Foundation Model · Amazon BedrockNova FamilyBalanced TierTextMulti-Tier Pricing
Nova Pro
Amazon Bedrock token pricing and cost optimization reference for Nova Pro.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 24 AWS regions.
ProviderAmazon
Maker HQSeattle, Washington, USA
Class / TierBalanced
ModalityText
Prompt CachingSave 88%
Batch APISave 50%
AWS Regions24 Global
Bedrock Model ID
amazon.nova-pro-v1:0Input / Prompt
$0.80/ 1M tokens
$0.0008 per 1K tokens
Output / Completion
$3.20/ 1M tokens
$0.0032 per 1K tokens
Prompt Cache Read
$0.10/ 1M tokens
Save 88% vs prompt
Batch Inference
$0.40/ 1M in
Save 50% via Batch API
Price Ratio
1 : 4.0
Prompt to completion factor
Alternatives to Nova Pro
| Option | Price vs Nova Pro | Why look at it |
|---|---|---|
| Nova 2.0 OmniCompare → | input-62%-$0.50/1M output-22%-$0.70/1M Standard tier, per 1M tokens | Next step down in price from Amazon (general tier) |
| Nova Pro Latency OptimizedCompare → | input+25%+$0.20/1M output+25%+$0.80/1M Standard tier, per 1M tokens | Next step up in price from Amazon |
| Nova 2.0 ProCompare → | input+56%+$0.45/1M output+213%+$6.80/1M Standard tier, per 1M tokens | Same Nova line, different version |
| Titan Text PremierCompare → | input-38%-$0.30/1M output-53%-$1.70/1M Standard tier, per 1M tokens | Also from Amazon (flagship tier) |
Nova Pro Spend Estimator
Model inference spend by prompt volume, cache hit rate, and batch processing.
M tokens
M tokens
30%
Estimated Monthly Spend
$0.00
Fresh Prompts:$0.00
Cached Prompts:$0.00
Completions:$0.00
Active: Input: $0.80/1M · Output: $3.20/1M
Key Cost Levers & Architecture
Practical mechanisms to reduce inference costs with Nova Pro on AWSPrompt CachingSave ~88%
Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.
- Read Rate: $0.10 / 1M tokens
- Write Rate (5m TTL): $1.00 / 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: $0.40 / 1M tokens
- Batch Output: $1.60 / 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 regionsBaseline: $0.42/1M inGovCloud: $1.28/1M in24 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) | $0.80 | $3.20 | $0.20 | $0.40 | +90% vs Baseline |
| us-west-2 US West (Oregon) | $0.80 | $3.20 | $0.20 | $0.40 | +90% vs Baseline |
| eu-central-1 EU (Frankfurt) | $1.05 | $4.20 | $0.26 | $0.53 | +150% vs Baseline |
| eu-west-1 EU (Ireland) | $0.92 | $3.68 | $0.23 | $0.46 | +119% vs Baseline |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.96 | $3.84 | $0.24 | $0.48 | +129% vs Baseline |
| us-gov-west-1 AWS GovCloud (US-West) | $0.96 | $3.84 | $0.24 | $0.48 | GovCloud (+129%) |
| ap-southeast-3 Asia Pacific (Jakarta) | $0.42 | $1.68 | $0.10 | $0.42 | Baseline |
| ap-southeast-5 Asia Pacific (Malaysia) | $0.96 | $1.92 | $0.12 | $0.48 | +129% vs Baseline |
| ap-southeast-4 Asia Pacific (Melbourne) | $0.87 | $3.48 | $0.22 | $0.43 | +107% vs Baseline |
| ap-south-1 Asia Pacific (Mumbai) | $0.94 | $3.76 | $0.23 | $0.47 | +124% vs Baseline |
| ap-northeast-2 Asia Pacific (Seoul) | $0.95 | $3.80 | $0.24 | $0.47 | +126% vs Baseline |
| ap-southeast-1 Asia Pacific (Singapore) | $1.08 | $4.32 | $0.27 | $0.54 | +157% vs Baseline |
| ap-southeast-2 Asia Pacific (Sydney) | $0.84 | $3.36 | $0.21 | $0.42 | +100% vs Baseline |
| ap-east-2 Asia Pacific (Taipei) | $0.48 | $1.92 | $0.12 | $0.48 | +14% vs Baseline |
| ap-southeast-7 Asia Pacific (Thailand) | $0.48 | $1.92 | $0.12 | $0.48 | +14% vs Baseline |
| eu-west-2 EU (London) | $1.13 | $4.52 | $0.14 | $0.56 | +169% vs Baseline |
| eu-south-1 EU (Milan) | $1.28 | $5.21 | $0.32 | $0.64 | +205% vs Baseline |
| eu-west-3 EU (Paris) | $1.18 | $4.72 | $0.29 | $0.59 | +181% vs Baseline |
| eu-north-1 EU (Stockholm) | $0.87 | $3.48 | $0.22 | $0.43 | +107% vs Baseline |
| eu-south-2 Europe (Spain) | $0.88 | $3.52 | $0.22 | $0.44 | +110% vs Baseline |
| il-central-1 Israel (Tel Aviv) | $1.00 | $4.00 | $0.25 | $0.50 | +138% vs Baseline |
| me-central-1 Middle East (UAE) | $0.80 | $3.20 | $0.20 | $0.40 | +90% vs Baseline |
| us-east-2 US East (Ohio) | $0.80 | $3.20 | $0.20 | $0.40 | +90% vs Baseline |
| us-west-1 US West (N. California) | $1.03 | $4.12 | $0.13 | $0.52 | +145% vs Baseline |
No AWS regions found matching your filter.
Developer Quickstart
Invoke Nova Pro via Amazon Bedrock Converse APIPython (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")