Easily build complex reports
Monitoring and efficiency metrics
Custom cost allocation tags
Network cost visibility
Organizational cost hierarchies
Budgeting and budget alerts
Discover active resources
Consumption-based insights
Alerts for unexpected charges
Automated AWS cost savings
Discover cost savings
Unified view of AWS discounts
COGS and business metrics
Model savings plans
Collaborate on cost initiatives
Create and manage your teams
Automate cloud infrastructure
Cloud cost issue tracking
Detect cost spikes
by Emily Dunenfeld
Contents
By using Vantage to view your Amazon Bedrock Costs, you can group and filter costs as granular as your use case requires, enabling you to optimize your spend, identify cost-saving opportunities, and make data-driven decisions regarding usage.
Vantage is a cloud cost visibility and optimization platform that makes it easy for you to view your cloud costs, as granular as your use case requires. With Vantage, you can see costs from 14+ providers, including AWS, and from there you can filter to view your Amazon Bedrock charges. To get started, you’ll need to have or set up:
Note—getting set up is simple and only takes a few minutes.
Once you’re logged in, you can create a Cost Report to see your total Bedrock costs by following these steps:
The view will encompass all Bedrock costs and will look something like this:
Now that your Cost Report is saved you can group to better allocate and understand your costs. See the next section for examples and instructions.
You also create this view using the Vantage Terraform provider with the below script. For an introduction to Vantage Terraform, follow this tutorial.
terraform { required_providers { vantage = { source = "vantage-sh/vantage" } } } variable "workspace_token" { type = string description = "Vantage workspace token" default = "<YOUR_VANTAGE_WORKSPACE>" } locals { filter = <<FILTER (costs.provider = 'aws' AND costs.service = 'AmazonBedrock' OR costs.provider = 'aws' AND costs.service = 'Claude (Amazon Bedrock Edition)' OR costs.provider = 'aws' AND costs.service = 'Claude Instant (Amazon Bedrock Edition)' OR costs.provider = 'aws' AND costs.service = 'Claude 3 Haiku (Amazon Bedrock Edition)') FILTER } resource "vantage_cost_report" "bedrock_report" { filter = local.filter title = "Amazon Bedrock Report" workspace_token = var.workspace_token }
Terraform script to see Amazon Bedrock costs
Note—The filter local variable uses Vantage Query Language(VQL) to specify each model in the report. Update the filter local variable with the models you want to see.
filter
Having a view of total costs is helpful for things like overall impact and budgeting, but to really understand and action upon them, you’ll need to see these costs broken up into smaller increments. Once you have your Cost Report with all costs saved, you can follow the instructions below for some examples of ways to group costs.
Note—to group by costs in Vantage, click Group By in the top left, then select what you would like to group by. You can also filter by these categories by adding a new rule within the Filters menu.
To view costs for a specific team and environment, add a filter by account:
You’ll now see costs specifically for that team and environment.
For insights on spend per model, simply click Group by and select Resource. You’ll see a list of models, complete with the version number, and the accrued costs. Optionally, adjust the view of the costs for better visualization. For example, view costs as a pie chart by clicking the pie chart icon in the top right.
Viewing costs by operation is useful for understanding how your usage is distributed. Keep the report grouped by resource, and add an additional grouping for Subcategory. Now, you can see costs further broken out by operation for each model.
For even further granularity, use tags to group and filter costs by additional criteria. For example, application, feature name, or customer segment. You can even create virtual tags within Vantage, without engineering involvement.
By breaking down costs by model, operation, team, and more, you gain insight into what is driving spend. This enables your company to make more informed decisions on AI initiatives, allocate costs accurately, and optimize spend. With these insights, you can maximize the value of your AI investments while maintaining cost efficiency.
Monitor your AWS costs.
Grafana is a strong competitor to the monitoring and observability features of Datadog for a fraction of the price.
AWS is implementing a policy update that will no longer allow Reserved Instances and Savings Plans to be shared across end customers.
Use FinOps as Code to explore all your active cost-generating provider resources.