Cost
You are responsible for the cost of the AWS services used while
running this solution. As of this latest revision, the cost for
running the default basic implementation of this solution in the
US East (N. Virginia) Region is approximately
$547.33 per month.
Amazon Kendra and Amazon Connect are not part of the default
solution implementation, but the solution does provide the capability to integrate with
them. Because the solution does not create resources for Amazon Kendra or Amazon Connect
automatically, they are not included in the example cost table. If you intend to integrate
Amazon Kendra and Amazon Connect, review the Amazon Kendra pricing and Amazon
Connect pricing to adjust your cost estimate accordingly.
We recommend creating a
budget
through
AWS Cost Explorer to help manage costs. Prices are subject to
change. For full details, see the pricing webpage for each AWS
service used in this solution. For additional information, see
Creating
a cost budget in the AWS Cost Management User
Guide.
Option 1: Default basic deployment
The following table provides a sample cost breakdown for
deploying this solution with the default parameters in the US
East (N. Virginia) Region for one month.
|
Amazon API Gateway
|
1,000,000 REST API calls per month
|
$3.50
|
|
Amazon Cognito
|
1,000 active users per month without the advanced
security feature
|
$0.00
|
|
Amazon S3
|
100 GB data transfer + 1,000,000 requests (100 records x
100 KB from Amazon Kinesis)
|
$3.27
|
|
AWS Lambda
|
2,000,000 requests with 200 ms duration
|
$1.23
|
|
Systems Manager Parameter Store
|
2,000,000 requests with 10 standard parameters
|
$0.00
|
|
Amazon Lex
|
100,000 text requests per month
|
$75.00
|
|
Amazon Data Firehose
|
100,000 records per month with 100 KB per record
|
$0.28
|
|
Amazon DynamoDB
|
1 GB storage + 1 read and 1 write per second + 20 hours
peak read/write per month
|
$11.41
|
|
Amazon Polly
|
10,000 requests + 50 characters per request
|
$4.00
|
|
Amazon Translate
|
100,000 requests + 50 characters per request (OPTIONAL
for non-English)
|
$75.00
|
|
Amazon Comprehend
|
100,000 requests + 50 characters per request
|
$5.00
|
|
Amazon OpenSearch Service
|
m6g.large.search instance running all hours in a month
for 4 nodes
|
$368.64
|
|
Total for a default basic deployment: |
$547.33
|
Option 2a: SageMaker AI embeddings only
| AWS service |
Dimensions |
Cost [$USD] |
| Amazon SageMaker AI Endpoint for text embeddings (optional) |
ml.g4dn.xlarge instance running all hours in a
month for 1 node |
$165.60 |
|
Total with SageMaker AI embeddings only ($547.33 + $165.60):
|
$712.93
|
Option 2b: Amazon Bedrock embeddings only
| AWS service |
Dimensions |
Cost [$USD] |
|
Amazon Bedrock for text embeddings (optional)
|
Daily average of 8,000 requests of 2,000 input tokens estimated using Amazon
Titan Embeddings Text |
$48.00
|
|
Total with Amazon Bedrock embeddings only ($547.33 + $48.00):
|
$595.33
|
Option 3a: SageMaker AI embeddings and LLMs
| AWS service |
Dimensions |
Cost [$USD] |
|
Amazon SageMaker AI Endpoint for LLM question answering
(optional)
|
ml.g5.12xlarge instance running all hours in a month for 1 node
|
$5,104.80
|
|
Total with SageMaker AI embeddings and LLMs ($712.93 +
$5,104.80): |
$5,817.73 |
Option 3b: Amazon Bedrock embeddings and LLMs
| AWS service |
Dimensions |
Cost [$USD] |
|
Amazon Bedrock for LLM question answering (optional)
|
Daily average of 8,000 requests each made of 2,000 input tokens and 200 output
tokens estimated using Anthropic Claude 3 Haiku (lower cost LLM option) or Anthropic Claude 3 Sonnet (higher cost LLM option) |
$180.00 (Haiku) to $2,160.00 (Sonnet) |
|
Total with Amazon Bedrock embeddings and LLMs ($595.33 +
$180.00 to $2,160.00): |
$775.33 to $2,755.33 |
Option 4a: SageMaker AI embeddings and LLM and RAG using Amazon Kendra
| AWS service |
Dimensions |
Cost [$USD] |
|
Amazon Kendra index
|
0-8,000 queries a day and up to 100,000 documents with
Amazon Kendra Enterprise Edition with 0-50 data sources
|
$1,008.00 |
|
Total with SageMaker AI embeddings and LLM and RAG using Amazon Kendra
($5,817.73 + $1,008.00):
|
$6,825.73
|
Option 4b: Amazon Bedrock embeddings and LLM and RAG using Amazon Bedrock knowledge base
| AWS service |
Dimensions |
Cost [$USD] |
|
Amazon Bedrock knowledge base (optional)
|
8,000 questions a day with 5 GB of data stored in Amazon OpenSearch Service Serverless vector
store and using Anthropic Claude 3 Haiku (lower cost LLM option) or Anthropic Claude
3 Sonnet (higher cost LLM option) |
$733.00 (Haiku) to $2,713.00 (Sonnet) |
| Total with Amazon Bedrock
embeddings and LLM and RAG using Amazon Bedrock knowledge base ($775.33 to
$2,755.33 + $733.00 to $2,713.00 ): |
$1,508.33 to $5,468.33 |
Option 5: Amazon Bedrock embeddings and LLM and RAG using Amazon Bedrock knowledge base and Guardrails for Amazon Bedrock
| AWS service |
Dimensions |
Cost [$USD] |
| Guardrails for Amazon Bedrock (optional) |
8,000 requests a day (1 text unit user query and 1 unit FM response) with
content filters, denied topics, sensitive information filters, and the word filters
policy enabled |
$888.00 |
|
Total with Amazon Bedrock embeddings and LLM and RAG
using Amazon Bedrock knowledge base ($2,084.77 to $5,468.33 +
$888.00):
|
$2,972.77 to $6,356.33
|
