AWS bedrock documentation change
Summary
Minor editorial improvements including sentence restructuring for clarity, replacing semicolons with periods, adding transitional words, and breaking long sentences into shorter ones. Content about cost management using request metadata remains unchanged.
Security assessment
Changes are purely grammatical/editorial with no security implications. No vulnerabilities, security features, or security mechanisms are discussed or modified. All content remains focused on cost attribution methods.
Diff
diff --git a/bedrock/latest/userguide/cost-mgmt-request-metadata.md b/bedrock/latest/userguide/cost-mgmt-request-metadata.md index c392b7b7e..c730ec75a 100644 --- a//bedrock/latest/userguide/cost-mgmt-request-metadata.md +++ b//bedrock/latest/userguide/cost-mgmt-request-metadata.md @@ -11 +11 @@ How request metadata worksLimitsWhere request metadata appearsGetting cost from -Request metadata lets you attach key-value tags to individual Amazon Bedrock inference calls on the [bedrock-runtime](./endpoints.html) endpoint. The tags are recorded with the request in your [model invocation logs](./model-invocation-logging.html), so you can attribute usage to a team, application, environment, experiment, or any other dimension that varies per call. There is no resource to create or configure ahead of time — each call can carry a different set of tags. +Request metadata lets you attach key-value tags to individual Amazon Bedrock inference calls on the [bedrock-runtime](./endpoints.html) endpoint. The tags are recorded with the request in your [model invocation logs](./model-invocation-logging.html). You can then attribute usage to a team, application, environment, experiment, or any other dimension that varies per call. There is no resource to create or configure ahead of time — each call can carry a different set of tags. @@ -141 +141 @@ Compute from token counts -Each log record carries the input, output, cache-read, and cache-write token counts for the request. Multiply these by the per-token rates in [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) and group by any metadata tag. This is per-prompt and near real-time, but it is an estimate. You maintain the rate card, and it does not reflect discounts, commitments, batch pricing, free tier, or provisioned throughput unless you model them. +Each log record carries the input, output, cache-read, and cache-write token counts for the request. Multiply these by the per-token rates in [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) and group by any metadata tag. This approach is per-prompt and near real-time, but it is an estimate. You maintain the rate card. It does not reflect discounts, commitments, batch pricing, free tier, or provisioned throughput unless you model them. @@ -171 +171 @@ Reconcile against CUR -Join your invocation logs to your AWS Cost and Usage Report for invoice-accurate totals. Neither classic CUR nor CUR 2.0 includes a per-request identifier on its line items; both aggregate cost by usage type over an hour or a day. Treat this path as reconciliation at the model and usage-type grain, with the logs providing the per-request detail underneath. +Join your invocation logs to your AWS Cost and Usage Report for invoice-accurate totals. Neither classic CUR nor CUR 2.0 includes a per-request identifier on its line items. Both aggregate cost by usage type over an hour or a day. Treat this path as reconciliation at the model and usage-type grain, with the logs providing the per-request detail underneath. @@ -175 +175 @@ Join your invocation logs to your AWS Cost and Usage Report for invoice-accurate -Request metadata and IAM session tags are different mechanisms. Request metadata is set per call and varies per request; it lands in your invocation logs. IAM session tags are bound per session and surface only as aggregated billing data in AWS Cost Explorer and CUR. For per-user, per-prompt attribution, use request metadata, or a per-user identity in the ARN, rather than session tags. +Request metadata and IAM session tags are different mechanisms. Request metadata is set per call and varies per request. It lands in your invocation logs. IAM session tags are bound per session and surface only as aggregated billing data in AWS Cost Explorer and CUR. For per-user, per-prompt attribution, use request metadata or a per-user identity in the ARN rather than session tags. @@ -181 +181 @@ Request metadata and IAM session tags are different mechanisms. Request metadata - * Request metadata is not delivered as an AWS cost allocation tag and does not appear in AWS Cost Explorer or CUR. To analyze costs by metadata dimension, join your invocation logs with your Cost and Usage Report on `requestId`, or aggregate token counts directly from log records and multiply by the per-token rates in [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/). For attribution that flows natively to Cost Explorer and CUR, use [Application inference profiles](./cost-mgmt-application-inference-profiles.html), [Projects](./cost-mgmt-projects.html), or [Workspaces](./cost-mgmt-workspaces.html). + * Request metadata is not delivered as an AWS cost allocation tag and does not appear in AWS Cost Explorer or CUR. To analyze costs by metadata dimension, join your invocation logs with your Cost and Usage Report on `requestId`. Alternatively, aggregate token counts directly from log records and multiply by the per-token rates in [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/). For attribution that flows natively to Cost Explorer and CUR, use [Application inference profiles](./cost-mgmt-application-inference-profiles.html), [Projects](./cost-mgmt-projects.html), or [Workspaces](./cost-mgmt-workspaces.html). @@ -187 +187 @@ Request metadata and IAM session tags are different mechanisms. Request metadata - * Request metadata is supplied per call and is not enforced by Amazon Bedrock. Requests that omit it still succeed, and there is no service-side policy to require it. To guarantee coverage across an organization, set request metadata in a shared client or LLM gateway. For attribution that is always present without per-call code, use [IAM principal attribution](./cost-mgmt-iam-principal-tracking.html), which captures the caller identity automatically. + * Request metadata is supplied per call and is not enforced by Amazon Bedrock. Requests that omit it still succeed, and there is no service-side policy to require it. To guarantee coverage across an organization, set request metadata in a shared client or LLM gateway. For attribution that is always present without per-call code, use [IAM principal attribution](./cost-mgmt-iam-principal-tracking.html). It captures the caller identity automatically.