AWS general documentation change
Summary
Updated service quotas for guardrail policies and added Claude Sonnet 4 model limits
Security assessment
Added documentation for security-related guardrail policies (sensitive information/word filters) by expanding regional quotas. While these relate to security features, there's no evidence of addressing specific vulnerabilities. New model quotas are operational limits, not security features.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index de07661f6..7efd88325 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -266 +266 @@ Name | Default | Adjustable | Description -(Guardrails) On-demand ApplyGuardrail Sensitive information filter policy text units burst rate | us-east-1: 400 Each of the other supported Regions: 25 | No | The maximum number of text units that can be processed for Sensitive information filter policies in one burst. +(Guardrails) On-demand ApplyGuardrail Sensitive information filter policy text units burst rate | us-east-1: 400 us-west-2: 400 Each of the other supported Regions: 25 | No | The maximum number of text units that can be processed for Sensitive information filter policies in one burst. @@ -268 +268 @@ Name | Default | Adjustable | Description -(Guardrails) On-demand ApplyGuardrail Word filter policy text units burst rate | us-east-1: 400 Each of the other supported Regions: 25 | No | The maximum number of text units that can be processed for Word filter policies in one burst. +(Guardrails) On-demand ApplyGuardrail Word filter policy text units burst rate | us-east-1: 400 us-west-2: 400 Each of the other supported Regions: 25 | No | The maximum number of text units that can be processed for Word filter policies in one burst. @@ -371,0 +372 @@ Batch inference input file size (in GB) for Claude 3.5 Sonnet v2 | Each supporte +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. @@ -395,0 +397 @@ Batch inference job size (in GB) for Claude 3.5 Sonnet v2 | Each supported Regio +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. @@ -433,0 +436 @@ Cross-region model inference requests per minute for Anthropic Claude Sonnet 4 V +Cross-region model inference requests per minute for Anthropic Claude Sonnet 4 V1 1M Context Length | Each supported Region: 5 | No | The maximum number of cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4 V1 1M Context Length. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -458,0 +462 @@ Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4 V1 +Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4 V1 1M Context Length | Each supported Region: 1,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-1FA095B8) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4 V1 1M Context Length. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -497,0 +502 @@ 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 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. @@ -519,0 +525 @@ Model invocation max tokens per day for Anthropic Claude Sonnet 4 V1 (doubled fo +Model invocation max tokens per day for Anthropic Claude Sonnet 4 V1 1M Context Length (doubled for cross-region calls) | Each supported Region: 720,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Sonnet 4 V1 1M Context Length. Combines sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. Doubled for cross-region calls; not applicable in case of approved TPM increase. @@ -725,0 +732 @@ Records per batch inference job for Claude 3.5 Sonnet v2 | Each supported Region +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. @@ -749,0 +757 @@ 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 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. @@ -773,0 +782 @@ 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 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. @@ -790,0 +800 @@ 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 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.