For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Carry a validated caller identity into AWS billing records, so LLM spend is attributed per team, app, user, or any chosen attribution value on the provider’s own bill.

Invoice-grade attribution means that the value that names a request reaches the cloud provider’s own billing records. Finance then slices the same numbers that the provider charges. Agentgateway can also compute per-team spend from token counts and a price list, but that number is an estimate rather than the invoice. For the reasoning behind the term, see Invoice-grade attribution on Amazon Bedrock with agentgateway.

You configure the attribution values, and agentgateway resolves each one from an identity that it validated or from a static value that you assign.

Before you begin

1. Set up an agentgateway proxy.
2. Create the AgentgatewayBackend and HTTPRoute for the LLM provider that you want to attribute, such as Amazon Bedrock.
3. Apply a JWT authentication policy to the route, so that jwt.* values are available to attribution expressions.

Amazon Bedrock

Bedrock attributes inference cost to the IAM principal that made the call. For gateway traffic, the documented pattern is a per-caller session. Agentgateway assumes an AWS Identity and Access Management (IAM) role for each request. The session name and the session tags come from the caller’s identity.

The session name lands in AWS CloudTrail and in the IAM principal column of the Cost and Usage Report. The tags surface as cost allocation tags in Cost Explorer and in the Cost and Usage Report.

Session identity and tags

Configure assumeRole in the auth.aws settings of the AgentgatewayBackend. The session name is either a static sessionName or a sessionNameExpression. Each tag is either a static value or a CEL expression that agentgateway evaluates against the request.

kubectl apply -f- <<EOF
apiVersion: agentgateway.dev/v1alpha1
kind: AgentgatewayBackend
metadata:
  name: bedrock
  namespace: agentgateway-system
spec:
  ai:
    provider:
      bedrock:
        model: "amazon.nova-micro-v1:0"
        region: "us-east-1"
  policies:
    auth:
      aws:
        assumeRole:
          roleArn: arn:aws:iam::123456789012:role/bedrock-invoke
          sessionNameExpression: jwt.sub
          tags:
          - key: user
            expression: jwt.sub
          - key: team
            expression: request.headers["x-team"]
          - key: environment
            value: prod
EOF

Review the following table to understand this configuration. For more information, see the API reference.

Agentgateway checks static values against the STS limits when the resource is accepted. Expressions are evaluated per request and fail closed. An expression that errors, or that produces an empty or invalid value, rejects the request before agentgateway calls AWS. No request reaches Bedrock unattributed.

To see the tags on the bill, activate the keys as cost allocation tags in the AWS Billing console. New keys take up to 24 hours to become available for activation. Activated tags apply to usage from that point on.

Choose attribution values

Where the value comes from decides what the bill is worth in a dispute.

• jwt.* values come from a token that agentgateway validated under a JWT authentication policy. The value is a fact about who logged in, checked on every request.
• Static values are the ones that you assign to the backend or route. Use them for callers that do not log in, such as batch jobs and internal services.
• request.headers[...] is the caller’s word. Use it only for dimensions that the caller is trusted to assert, such as an environment name. Never use it for the identity that chargeback depends on.

Keep the values low-cardinality on the bill. Every distinct set of session tags is its own STS session and its own set of line items in the Cost and Usage Report. Tag by team and cost center everywhere, and tag per user only where the chargeback question needs it.

Verify

Learn more

• Transform requests for request transformations and the CEL context.
• Virtual keys to attribute usage inside agentgateway.
• Amazon Bedrock provider configuration.