AWS general documentation change
Summary
Added new evaluation-related service quotas and reorganized existing quotas. Updated Agent collaborator limits, removed specific Claude Opus/Sonnet 4 batch inference limits, added custom model creation status limit.
Security assessment
Changes focus on service quota adjustments and documentation organization. No security controls, vulnerabilities, or security features are mentioned. Modifications relate to operational limits rather than security mechanisms.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index be38a1ed5..835d54fd6 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -165,0 +166,12 @@ Name | Default | Adjustable | Description +(Evaluation) Number of concurrent automatic model evaluation jobs | Each supported Region: 20 | No | The maximum number of automatic model evaluation jobs that you can specify at one time in this account in the current Region. +(Evaluation) Number of concurrent model evaluation jobs that use human workers | Each supported Region: 10 | No | The maximum number of model evaluation jobs that use human workers you can specify at one time in this account in the current Region. +(Evaluation) Number of custom metrics | Each supported Region: 10 | No | The maximum number of custom metrics that you can specify in a model evaluation job that uses human workers. +(Evaluation) Number of custom prompt datasets in a human-based model evaluation job | Each supported Region: 1 | No | The maximum number of custom prompt datasets that you can specify in a human-based model evaluation job in this account in the current Region. +(Evaluation) Number of datasets per job | Each supported Region: 5 | No | The maximum number of datasets that you can specify in an automated model evaluation job. This includes both custom and built-in prompt datasets. +(Evaluation) Number of evaluation jobs | Each supported Region: 5,000 | No | The maximum number of model evaluation jobs that you can create in this account in the current Region. +(Evaluation) Number of metrics per dataset | Each supported Region: 3 | No | The maximum number of metrics that you can specify per dataset in an automated model evaluation job. This includes both custom and built-in metrics. +(Evaluation) Number of models in a model evaluation job that uses human workers | Each supported Region: 2 | No | The maximum number of models that you can specify in a model evaluation job that uses human workers. +(Evaluation) Number of models in automated model evaluation job | Each supported Region: 1 | No | The maximum number of models that you can specify in an automated model evaluation job. +(Evaluation) Number of prompts in a custom prompt dataset | Each supported Region: 1,000 | No | The maximum number of prompts a custom prompt dataset can contain. +(Evaluation) Size of prompt | Each supported Region: 4 | No | The maximum size (in KB) of an individual prompt in a custom prompt dataset. +(Evaluation) Task time for workers | Each supported Region: 30 | No | The maximum length (in days) of time that a worker can have to complete tasks. @@ -222 +234 @@ Action groups per Agent | Each supported Region: 20 | [Yes](https://console.aws -Agent Collaborators per Agent | us-west-2: 10 ap-northeast-1: 10 ap-northeast-3: 10 ap-southeast-1: 10 ap-southeast-2: 10 eu-north-1: 10 eu-south-1: 10 eu-west-2: 10 Each of the other supported Regions: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-EAFCD549) | The maximum number of collaborator agents that you can add to an Agent. +Agent Collaborators per Agent | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-EAFCD549) | The maximum number of collaborator agents that you can add to an Agent. @@ -224 +236 @@ Agent nodes per flow | Each supported Region: 20 | No | The maximum number of ag -Agents per account | us-west-2: 200 ap-northeast-1: 200 ap-northeast-3: 200 ap-southeast-1: 200 ap-southeast-2: 200 eu-north-1: 200 eu-south-1: 200 eu-west-2: 200 Each of the other supported Regions: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-97D79C54) | The maximum number of Agents in one account. +Agents per account | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-97D79C54) | The maximum number of Agents in one account. @@ -234,2 +245,0 @@ Batch inference input file size (in GB) for Claude 3.5 Sonnet v2 | Each supporte -Batch inference input file size (in GB) for Claude Opus 4 | Each supported Region: 1 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-BE1E8E0C) | The maximum size of a single file (in GB) submitted for batch inference for Claude Opus 4. -Batch inference input file size (in GB) for Claude Sonnet 4 | Each supported Region: 1 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F611997D) | The maximum size of a single file (in GB) submitted for batch inference for Claude Sonnet 4. @@ -259,2 +268,0 @@ Batch inference job size (in GB) for Claude 3.5 Sonnet v2 | Each supported Regio -Batch inference job size (in GB) for Claude Opus 4 | Each supported Region: 5 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-96D7DA10) | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Opus 4. -Batch inference job size (in GB) for Claude Sonnet 4 | Each supported Region: 5 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E31283B0) | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Sonnet 4. @@ -341,0 +350 @@ Custom models per account | Each supported Region: 100 | [Yes](https://console. +Custom models with a creating status per account | Each supported Region: 2 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-C02E1E99) | The maximum number of custom models with a creating status. @@ -417,2 +425,0 @@ Minimum number of records per batch inference job for Claude 3.5 Sonnet v2 | Eac -Minimum number of records per batch inference job for Claude Opus 4 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-A00860E7) | The minimum number of records across all input files in a batch inference job for Claude Opus 4. -Minimum number of records per batch inference job for Claude Sonnet 4 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F72F26EE) | The minimum number of records across all input files in a batch inference job for Claude Sonnet 4. @@ -507,4 +513,0 @@ No-commitment model units for Provisioned Throughput created for custom model Am -Number of concurrent automatic model evaluation jobs | Each supported Region: 20 | No | The maximum number of automatic model evaluation jobs that you can specify at one time in this account in the current Region. -Number of concurrent model evaluation jobs that use human workers | Each supported Region: 10 | No | The maximum number of model evaluation jobs that use human workers you can specify at one time in this account in the current Region. -Number of custom metrics | Each supported Region: 10 | No | The maximum number of custom metrics that you can specify in a model evaluation job that uses human workers. -Number of custom prompt datasets in a human-based model evaluation job | Each supported Region: 1 | No | The maximum number of custom prompt datasets that you can specify in a human-based model evaluation job in this account in the current Region. @@ -512,6 +514,0 @@ Number of custom prompt routers per account | Each supported Region: 500 | No | -Number of datasets per job | Each supported Region: 5 | No | The maximum number of datasets that you can specify in an automated model evaluation job. This includes both custom and built-in prompt datasets. -Number of evaluation jobs | Each supported Region: 5,000 | No | The maximum number of model evaluation jobs that you can create in this account in the current Region. -Number of metrics per dataset | Each supported Region: 3 | No | The maximum number of metrics that you can specify per dataset in an automated model evaluation job. This includes both custom and built-in metrics. -Number of models in a model evaluation job that uses human workers | Each supported Region: 2 | No | The maximum number of models that you can specify in a model evaluation job that uses human workers. -Number of models in automated model evaluation job | Each supported Region: 1 | No | The maximum number of models that you can specify in an automated model evaluation job. -Number of prompts in a custom prompt dataset | Each supported Region: 1,000 | No | The maximum number of prompts a custom prompt dataset can contain. @@ -648,2 +644,0 @@ Records per batch inference job for Claude 3.5 Sonnet v2 | Each supported Region -Records per batch inference job for Claude Opus 4 | Each supported Region: 50,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-175A229B) | The maximum number of records across all input files in a batch inference job for Claude Opus 4. -Records per batch inference job for Claude Sonnet 4 | Each supported Region: 50,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-8A6B31EE) | The maximum number of records across all input files in a batch inference job for Claude Sonnet 4. @@ -673,2 +667,0 @@ Records per input file per batch inference job for Claude 3.5 Sonnet v2 | Each s -Records per input file per batch inference job for Claude Opus 4 | Each supported Region: 50,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4D46C6C7) | The maximum number of records in an input file in a batch inference job for Claude Opus 4. -Records per input file per batch inference job for Claude Sonnet 4 | Each supported Region: 50,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-02DB18B4) | The maximum number of records in an input file in a batch inference job for Claude Sonnet 4. @@ -695 +687,0 @@ Scheduled customization jobs | Each supported Region: 2 | No | The maximum numbe -Size of prompt | Each supported Region: 4 | No | The maximum size (in KB) of an individual prompt in a custom prompt dataset. @@ -702,2 +693,0 @@ Sum of in-progress and submitted batch inference jobs using a base model for Cla -Sum of in-progress and submitted batch inference jobs using a base model for Claude Opus 4 | Each supported Region: 20 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-90B9662E) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Opus 4. -Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4 | Each supported Region: 20 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-79EFF176) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4. @@ -721,2 +710,0 @@ Sum of in-progress and submitted batch inference jobs using a base model for Tit -Sum of in-progress and submitted batch inference jobs using a custom model for Claude Opus 4 | Each supported Region: 3 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4E73C7FD) | The maximum number of in-progress and submitted batch inference jobs using a custom model for Claude Opus 4. -Sum of in-progress and submitted batch inference jobs using a custom model for Claude Sonnet 4 | Each supported Region: 3 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-34E7AD2F) | The maximum number of in-progress and submitted batch inference jobs using a custom model for Claude Sonnet 4. @@ -746 +733,0 @@ Sum of training and validation records for a Titan Text G1 - Premier v1 Fine-tun -Task time for workers | Each supported Region: 30 | No | The maximum length (in days) of time that a worker can have to complete tasks.