Nova Pro Pricing & Token Calculator (Amazon)

Input / Prompt

$0.40/ 1M tokens

$0.0004 per 1K tokens

Output / Completion

$1.60/ 1M tokens

$0.0016 per 1K tokens

Prompt Cache Read

$0.10/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.20/ 1M in

Save 50% via Batch API

Price Ratio

1 : 4.0

Prompt to completion factor

Regional Reach

24AWS Regions

Compare 24 regions ↓

Nova Pro Spend Estimator

Model inference spend by prompt volume, cache hit rate, and batch processing.

Prompt Tokens (Millions / month)

M tokens

Completion Tokens (Millions / month)

M tokens

Prompt Cache Hit Rate(75% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $0.40/1M · Output: $1.60/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Nova Pro on AWS

Prompt CachingSave ~75%

Caches repetitive system instructions, schemas, and document prefixes in memory with a 5-minute TTL.

Read Rate: $0.10 / 1M tokens
Write Rate: $0.50 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 50%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $0.20 / 1M tokens
Batch Output: $0.80 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers24 Regions

AWS Bedrock supports standard on-demand inference, priority reserved throughput, and cross-region routing.

Standard: Lowest latency, pay-per-token with zero commitments
Cross-Region Routing: Automatically burst traffic to available regional capacity
GovCloud: Dedicated isolated compliance partitions with +20% uplift

Regional Pricing Matrix

Live rates across all 24 available AWS cloud regions

Baseline: $0.40/1M inGovCloud: $2.24/1M in24 Global Regions

AWS Region	Prompt Input	Completion Output	Cache Read	Batch Input	Pricing Tier
US East (N. Virginia)`us-east-1`	$0.80/1M	$1.60/1M	$0.20/1M	—/1M	+100% vs Baseline
US West (Oregon)`us-west-2`	$1.40/1M	$3.20/1M	$0.20/1M	—/1M	+250% vs Baseline
EU (Frankfurt)`eu-central-1`	$0.53/1M	$2.10/1M	$0.13/1M	—/1M	+31% vs Baseline
EU (Ireland)`eu-west-1`	$0.46/1M	$1.84/1M	$0.12/1M	—/1M	+15% vs Baseline
Asia Pacific (Tokyo)`ap-northeast-1`	$1.68/1M	$3.84/1M	$0.24/1M	—/1M	+320% vs Baseline
AWS GovCloud (US-West)`us-gov-west-1`	$1.68/1M	$1.92/1M	$0.12/1M	—/1M	GovCloud (+320%)
Asia Pacific (Jakarta)`ap-southeast-3`	$1.47/1M	$5.88/1M	$0.10/1M	—/1M	+267% vs Baseline
Asia Pacific (Malaysia)`ap-southeast-5`	$0.48/1M	$1.92/1M	$0.12/1M	—/1M	+20% vs Baseline
Asia Pacific (Melbourne)`ap-southeast-4`	$1.52/1M	$6.09/1M	$0.11/1M	—/1M	+281% vs Baseline
Asia Pacific (Mumbai)`ap-south-1`	$0.47/1M	$1.88/1M	$0.23/1M	—/1M	+17% vs Baseline
Asia Pacific (Seoul)`ap-northeast-2`	$0.47/1M	$6.65/1M	$0.12/1M	—/1M	+19% vs Baseline
Asia Pacific (Singapore)`ap-southeast-1`	$1.08/1M	$2.16/1M	$0.47/1M	—/1M	+170% vs Baseline
Asia Pacific (Sydney)`ap-southeast-2`	$0.42/1M	$1.68/1M	$0.21/1M	—/1M	+5% vs Baseline
Asia Pacific (Taipei)`ap-east-2`	$1.68/1M	$1.92/1M	$0.42/1M	—/1M	+320% vs Baseline
Asia Pacific (Thailand)`ap-southeast-7`	$0.48/1M	$1.92/1M	$0.42/1M	—/1M	+20% vs Baseline
EU (London)`eu-west-2`	$1.13/1M	$2.26/1M	$0.49/1M	—/1M	+182% vs Baseline
EU (Milan)`eu-south-1`	$2.24/1M	$5.21/1M	$0.16/1M	—/1M	+460% vs Baseline
EU (Paris)`eu-west-3`	$2.06/1M	$2.36/1M	$0.15/1M	—/1M	+416% vs Baseline
EU (Stockholm)`eu-north-1`	$0.87/1M	$6.09/1M	$0.38/1M	—/1M	+117% vs Baseline
Europe (Spain)`eu-south-2`	$1.54/1M	$1.76/1M	$0.11/1M	—/1M	+285% vs Baseline
Israel (Tel Aviv)`il-central-1`	$0.50/1M	$4.00/1M	$0.13/1M	—/1M	+25% vs Baseline
Middle East (UAE)`me-central-1`	$0.80/1M	$1.60/1M	$0.10/1M	—/1M	+100% vs Baseline
US East (Ohio)`us-east-2`	$0.40/1M	$5.60/1M	$0.20/1M	—/1M	Baseline
US West (N. California)`us-west-1`	$0.52/1M	$2.06/1M	$0.13/1M	—/1M	+29% vs Baseline

Developer Quickstart

Invoke Nova Pro via Amazon Bedrock Converse API

Python (boto3) · Amazon Bedrock Runtime

import boto3

# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="amazon.nova-pro-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Nova Pro."}]
        }
    ],
    inferenceConfig={
        "maxTokens": 1024,
        "temperature": 0.7
    }
)

output_text = response["output"]["message"]["content"][0]["text"]
usage = response["usage"]
print(f"Response: {output_text}")
print(f"Usage: {usage['inputTokens']} in, {usage['outputTokens']} out")