Input / Prompt
$0.15/ 1M tokens
$0.0001 per 1K tokens
Output / Completion
$1.25/ 1M tokens
$0.0013 per 1K tokens
Prompt Cache Read
$0.04/ 1M tokens
Save 75% vs prompt
Batch Inference
$0.07/ 1M in
Save 50% via Batch API
Price Ratio
1 : 8.3
Prompt to completion factor
Regional Reach
26AWS Regions

Nova 2.0 Lite Spend Estimator

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

Workload Presets:
M tokens
M tokens
30%
Estimated Monthly Spend
$0.00
Fresh Prompts:$0.00
Cached Prompts:$0.00
Completions:$0.00
Active: Input: $0.15/1M ยท Output: $1.25/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Nova 2.0 Lite on AWS
Prompt CachingSave ~75%

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

  • Read Rate: $0.04 / 1M tokens
  • Write Rate: $0.19 / 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: $0.07 / 1M tokens
  • Batch Output: $0.63 / 1M tokens
  • Ideal for: Offline classification, synthetic data generation, benchmark evals
Cross-Region & Tiers26 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 26 available AWS cloud regions
Baseline: $0.15/1M inGovCloud: $0.73/1M in26 Global Regions
Showing 5 benchmark regions
AWS RegionPrompt InputCompletion OutputCache ReadBatch InputPricing Tier
$0.15/1M$1.25/1M$0.04/1Mโ€”/1MBaseline
$0.53/1M$4.81/1M$0.13/1Mโ€”/1M+250% vs Baseline
EU (Frankfurt)eu-central-1
$0.68/1M$1.80/1M$0.05/1Mโ€”/1M+355% vs Baseline
EU (Ireland)eu-west-1
$0.59/1M$1.44/1M$0.15/1Mโ€”/1M+297% vs Baseline
Asia Pacific (Tokyo)ap-northeast-1
$0.18/1M$1.66/1M$0.16/1Mโ€”/1M+20% vs Baseline
$0.56/1M$1.31/1M$0.08/1Mโ€”/1M+273% vs Baseline
$0.72/1M$1.70/1M$0.18/1Mโ€”/1M+378% vs Baseline
$0.17/1M$2.71/1M$0.08/1Mโ€”/1M+10% vs Baseline
$0.61/1M$1.48/1M$0.04/1Mโ€”/1M+308% vs Baseline
$0.32/1M$4.60/1M$0.08/1Mโ€”/1M+113% vs Baseline
Asia Pacific (Seoul)ap-northeast-2
$0.36/1M$1.48/1M$0.09/1Mโ€”/1M+140% vs Baseline
$0.20/1M$1.70/1M$0.05/1Mโ€”/1M+37% vs Baseline
Asia Pacific (Sydney)ap-southeast-2
$0.16/1M$4.60/1M$0.08/1Mโ€”/1M+7% vs Baseline
$0.36/1M$5.27/1M$0.09/1Mโ€”/1M+140% vs Baseline
$0.41/1M$1.70/1M$0.18/1Mโ€”/1M+173% vs Baseline
Canada (Central)ca-central-1
$0.18/1M$1.33/1M$0.04/1Mโ€”/1M+17% vs Baseline
$0.19/1M$1.95/1M$0.16/1Mโ€”/1M+25% vs Baseline
EU (London)eu-west-2
$0.73/1M$1.76/1M$0.10/1Mโ€”/1M+390% vs Baseline
EU (Milan)eu-south-1
$0.24/1M$7.72/1M$0.08/1Mโ€”/1M+60% vs Baseline
EU (Paris)eu-west-3
$0.22/1M$6.46/1M$0.12/1Mโ€”/1M+47% vs Baseline
EU (Stockholm)eu-north-1
$0.18/1M$1.50/1M$0.14/1Mโ€”/1M+21% vs Baseline
Europe (Spain)eu-south-2
$0.18/1M$4.81/1M$0.04/1Mโ€”/1M+21% vs Baseline
Israel (Tel Aviv)il-central-1
$0.67/1M$3.13/1M$0.17/1Mโ€”/1M+343% vs Baseline
Middle East (UAE)me-central-1
$0.30/1M$4.38/1M$0.04/1Mโ€”/1M+100% vs Baseline
$0.58/1M$2.50/1M$0.04/1Mโ€”/1M+285% vs Baseline
$0.21/1M$3.35/1M$0.11/1Mโ€”/1M+43% vs Baseline

Developer Quickstart

Invoke Nova 2.0 Lite via Amazon Bedrock Converse API
Python (boto3) ยท 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-lite-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Nova 2.0 Lite."}]
        }
    ],
    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")

Compare Nova 2.0 Lite with Alternatives

Open Multi-Model Estimator →
Nova 2.0 Lite vsJamba 1.5 LargeAI21 Labs
Input Rate:$2.00/1M
Output Rate:$8.00/1M
Compare Side-by-Side →
Nova 2.0 Lite vsJamba 1.5 MiniAI21 Labs
Input Rate:$0.20/1M
Output Rate:$0.40/1M
Compare Side-by-Side →
Nova 2.0 Lite vsQwen3 235B A22B 2507Alibaba (Qwen)
Input Rate:$0.11/1M
Output Rate:$0.44/1M
Compare Side-by-Side →