300,000-token context window and returns up to 10,000 output tokens per response.

Are Amazon Nova Pro's weights open?

No. Amazon Nova Pro is a closed-weights model. You call it through Amazon's API as amazon.nova-pro-v1:0 or through Vercel AI Gateway as amazon/nova-pro.

When was Amazon Nova Pro released?

Amazon released Amazon Nova Pro on December 3, 2024.

Sources

Last verified from aws.amazon.com.

Newsletter

Get model price changes as they ship

One email per week. New model releases, price cuts and what they mean for your bill.