Foundation Model · Amazon BedrockNova FamilyGeneral TierMultimodalMulti-Tier Pricing

Nova 2.0 Omni

Amazon Bedrock token pricing and cost optimization reference for Nova 2.0 Omni.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 27 AWS regions.

ProviderAmazon

Maker HQSeattle, Washington, USA

Class / TierGeneral

ModalityMultimodal

Prompt CachingSave 75%

Batch APISave 33%

AWS Regions27 Global

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

Input / Prompt

$0.30/ 1M tokens

$0.0003 per 1K tokens

Output / Completion

$2.50/ 1M tokens

$0.0025 per 1K tokens

Prompt Cache Read

$0.07/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.20/ 1M in

Save 33% via Batch API

Price Ratio

1 : 8.3

Prompt to completion factor

Regional Reach

27AWS Regions

Compare 27 regions ↓

Alternatives to Nova 2.0 Omni

Option	Price vs Nova 2.0 Omni	Why look at it
Titan Text Premier Compare →	input+67%+$0.20/1M output-40%-$1.00/1M Standard tier, per 1M tokens	Next step down in price from Amazon (flagship tier)
Nova Pro Compare →	input+167%+$0.50/1M output+28%+$0.70/1M Standard tier, per 1M tokens	Next step up in price from Amazon (balanced tier)
Nova 2.0 Lite Compare →	inputsame price outputsame price Standard tier, per 1M tokens	Same Nova line, different version
Nova Pro Latency Optimized Compare →	input+233%+$0.70/1M output+60%+$1.50/1M Standard tier, per 1M tokens	Also from Amazon (balanced tier)

Nova 2.0 Omni 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: $0.30/1M · Output: $2.50/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Nova 2.0 Omni 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: $0.07 / 1M tokens
Write Rate (5m TTL): $0.38 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 33%

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

Batch Input: $0.20 / 1M tokens
Batch Output: $1.30 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers27 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 27 available AWS cloud regions

Baseline: $0.20/1M inGovCloud: $0.50/1M in27 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)	$0.30	$2.50	—	$0.20	+50% vs Baseline
us-west-2 US West (Oregon)	$0.30	$2.50	—	$0.20	+50% vs Baseline
eu-central-1 EU (Frankfurt)	$0.40	$3.30	—	$0.20	+100% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$0.40	$3.00	—	$0.20	+100% vs Baseline
af-south-1 Africa (Cape Town)	$0.30	$2.80	—	$0.20	+50% vs Baseline
ap-southeast-3 Asia Pacific (Jakarta)	$0.30	$2.60	—	$0.20	+50% vs Baseline
ap-southeast-5 Asia Pacific (Malaysia)	$0.40	$3.40	—	$0.20	+100% vs Baseline
ap-southeast-4 Asia Pacific (Melbourne)	$0.30	$2.70	—	$0.20	+50% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$0.40	$3.00	—	$0.20	+100% vs Baseline
ap-northeast-2 Asia Pacific (Seoul)	$0.40	$3.00	—	$0.20	+100% vs Baseline
ap-southeast-1 Asia Pacific (Singapore)	$0.40	$3.40	—	$0.20	+100% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$0.30	$2.60	—	$0.20	+50% vs Baseline
ap-east-2 Asia Pacific (Taipei)	$0.40	$3.00	—	$0.20	+100% vs Baseline
ap-southeast-7 Asia Pacific (Thailand)	$0.40	$3.40	—	$0.20	+100% vs Baseline
ca-central-1 Canada (Central)	$0.30	$2.70	—	$0.20	+50% vs Baseline
ca-west-1 Canada West (Calgary)	$0.30	$2.80	—	$0.20	+50% vs Baseline
eu-west-2 EU (London)	$0.40	$3.50	—	$0.20	+100% vs Baseline
eu-south-1 EU (Milan)	$0.50	$4.00	—	$0.20	+150% vs Baseline
eu-west-3 EU (Paris)	$0.40	$3.70	—	$0.20	+100% vs Baseline
eu-north-1 EU (Stockholm)	$0.30	$2.70	—	$0.20	+50% vs Baseline
eu-south-2 Europe (Spain)	$0.30	$2.80	—	$0.20	+50% vs Baseline
il-central-1 Israel (Tel Aviv)	$0.40	$3.10	—	$0.20	+100% vs Baseline
mx-central-1 Mexico (Central)	$0.20	$40.00	—	$0.20	Baseline
me-south-1 Middle East (Bahrain)	$0.30	$2.70	—	$0.20	+50% vs Baseline
me-central-1 Middle East (UAE)	$0.30	$2.50	—	$0.20	+50% vs Baseline
us-east-2 US East (Ohio)	$0.30	$2.50	—	$0.20	+50% vs Baseline
us-west-1 US West (N. California)	$0.40	$3.20	—	$0.20	+100% vs Baseline

Developer Quickstart

Invoke Nova 2.0 Omni 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-omni-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Nova 2.0 Omni."}]
        }
    ],
    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")