AWS Cost Explorer Service
Browse all Amazonaws APIs★ Only Publicly Available OpenAPI DocumentFinanceExpense ManagementapiKey37 EndpointsREST
For Agents
Query AWS cost and usage data, forecast future spend, detect anomalies, and fetch RI and Savings Plans recommendations programmatically.
Use for: I need to get last month's cost broken down by service, Forecast next quarter's AWS spend, Find cost anomalies in the last 30 days, Get RI purchase recommendations for compute usage
Not supported: Does not deliver line-item billing files, enforce spending thresholds, or purchase commitments. Use for cost and usage analytics, forecasting, and anomaly detection only.
AWS Cost Explorer is the analytics API for AWS spend. It exposes the same data the Cost Explorer console renders, including cost and usage by service, account, tag, and dimension, programmatically with daily and monthly granularity. The API supports forecasting future costs and usage, detecting cost anomalies through anomaly monitors and subscriptions, retrieving Reserved Instance and Savings Plans coverage and utilisation, and getting purchase recommendations. Cost categories let you build custom rollups (by team, environment, or product) on top of raw cost data.
Install Jentic One Beta
Connect the AWS Cost Explorer Service to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the AWS Cost Explorer Service, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with AWS Cost Explorer Service API.
Query cost and usage with GetCostAndUsage filtered and grouped by service, linked account, tag, region, or any cost dimension
Generate cost and usage forecasts up to 12 months ahead with confidence intervals
Define anomaly monitors and anomaly subscriptions that alert when spend deviates from baseline
Retrieve Reserved Instance utilisation, coverage, and purchase recommendations
Retrieve Savings Plans utilisation, coverage, and purchase recommendations
Build cost categories that group spend by custom rules (account, tag, charge type) for executive reporting
Get rightsizing recommendations for EC2 instances based on observed utilisation
Use Cases
Patterns agents use AWS Cost Explorer Service API for, with concrete tasks.
★ Monthly Cost Report by Team
Build a monthly internal cost report showing spend per team without exporting CSVs by hand. GetCostAndUsage filtered by linked account or tag (Team=*) and grouped by Tag returns spend per team in one call. Render the response into a Slack post or a Notion page so engineering managers see their share of the bill on the first business day of every month.
Call GetCostAndUsage with TimePeriod={Start: 2026-05-01, End: 2026-06-01}, Granularity=MONTHLY, Metrics=['UnblendedCost'], GroupBy=[{Type: TAG, Key: Team}].
Quarterly Forecast for Finance
Give finance a forward-looking view of AWS spend so they can budget the next quarter accurately. GetCostForecast returns a point estimate plus 80 and 95 percent confidence intervals over a chosen horizon. Combine with usage forecasts to flag where committed spend (RIs or Savings Plans) under-covers the forecasted demand.
Call GetCostForecast with TimePeriod for the next 90 days, Metric=UNBLENDED_COST, Granularity=MONTHLY, PredictionIntervalLevel=95.
Cost Anomaly Detection
Catch unexpected spend spikes, such as a forgotten dev cluster, an opened S3 bucket, or a misconfigured data transfer, within hours rather than at month end. CreateAnomalyMonitor defines a service-level or account-level monitor; CreateAnomalySubscription routes detected anomalies to email or SNS. GetAnomalies returns historical anomalies for review and tuning.
CreateAnomalyMonitor with MonitorType=DIMENSIONAL and DimensionalValueCount=10, then CreateAnomalySubscription with Threshold=100 USD and Subscribers=[{Type: EMAIL, Address: cost-alerts@company.com}].
Agent-Driven Cost Investigator
When an alert fires, let an agent investigate the underlying spend pattern automatically: pull cost by service for the last 14 days, drill into the top growing service by usage type, and surface a probable root cause to the on-call engineer. The agent calls Cost Explorer through Jentic so AWS credentials never leave the vault, and runs the same investigation across multiple linked accounts in an organisation.
Search Jentic for 'get AWS cost grouped by service', execute it for the last 14 days, identify the service with the largest daily delta, then GetCostAndUsage grouped by USAGE_TYPE on that service to surface the top driver.
Key Endpoints
37 endpoints — aws cost explorer is the analytics api for aws spend.
