Foundation Model · Amazon BedrockNova FamilyBalanced TierTextMulti-Tier Pricing

Nova 2.0 Pro

Amazon Bedrock token pricing and cost optimization reference for Nova 2.0 Pro.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 25 AWS regions.

ProviderAmazon

Maker HQSeattle, Washington, USA

Class / TierBalanced

ModalityText

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions25 Global

Bedrock Model IDamazon.nova-2-0-pro-v1:0

Input / Prompt

$1.25/ 1M tokens

$0.0013 per 1K tokens

Output / Completion

$10.00/ 1M tokens

$0.0100 per 1K tokens

Prompt Cache Read

$0.31/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.63/ 1M in

Save 50% via Batch API

Price Ratio

1 : 8.0

Prompt to completion factor

Regional Reach

25AWS Regions

Compare 25 regions ↓

Alternatives to Nova 2.0 Pro

Option	Price vs Nova 2.0 Pro	Why look at it
Nova Pro Latency Optimized Compare →	input-20%-$0.25/1M output-60%-$6.00/1M Standard tier, per 1M tokens	Next step down in price from Amazon
Nova Premier Compare →	input+100%+$1.25/1M output+25%+$2.50/1M Standard tier, per 1M tokens	Next step up in price from Amazon (flagship tier)
Nova Pro Compare →	input-36%-$0.45/1M output-68%-$6.80/1M Standard tier, per 1M tokens	Same Nova line, different version
Nova 2.0 Omni Compare →	input-76%-$0.95/1M output-75%-$7.50/1M Standard tier, per 1M tokens	Also from Amazon (general tier)

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: $1.25/1M · Output: $10.00/1M

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 5-minute and extended 1-hour TTL tiers.

Read Rate: $0.31 / 1M tokens
Write Rate (5m TTL): $1.56 / 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: $0.63 / 1M tokens
Batch Output: $5.00 / 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: $1.25/1M inGovCloud: $2.01/1M in25 Global Regions

AWS Region	Prompt Input $/1M	Completion Output $/1M	Cache Read $/1M	Batch Input $/1M	Pricing Tier
us-east-1 US East (N. Virginia)	$1.25	$10.00	—	$0.63	Baseline
us-west-2 US West (Oregon)	$1.25	$10.00	—	$0.63	Baseline
eu-central-1 EU (Frankfurt)	$1.63	$13.08	—	$0.81	+30% vs Baseline
eu-west-1 EU (Ireland)	$1.43	$11.47	—	$0.71	+14% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$1.51	$12.50	—	$0.76	+21% vs Baseline
ap-southeast-3 Asia Pacific (Jakarta)	$1.32	$10.56	—	$0.66	+6% vs Baseline
ap-southeast-5 Asia Pacific (Malaysia)	$1.69	$13.56	—	$0.84	+35% vs Baseline
ap-southeast-4 Asia Pacific (Melbourne)	$1.36	$10.84	—	$0.68	+9% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$1.48	$11.80	—	$0.74	+18% vs Baseline
ap-northeast-2 Asia Pacific (Seoul)	$1.48	$11.84	—	$0.74	+18% vs Baseline
ap-southeast-1 Asia Pacific (Singapore)	$1.69	$13.56	—	$0.84	+35% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$1.31	$10.51	—	$0.66	+5% vs Baseline
ap-east-2 Asia Pacific (Taipei)	$1.51	$12.50	—	$0.76	+21% vs Baseline
ap-southeast-7 Asia Pacific (Thailand)	$1.69	$13.56	—	$0.84	+35% vs Baseline
ca-central-1 Canada (Central)	$1.33	$10.66	—	$0.67	+6% vs Baseline
ca-west-1 Canada West (Calgary)	$1.41	$11.26	—	$0.70	+13% vs Baseline
eu-west-2 EU (London)	$1.76	$14.07	—	$0.88	+41% vs Baseline
eu-south-1 EU (Milan)	$2.01	$16.05	—	$1.00	+61% vs Baseline
eu-west-3 EU (Paris)	$1.84	$14.74	—	$0.92	+47% vs Baseline
eu-north-1 EU (Stockholm)	$1.36	$10.87	—	$0.68	+9% vs Baseline
eu-south-2 Europe (Spain)	$1.38	$11.02	—	$0.69	+10% vs Baseline
il-central-1 Israel (Tel Aviv)	$1.56	$12.51	—	$0.78	+25% vs Baseline
me-central-1 Middle East (UAE)	$1.25	$10.02	—	$0.63	Baseline
us-east-2 US East (Ohio)	$1.25	$10.00	—	$0.63	Baseline
us-west-1 US West (N. California)	$1.61	$12.84	—	$0.81	+29% 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")