Nova 2.0 Pro Pricing & Token Calculator (Amazon)

Input / Prompt

$0.63/ 1M tokens

$0.0006 per 1K tokens

Output / Completion

$5.00/ 1M tokens

$0.0050 per 1K tokens

Prompt Cache Read

$0.16/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.31/ 1M in

Save 50% via Batch API

Price Ratio

1 : 8.0

Prompt to completion factor

Regional Reach

25AWS Regions

Compare 25 regions ↓

Nova 2.0 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: $0.63/1M · Output: $5.00/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Nova 2.0 Pro on AWS

Prompt CachingSave ~75%

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

Read Rate: $0.16 / 1M tokens
Write Rate: $0.78 / 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: $0.31 / 1M tokens
Batch Output: $2.50 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers25 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 25 available AWS cloud regions

Baseline: $0.63/1M inGovCloud: $3.08/1M in25 Global Regions

AWS Region	Prompt Input	Completion Output	Cache Read	Batch Input	Pricing Tier
US East (N. Virginia)`us-east-1`	$2.41/1M	$11.00/1M	—/1M	—/1M	+285% vs Baseline
US West (Oregon)`us-west-2`	$0.63/1M	$5.50/1M	—/1M	—/1M	Baseline
EU (Frankfurt)`eu-central-1`	$1.63/1M	$6.54/1M	—/1M	—/1M	+161% vs Baseline
EU (Ireland)`eu-west-1`	$2.50/1M	$11.47/1M	—/1M	—/1M	+300% vs Baseline
Asia Pacific (Tokyo)`ap-northeast-1`	$1.51/1M	$6.25/1M	—/1M	—/1M	+142% vs Baseline
Asia Pacific (Jakarta)`ap-southeast-3`	$0.66/1M	$5.28/1M	—/1M	—/1M	+6% vs Baseline
Asia Pacific (Malaysia)`ap-southeast-5`	$1.69/1M	$13.56/1M	—/1M	—/1M	+170% vs Baseline
Asia Pacific (Melbourne)`ap-southeast-4`	$0.68/1M	$5.42/1M	—/1M	—/1M	+9% vs Baseline
Asia Pacific (Mumbai)`ap-south-1`	$1.48/1M	$20.65/1M	—/1M	—/1M	+137% vs Baseline
Asia Pacific (Seoul)`ap-northeast-2`	$2.59/1M	$5.92/1M	—/1M	—/1M	+314% vs Baseline
Asia Pacific (Singapore)`ap-southeast-1`	$0.84/1M	$6.78/1M	—/1M	—/1M	+35% vs Baseline
Asia Pacific (Sydney)`ap-southeast-2`	$1.31/1M	$10.51/1M	—/1M	—/1M	+110% vs Baseline
Asia Pacific (Taipei)`ap-east-2`	$2.64/1M	$21.88/1M	—/1M	—/1M	+323% vs Baseline
Asia Pacific (Thailand)`ap-southeast-7`	$1.69/1M	$6.78/1M	—/1M	—/1M	+170% vs Baseline
Canada (Central)`ca-central-1`	$0.73/1M	$5.33/1M	—/1M	—/1M	+17% vs Baseline
Canada West (Calgary)`ca-west-1`	$0.70/1M	$19.70/1M	—/1M	—/1M	+13% vs Baseline
EU (London)`eu-west-2`	$3.08/1M	$14.07/1M	—/1M	—/1M	+393% vs Baseline
EU (Milan)`eu-south-1`	$1.00/1M	$16.05/1M	—/1M	—/1M	+61% vs Baseline
EU (Paris)`eu-west-3`	$0.92/1M	$14.74/1M	—/1M	—/1M	+47% vs Baseline
EU (Stockholm)`eu-north-1`	$0.68/1M	$5.43/1M	—/1M	—/1M	+9% vs Baseline
Europe (Spain)`eu-south-2`	$2.42/1M	$5.51/1M	—/1M	—/1M	+286% vs Baseline
Israel (Tel Aviv)`il-central-1`	$2.73/1M	$12.51/1M	—/1M	—/1M	+337% vs Baseline
Middle East (UAE)`me-central-1`	$2.19/1M	$5.01/1M	—/1M	—/1M	+250% vs Baseline
US East (Ohio)`us-east-2`	$0.69/1M	$5.50/1M	—/1M	—/1M	+10% vs Baseline
US West (N. California)`us-west-1`	$0.89/1M	$14.12/1M	—/1M	—/1M	+42% vs Baseline

Developer Quickstart

Invoke Nova 2.0 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-2-0-pro-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Nova 2.0 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")