METHOD
PATH
DESCRIPTION
POST
/#X-Amz-Target=AWSInsightsIndexService.GetCostAndUsage
Query cost and usage by dimension and group
POST
/#X-Amz-Target=AWSInsightsIndexService.GetCostForecast
Forecast future cost
POST
/#X-Amz-Target=AWSInsightsIndexService.GetUsageForecast
Forecast future usage
POST
/#X-Amz-Target=AWSInsightsIndexService.CreateAnomalyMonitor
Create a cost anomaly monitor
POST
/#X-Amz-Target=AWSInsightsIndexService.CreateAnomalySubscription
Subscribe to anomaly alerts
POST
/#X-Amz-Target=AWSInsightsIndexService.GetAnomalies
List detected anomalies
POST
/#X-Amz-Target=AWSInsightsIndexService.GetReservationUtilization
Reserved Instance utilisation
POST
/#X-Amz-Target=AWSInsightsIndexService.GetSavingsPlansUtilization
Savings Plans utilisation
POST
/#X-Amz-Target=AWSInsightsIndexService.GetCostAndUsage
Query cost and usage by dimension and group
POST
/#X-Amz-Target=AWSInsightsIndexService.GetCostForecast
Forecast future cost
POST
/#X-Amz-Target=AWSInsightsIndexService.GetUsageForecast
Forecast future usage
POST
/#X-Amz-Target=AWSInsightsIndexService.CreateAnomalyMonitor
Create a cost anomaly monitor
POST
/#X-Amz-Target=AWSInsightsIndexService.CreateAnomalySubscription
Subscribe to anomaly alerts
POST
/#X-Amz-Target=AWSInsightsIndexService.GetAnomalies
List detected anomalies
POST
/#X-Amz-Target=AWSInsightsIndexService.GetReservationUtilization
Reserved Instance utilisation
POST
/#X-Amz-Target=AWSInsightsIndexService.GetSavingsPlansUtilization
Savings Plans utilisation
Why Jentic?
Three things that make agents converge on Jentic-routed access.
Credential isolation
AWS access key ID and secret access key for AWS Cost Explorer Service are stored encrypted in the Jentic vault. Agents receive scoped, short-lived signing credentials and the raw IAM secrets never enter the agent context. Jentic computes the AWS Signature Version 4 signature server-side for every request.
Intent-based discovery
Agents search Jentic by intent (for example, 'get AWS cost broken down by service') and Jentic returns matching AWS Cost Explorer Service operations with their input schemas, the correct AWS service endpoint, and the required IAM action, so the agent can invoke the right call without crawling the AWS docs.
Time to first call
Direct AWS Cost Explorer Service integration: 1-3 days for AWS SDK setup, IAM role configuration, Sigv4 signing, and error handling. Through Jentic: under 1 hour, search, load schema, execute.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using AWS Cost Explorer Service API through Jentic.
What authentication does the AWS Cost Explorer API use?
All requests are signed with AWS Signature Version 4 using an AWS access key ID and secret access key. The endpoint is region-locked to us-east-1. Through Jentic, the credentials live encrypted in the vault and Jentic computes the signature server-side, so the agent only sees a scoped credential reference.
Can I get cost broken down by tag with this API?
Yes. Pass GroupBy=[{Type: TAG, Key: <your-tag-key>}] to GetCostAndUsage. The tag must first be activated as a cost allocation tag in the Billing console; once activated, costs are grouped by tag value with one row per distinct tag value plus an unallocated row.
What are the rate limits for the AWS Cost Explorer API?
Cost Explorer enforces a default of 5 requests per second per account, with bursts up to a small queue. High-volume reporting workloads should batch grouping into the largest practical query rather than fan out many small calls, and use exponential backoff on ThrottlingException.
How do I forecast next month's AWS spend through Jentic?
Search Jentic for 'forecast AWS cost', load the GetCostForecast schema, and execute it with TimePeriod for the next month, Metric=UNBLENDED_COST, Granularity=MONTHLY, and PredictionIntervalLevel=95. The operation maps to GetCostForecast and returns the forecast plus the chosen confidence interval.
How fresh is Cost Explorer data?
Most cost and usage data is updated at least once every 24 hours, with finalised data available the day after the billing period closes. Reserved Instance and Savings Plans coverage refreshes on the same daily cycle, so real-time spend tracking is not the right use case for this API. Use AWS Budgets for threshold alerts and CloudWatch metrics for near-real-time signals.
Is AWS Cost Explorer free to use?
The Cost Explorer console UI is free; the Cost Explorer API charges $0.01 per paginated request. High-volume reporting (large daily backfills, granular tag breakdowns) should be designed to minimise the number of paged requests.
GET STARTED