Foundation Model · Amazon BedrockNova FamilyLightweight TierTextMulti-Tier Pricing
Nova Micro
Amazon Bedrock token pricing and cost optimization reference for Nova Micro.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 21 AWS regions.
ProviderAmazon
Maker HQSeattle, Washington, USA
Class / TierLightweight
ModalityText
Prompt CachingSave 75%
Batch APISave 50%
AWS Regions21 Global
Bedrock Model ID
amazon.nova-micro-v1:0Input / Prompt
$0.04/ 1M tokens
$0.0000 per 1K tokens
Output / Completion
$0.14/ 1M tokens
$0.0001 per 1K tokens
Prompt Cache Read
$0.0088/ 1M tokens
Save 75% vs prompt
Batch Inference
$0.02/ 1M in
Save 50% via Batch API
Price Ratio
1 : 4.0
Prompt to completion factor
Alternatives to Nova Micro
| Option | Price vs Nova Micro | Why look at it |
|---|---|---|
| Nova LiteCompare → | input+71%+$0.025/1M output+71%+$0.10/1M Standard tier, per 1M tokens | Next step up in price from Amazon (general tier) |
| Nova 2.0 OmniCompare → | input+757%+$0.265/1M output+1686%+$2.36/1M Standard tier, per 1M tokens | Same Nova line, different version (general tier) |
| Titan Text G1Compare → | input+329%+$0.115/1M output+43%+$0.06/1M Standard tier, per 1M tokens | Also from Amazon (general tier) |
| Titan Text PremierCompare → | input+1329%+$0.465/1M output+971%+$1.36/1M Standard tier, per 1M tokens | Also from Amazon (flagship tier) |
Nova Micro 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: $0.04/1M · Output: $0.14/1M
Key Cost Levers & Architecture
Practical mechanisms to reduce inference costs with Nova Micro on AWSPrompt CachingSave ~75%
Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.
- Read Rate: $0.0088 / 1M tokens
- Write Rate (5m TTL): $0.04 / 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: $0.02 / 1M tokens
- Batch Output: $0.07 / 1M tokens
- Ideal for: Offline classification, synthetic data generation, benchmark evals
Cross-Region & Tiers21 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 21 available AWS cloud regionsBaseline: $0.02/1M inGovCloud: $0.06/1M in21 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) | $0.04 | $0.14 | $0.0088 | $0.02 | +67% vs Baseline |
| us-west-2 US West (Oregon) | $0.04 | $0.14 | $0.0088 | $0.02 | +67% vs Baseline |
| eu-central-1 EU (Frankfurt) | $0.05 | $0.18 | $0.01 | $0.02 | +119% vs Baseline |
| eu-west-1 EU (Ireland) | $0.04 | $0.16 | $0.01 | $0.02 | +90% vs Baseline |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.04 | $0.17 | $0.01 | $0.02 | +100% vs Baseline |
| us-gov-west-1 AWS GovCloud (US-West) | $0.04 | $0.17 | $0.01 | $0.02 | GovCloud (+100%) |
| ap-southeast-5 Asia Pacific (Malaysia) | $0.04 | — | — | — | +100% vs Baseline |
| ap-south-1 Asia Pacific (Mumbai) | $0.04 | $0.16 | $0.01 | $0.02 | +95% vs Baseline |
| ap-northeast-2 Asia Pacific (Seoul) | $0.04 | $0.16 | $0.01 | $0.02 | +95% vs Baseline |
| ap-southeast-1 Asia Pacific (Singapore) | $0.05 | $0.19 | $0.01 | $0.02 | +124% vs Baseline |
| ap-southeast-2 Asia Pacific (Sydney) | $0.04 | $0.15 | $0.0092 | $0.02 | +76% vs Baseline |
| ap-east-2 Asia Pacific (Taipei) | — | — | — | — | Baseline |
| ap-southeast-7 Asia Pacific (Thailand) | $0.02 | $0.08 | — | $0.02 | Baseline |
| eu-west-2 EU (London) | $0.05 | $0.20 | — | — | +133% vs Baseline |
| eu-south-1 EU (Milan) | $0.06 | $0.22 | $0.01 | — | +167% vs Baseline |
| eu-west-3 EU (Paris) | $0.05 | $0.21 | $0.01 | $0.03 | +148% vs Baseline |
| eu-north-1 EU (Stockholm) | $0.04 | $0.15 | $0.0095 | $0.02 | +81% vs Baseline |
| eu-south-2 Europe (Spain) | $0.04 | $0.16 | $0.0097 | — | +86% vs Baseline |
| il-central-1 Israel (Tel Aviv) | $0.04 | $0.18 | $0.01 | $0.02 | +110% vs Baseline |
| me-central-1 Middle East (UAE) | $0.04 | $0.14 | $0.0088 | $0.02 | +67% vs Baseline |
| us-east-2 US East (Ohio) | $0.04 | $0.14 | $0.0088 | $0.02 | +67% vs Baseline |
No AWS regions found matching your filter.
Developer Quickstart
Invoke Nova Micro 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-micro-v1:0",
messages=[
{
"role": "user",
"content": [{"text": "Summarize key features and cost levers of Nova Micro."}]
}
],
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")