AWS general documentation change
Summary
Updated quota limits for guardrail regex entities and increased token capacity for Anthropic Claude model variants across multiple regions
Security assessment
Changes relate to service quota adjustments (increased regex limits and token capacities) rather than addressing security vulnerabilities. The guardrail regex entity change modifies operational limits in sensitive information filtering but doesn't indicate a security fix. Other changes are performance/scaling improvements for model inference.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index a020525cf..637272515 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -292 +292 @@ Name | Default | Adjustable | Description -(Guardrails) Regex entities in Sensitive Information Filter | Each supported Region: 10 | No | The maximum number of guardrail filter regexes that can be included in a sensitive information policy +(Guardrails) Regex entities in Sensitive Information Filter | ca-central-1: 30 Each of the other supported Regions: 10 | No | The maximum number of guardrail filter regexes that can be included in a sensitive information policy @@ -611 +611 @@ Cross-region model inference tokens per minute for Anthropic Claude Opus 4.5 | E -Cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 | Each supported Region: 2,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0AD9BBE8) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 | Each supported Region: 3,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0AD9BBE8) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -617 +617 @@ Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.5 V -Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6 | Each supported Region: 5,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-15B8E632) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6 | Each supported Region: 6,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-15B8E632) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -663 +663 @@ Global cross-region model inference tokens per day for Anthropic Claude Opus 4.5 -Global cross-region model inference tokens per day for Anthropic Claude Opus 4.6 V1 | Each supported Region: 2,880,000,000 | No | The maximum number of global cross-region tokens that you can submit for model inference in one day for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Global cross-region model inference tokens per day for Anthropic Claude Opus 4.6 V1 | me-south-1: 2,880,000,000 Each of the other supported Regions: 4,320,000,000 | No | The maximum number of global cross-region tokens that you can submit for model inference in one day for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -668 +668 @@ Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4 -Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4.6 | Each supported Region: 7,200,000,000 | No | The maximum number of global cross-region tokens that you can submit for model inference in one day for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4.6 | me-south-1: 7,200,000,000 Each of the other supported Regions: 8,640,000,000 | No | The maximum number of global cross-region tokens that you can submit for model inference in one day for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -676 +676 @@ Global cross-region model inference tokens per minute for Anthropic Claude Opus -Global cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 | Each supported Region: 2,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-3DCCFAA4) | The maximum number of global cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Global cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 | me-south-1: 2,000,000 Each of the other supported Regions: 3,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-3DCCFAA4) | The maximum number of global cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -681 +681 @@ Global cross-region model inference tokens per minute for Anthropic Claude Sonne -Global cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6 | Each supported Region: 5,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-7BEE40FB) | The maximum number of global cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Global cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6 | me-south-1: 5,000,000 Each of the other supported Regions: 6,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-7BEE40FB) | The maximum number of global cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -777 +777 @@ Model invocation max tokens per day for Anthropic Claude Opus 4.6 1M Context Len -Model invocation max tokens per day for Anthropic Claude Opus 4.6 V1 (doubled for cross-region calls) | Each supported Region: 1,440,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Opus 4.6 V1. 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. +Model invocation max tokens per day for Anthropic Claude Opus 4.6 V1 (doubled for cross-region calls) | Each supported Region: 2,160,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Opus 4.6 V1. 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. @@ -782 +782 @@ Model invocation max tokens per day for Anthropic Claude Sonnet 4.5 V1 1M Contex -Model invocation max tokens per day for Anthropic Claude Sonnet 4.6 (doubled for cross-region calls) | Each supported Region: 3,600,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Sonnet 4.6. 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. +Model invocation max tokens per day for Anthropic Claude Sonnet 4.6 (doubled for cross-region calls) | Each supported Region: 4,320,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Sonnet 4.6. 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. @@ -1053 +1053 @@ On-demand model inference tokens per minute for Anthropic Claude Instant | us-e -On-demand model inference tokens per minute for Anthropic Claude Sonnet 4.6 | Each supported Region: 2,500,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Anthropic Claude Sonnet 4.6 | Each supported Region: 3,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream.