Connect AWS Bedrock to Rig

    Sync your daily Amazon Bedrock cost and usage into Rig: what AWS billed for each model and usage type, including input, output and cache tokens and third-party models sold through the AWS Marketplace. Rig reads AWS Cost Explorer with an IAM access key.

    Before you start

    • Use keys from the AWS account that pays the bill. In an AWS Organization that is the management account, and a member account's keys only see that account's spend.
    • Each Cost Explorer request costs $0.01 on your AWS bill. A sync makes a few requests, and the first read of a year of history makes more.
    • AWS requires the IAM access to the Billing and Cost Management console to be activated before IAM users can use these policies.

    Step 1: Create an IAM user for Cost Explorer

    1. In AWS, sign in to the paying account as an administrator.
    2. Activate IAM user access to Billing and Cost Management on the Account Settings page, if it is not already on.
    3. In IAM, create a user and attach a policy that allows ce:GetCostAndUsage and ce:GetDimensionValues.
    4. Create an access key for that user and copy the access key ID and the secret access key.

    Cost Explorer has no per-person view
    Cost Explorer has no caller dimension, so this connector shows spend per model per day. For per-person use, read the records of any gateway you run in front of Bedrock.

    Step 2: Connect it in Rig

    Adding a source needs a workspace owner, or a role with the Manage connections permission, on a workspace where you manage your own connections. If the Connectors tab says “Data ingestion for this workspace is managed by Rig”, ask an owner or Rig support to add the source.

    1. In Rig, open Connections, choose the Connectors tab and go to Sources & actions.
    2. Search for AWS Bedrock, open the card and click Connect.
    3. AWS access key ID: the access key ID from Step 1.
    4. AWS secret access key: the secret access key from Step 1.
    5. Click Continue. Rig checks the credentials and lists the streams it can reach, so choose the ones you want and click Connect.
    6. The source then syncs on its schedule, which is nightly unless you change it. To load data straight away, click Sync on its row; Test pulls a small sample first if you want to check the connection.

    What Rig pulls in

    AWS Bedrock lands in its own aws_bedrock schema in your warehouse:

    • Bedrock cost and usage: one row per day, per Bedrock-billed service and usage type, with the unblended cost, net unblended cost and the quantity used. Usage types name the model and the token kind.

    Only usage is counted. Credits, refunds, tax, fees and plan-covered usage are left out.

    Good to know

    • Cost Explorer refreshes about daily, and a day's figures can change until the month's bill closes, so Rig re-reads recent days and replaces them whole.
    • The data is tied to the first AWS account Rig reads. Keys for another account fail until a full resync.
    • Third-party models sold through the AWS Marketplace, such as Claude, are billed under their own Bedrock Edition services, and Rig includes those.
    • To disconnect AWS Bedrock, click the bin icon on the source's row under Sources & actions. Only whoever connected the source or a workspace owner can do this, and data already synced stays in the warehouse.

    What people use this for

    • Track Bedrock spend by model
    • Split cost by token type
    • Reconcile model spend with the bill

    More ideas for using AWS Bedrock

    AWS Bedrock documentation

    Was this guide helpful?