AWS bedrock documentation change
Summary
Restructured Provisioned Throughput documentation with updated pricing details, commitment options, and operational guidance. Added model unit quotas and GovCloud restrictions.
Security assessment
Changes focus on pricing models, service availability in GovCloud, and operational quotas without mentioning security controls, vulnerabilities, or security enhancements. The GovCloud restriction appears to be regional availability rather than security-related.
Diff
diff --git a/bedrock/latest/userguide/prov-throughput.md b/bedrock/latest/userguide/prov-throughput.md index 9d583c40e..f8ce6ffe8 100644 --- a//bedrock/latest/userguide/prov-throughput.md +++ b//bedrock/latest/userguide/prov-throughput.md @@ -5 +5 @@ -# Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock +# Provisioned Throughput @@ -7 +7 @@ -**Throughput** refers to the number and rate of inputs and outputs that a model processes and returns. You can purchase **Provisioned Throughput** to provision a higher level of throughput for a model at a fixed cost. If you customized a model, you must purchase Provisioned Throughput to be able to use it. +When you configure Provisioned Throughput for a model, you receive a level of throughput at a fixed cost. @@ -9 +9 @@ -You're billed hourly for a Provisioned Throughput that you purchase. For detailed information about pricing, see [Amazon Bedrock Pricing](https://aws.amazon.com/bedrock/pricing). The price per hour depends on the following factors: +You can use Provisioned Throughput with Amazon and third-party base models, and with customized models. @@ -11 +11 @@ You're billed hourly for a Provisioned Throughput that you purchase. For detaile - 1. The model that you choose (for custom models, pricing is the same as the base model that it was customized from). +Provisioned Throughput pricing varies depending on the model that you use and the level of commitment you choose. You receive a discounted rate when you commit to a longer period of time. For details about pricing for each model, see the [Model providers](https://console.aws.amazon.com/bedrock/home#/providers) page in the Amazon Bedrock console. @@ -13,5 +13 @@ You're billed hourly for a Provisioned Throughput that you purchase. For detaile - 2. The number of Model Units (MUs) that you specify for the Provisioned Throughput. An MU delivers a specific throughput level for the specified model. The throughput level of an MU specifies the following: - - * The number of input tokens that an MU can process across all requests within a span of one minute. - - * The number of output tokens that an MU can generate across all requests within a span of one minute. +Your options for throughput for a model differ depending on whether you run inference on a base model or a custom model. @@ -21,7 +17 @@ You're billed hourly for a Provisioned Throughput that you purchase. For detaile -For more information about what an MU specifies, contact your AWS account manager. - - 3. The duration of time you commit to keeping the Provisioned Throughput. The longer the commitment duration, the more discounted the hourly price becomes. You can choose between the following levels of commitment: - - * No commitment – You can delete the Provisioned Throughput at any time. - - * 1 month – You can't delete the Provisioned Throughput until the one month commitment term is over. +In the AWS GovCloud (US) region, you can only purchase Provisioned Throughput for custom models with no commitment. @@ -29 +19,5 @@ For more information about what an MU specifies, contact your AWS account manage - * 6 months – You can't delete the Provisioned Throughput until the six month commitment term is over. +Pricing option | Base model | Custom model +---|---|--- +Provisioned Throughput, no commitment (hourly pricing) | Not available | Available (maximum 2 Provisioned Throughputs per account) +Provisioned Throughput, 1 month commitment | Available | Available +Provisioned Throughput, 6 month commitment | Available | Available @@ -31 +25 @@ For more information about what an MU specifies, contact your AWS account manage -###### Note +You specify Provisioned Throughput in Model Units (MU). A model unit delivers a specific throughput level for the specified model. The throughput level of a MU for a given Text model specifies the following: @@ -33 +27 @@ For more information about what an MU specifies, contact your AWS account manage -Billing continues until you delete the Provisioned Throughput. + * **The total number of input tokens per minute** – The number of input tokens that an MU can process across all requests within a span of one minute. @@ -34,0 +29 @@ Billing continues until you delete the Provisioned Throughput. + * **The total number of output tokens per minute** – The number of output tokens that an MU can generate across all requests within a span of one minute. @@ -38 +32,0 @@ Billing continues until you delete the Provisioned Throughput. -The following steps outline the process of setting up and using Provisioned Throughput. @@ -40 +34 @@ The following steps outline the process of setting up and using Provisioned Thro - 1. Determine the number of MUs you wish to purchase for a Provisioned Throughput and the amount of time for which you want to commit to using the Provisioned Throughput. +Model unit quotas depend on the level of commitment you specify for the Provisioned Throughput. @@ -42 +36 @@ The following steps outline the process of setting up and using Provisioned Thro - 2. Purchase Provisioned Throughput for a base or custom model. + * For custom models with no commitment, a quota of one model unit is available for each Provisioned Throughput. You can create up to two Provisioned Throughputs per account. @@ -44 +38 @@ The following steps outline the process of setting up and using Provisioned Thro - 3. After the provisioned model is created, you can use it to [run model inference](./inference.html). + * For base or custom models with commitment, there is a default quota of 0 model units. To request an increase, use the [limit increase form](https://console.aws.amazon.com/support/home#/case/create?issueType=service-limit-increase). @@ -51,9 +45 @@ The following steps outline the process of setting up and using Provisioned Thro - * [Supported Region and models for Provisioned Throughput](./pt-supported.html) - - * [Prerequisites for Provisioned Throughput](./prov-thru-prereq.html) - - * [Purchase a Provisioned Throughput for an Amazon Bedrock model](./prov-thru-purchase.html) - - * [View information about a Provisioned Throughput](./prov-thru-info.html) - - * [Modify a Provisioned Throughput](./prov-thru-edit.html) + * [Procedures](./prov-thru-workflow.html) @@ -61 +47 @@ The following steps outline the process of setting up and using Provisioned Thro - * [Use a Provisioned Throughput with an Amazon Bedrock resource](./prov-thru-use.html) + * [Permissions](./prov-thru-permissions.html) @@ -63 +49 @@ The following steps outline the process of setting up and using Provisioned Thro - * [Delete a Provisioned Throughput](./prov-thru-delete.html) + * [Provisioned Throughput console procedures](./prov-cap-console.html) @@ -65 +51 @@ The following steps outline the process of setting up and using Provisioned Thro - * [Code examples for Provisioned Throughput](./prov-thru-code-examples.html) + * [Using the Provisioned Throughput API](./prov-thru-api.html) @@ -78 +64 @@ Cross-Region inference: Distribute model traffic -Supported Regions and models +Procedures