Foundation Model · Amazon BedrockTitan FamilyEmbedding TierEmbeddingMulti-Tier Pricing

Titan Embeddings v2

Amazon Bedrock token pricing and cost optimization reference for Titan Embeddings v2.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 23 AWS regions.

ProviderAmazon

Maker HQSeattle, Washington, USA

Class / TierEmbedding

ModalityEmbedding

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions23 Global

Bedrock Model IDamazon.titan-embeddings-v2-v1:0

Input / Prompt

$0.02/ 1M tokens

$0.0000 per 1K tokens

Output / Completion

—/ 1M tokens

Standard on-demand

Prompt Cache Read

$0.0050/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.01/ 1M in

Save 50% via Batch API

Price Ratio

—

Prompt to completion factor

Regional Reach

23AWS Regions

Compare 23 regions ↓

Titan Embeddings v2 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: $0.02/1M · Output: —/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Titan Embeddings v2 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: $0.0050 / 1M tokens
Write Rate (5m TTL): $0.03 / 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: $0.01 / 1M tokens
Batch Output: — / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers23 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 23 available AWS cloud regions

Baseline: $0.02/1M inGovCloud: $0.20/1M in23 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)	$0.02	—	—	$0.01	Baseline
us-west-2 US West (Oregon)	$0.02	—	—	$0.01	Baseline
eu-central-1 EU (Frankfurt)	$0.20	—	—	$0.10	+900% vs Baseline
eu-west-1 EU (Ireland)	$0.03	—	—	—	+30% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$0.03	—	—	$0.01	+45% vs Baseline
us-gov-west-1 AWS GovCloud (US-West)	$0.11	—	—	—	GovCloud (+450%)
ap-south-2 Asia Pacific (Hyderabad)	$0.03	—	—	—	+35% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$0.02	—	—	—	+20% vs Baseline
ap-northeast-3 Asia Pacific (Osaka)	$0.03	—	—	—	+35% vs Baseline
ap-northeast-2 Asia Pacific (Seoul)	$0.02	—	—	$0.01	+23% vs Baseline
ap-southeast-1 Asia Pacific (Singapore)	$0.03	—	—	—	+40% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$0.03	—	—	—	+30% vs Baseline
us-gov-east-1 AWS GovCloud (US-East)	$0.03	—	—	—	GovCloud (+50%)
ca-central-1 Canada (Central)	$0.10	—	—	$0.05	+400% vs Baseline
eu-west-2 EU (London)	$0.10	—	—	$0.05	+400% vs Baseline
eu-south-1 EU (Milan)	$0.02	—	—	$0.01	+15% vs Baseline
eu-west-3 EU (Paris)	$0.03	—	—	—	+50% vs Baseline
eu-north-1 EU (Stockholm)	$0.02	—	—	$0.01	+5% vs Baseline
eu-south-2 Europe (Spain)	$0.02	—	—	$0.01	+5% vs Baseline
eu-central-2 Europe (Zurich)	$0.03	—	—	—	+35% vs Baseline
sa-east-1 South America (Sao Paulo)	$0.20	—	—	$0.10	+900% vs Baseline
us-east-2 US East (Ohio)	$0.02	—	—	—	Baseline
us-west-1 US West (N. California)	$0.02	—	—	—	+20% vs Baseline

Developer Quickstart

Invoke Titan Embeddings v2 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.titan-embeddings-v2-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Titan Embeddings v2."}]
        }
    ],
    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")