AWS general documentation change
Summary
Updated quota limits for guardrail text processing in us-east-1 and added new OpenAI GPT OSS model quotas
Security assessment
Changes involve service quota adjustments and new model support documentation. While guardrail policies relate to content filtering, the changes only specify rate limits rather than addressing vulnerabilities or security features.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index 9c5df5208..de07661f6 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 | Each supported Region: 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 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 | Each supported Region: 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 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. @@ -520,0 +521,2 @@ Model invocation max tokens per day for DeepSeek R1 V1 (doubled for cross-region +Model invocation max tokens per day for OpenAI GPT OSS 120B (doubled for cross-region calls) | Each supported Region: 1,440,000,000 | No | Daily maximum tokens for model inference for OpenAI GPT OSS 120B. 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 OpenAI GPT OSS 20B (doubled for cross-region calls) | Each supported Region: 1,440,000,000 | No | Daily maximum tokens for model inference for OpenAI GPT OSS 20B. 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. @@ -652,0 +655,2 @@ On-demand model inference requests per minute for Mistral Mixtral 8x7b Instruct +On-demand model inference requests per minute for OpenAI GPT OSS 120B | Each supported Region: 250 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for OpenAI GPT OSS 120B. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for OpenAI GPT OSS 20B | Each supported Region: 250 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for OpenAI GPT OSS 20B. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -710,0 +715,2 @@ On-demand model inference tokens per minute for Mistral Large 2407 | Each suppor +On-demand model inference tokens per minute for OpenAI GPT OSS 120B | Each supported Region: 1,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for OpenAI GPT OSS 120B. 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 OpenAI GPT OSS 20B | Each supported Region: 1,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for OpenAI GPT OSS 20B. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream.