AWS general documentation change
Summary
Reorganized service quotas documentation for Bedrock Flows and Prompt Management features, adding detailed rate limits and node quotas while updating token calculation descriptions for several AI models
Security assessment
Changes primarily involve service quota documentation updates and organizational restructuring. No security vulnerabilities or mitigations are mentioned. The updates to token calculation descriptions (changing 'combined sum' to 'input and output tokens') improve accuracy but don't address security concerns. Rate limits and quotas help prevent resource exhaustion but are standard operational controls rather than security fixes.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index e32d1ab75..9be94c2eb 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -177,0 +178,35 @@ Name | Default | Adjustable | Description +(Flows) Agent nodes per flow | Each supported Region: 20 | No | The maximum number of agent nodes. +(Flows) Collector nodes per flow | Each supported Region: 1 | No | The maximum number of collector nodes. +(Flows) Condition nodes per flow | Each supported Region: 5 | No | The maximum number of condition nodes. +(Flows) Conditions per condition node | Each supported Region: 5 | No | The maximum number of conditions per condition node. +(Flows) CreateFlow requests per second | Each supported Region: 2 | No | The maximum number of CreateFlow requests per second. +(Flows) CreateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowAlias requests per second. +(Flows) CreateFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowVersion requests per second. +(Flows) DeleteFlow requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlow requests per second. +(Flows) DeleteFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowAlias requests per second. +(Flows) DeleteFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowVersion requests per second. +(Flows) Flow aliases per flow | Each supported Region: 10 | No | The maximum number of flow aliases. +(Flows) Flow executions per account | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F1613626) | The maximum number of flow executions per account. +(Flows) Flow versions per flow | Each supported Region: 10 | No | The maximum number of flow versions. +(Flows) Flows per account | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D321719B) | The maximum number of flows per account. +(Flows) GetFlow requests per second | Each supported Region: 10 | No | The maximum number of GetFlow requests per second. +(Flows) GetFlowAlias requests per second | Each supported Region: 10 | No | The maximum number of GetFlowAlias requests per second. +(Flows) GetFlowVersion requests per second | Each supported Region: 10 | No | The maximum number of GetFlowVersion requests per second. +(Flows) Inline code nodes per flow | Each supported Region: 5 | No | The maximum number of inline code nodes per flow. +(Flows) Input nodes per flow | Each supported Region: 1 | No | The maximum number of flow input nodes. +(Flows) Iterator nodes per flow | Each supported Region: 1 | No | The maximum number of iterator nodes. +(Flows) Knowledge base nodes per flow | Each supported Region: 20 | No | The maximum number of knowledge base nodes. +(Flows) Lambda function nodes per flow | Each supported Region: 20 | No | The maximum number of Lambda function nodes. +(Flows) Lex nodes per flow | Each supported Region: 5 | No | The maximum number of Lex nodes. +(Flows) ListFlowAliases requests per second | Each supported Region: 10 | No | The maximum number of ListFlowAliases requests per second. +(Flows) ListFlowVersions requests per second | Each supported Region: 10 | No | The maximum number of ListFlowVersions requests per second. +(Flows) ListFlows requests per second | Each supported Region: 10 | No | The maximum number of ListFlows requests per second. +(Flows) Output nodes per flow | Each supported Region: 20 | No | The maximum number of flow output nodes. +(Flows) PrepareFlow requests per second | Each supported Region: 2 | No | The maximum number of PrepareFlow requests per second. +(Flows) Prompt nodes per flow | Each supported Region: 20 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0F2A24D7) | The maximum number of prompt nodes. +(Flows) S3 retrieval nodes per flow | Each supported Region: 10 | No | The maximum number of S3 retrieval nodes. +(Flows) S3 storage nodes per flow | Each supported Region: 10 | No | The maximum number of S3 storage nodes. +(Flows) Total nodes per flow | Each supported Region: 40 | No | The maximum number of nodes in a flow. +(Flows) UpdateFlow requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlow requests per second. +(Flows) UpdateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlowAlias requests per second. +(Flows) ValidateFlowDefinition requests per second | Each supported Region: 2 | No | The maximum number of ValidateFlowDefinition requests per second. @@ -263,0 +299,8 @@ Name | Default | Adjustable | Description +(Prompt management) CreatePrompt requests per second | Each supported Region: 2 | No | The maximum number of CreatePrompt requests per second. +(Prompt management) CreatePromptVersion requests per second | Each supported Region: 2 | No | The maximum number of CreatePromptVersion requests per second. +(Prompt management) DeletePrompt requests per second | Each supported Region: 2 | No | The maximum number of DeletePrompt requests per second. +(Prompt management) GetPrompt requests per second | Each supported Region: 10 | No | The maximum number of GetPrompt requests per second. +(Prompt management) ListPrompts requests per second | Each supported Region: 10 | No | The maximum number of ListPrompts requests per second. +(Prompt management) Prompts per account | Each supported Region: 500 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B783C50B) | The maximum number of prompts. +(Prompt management) UpdatePrompt requests per second | Each supported Region: 2 | No | The maximum number of UpdatePrompt requests per second. +(Prompt management) Versions per prompt | Each supported Region: 10 | No | The maximum number of versions per prompt. @@ -267 +309,0 @@ Agent Collaborators per Agent | Each supported Region: 1,000 | [Yes](https://co -Agent nodes per flow | Each supported Region: 20 | No | The maximum number of agent nodes. @@ -319 +360,0 @@ Characters in Agent instructions | Each supported Region: 20,000 | No | The maxi -Collector nodes per flow | Each supported Region: 1 | No | The maximum number of collector nodes. @@ -321,2 +361,0 @@ Concurrent model import jobs | Each supported Region: 1 | No | The maximum numbe -Condition nodes per flow | Each supported Region: 5 | No | The maximum number of condition nodes. -Conditions per condition node | Each supported Region: 5 | No | The maximum number of conditions per condition node. @@ -326,5 +364,0 @@ CreateAgentAlias requests per second | Each supported Region: 2 | No | The maxim -CreateFlow requests per second | Each supported Region: 2 | No | The maximum number of CreateFlow requests per second. -CreateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowAlias requests per second. -CreateFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowVersion requests per second. -CreatePrompt requests per second | Each supported Region: 2 | No | The maximum number of CreatePrompt requests per second. -CreatePromptVersion requests per second | Each supported Region: 2 | No | The maximum number of CreatePromptVersion requests per second. @@ -379,2 +413,2 @@ Cross-region model inference tokens per minute for Mistral Pixtral Large 25.02 V -Cross-region model inference tokens per minute for Writer AI Palmyra X4 V1 | Each supported Region: 150,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FF1F238B) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Writer AI Palmyra X4 V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. -Cross-region model inference tokens per minute for Writer AI Palmyra X5 V1 | Each supported Region: 150,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-90DFE70F) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Writer AI Palmyra X5 V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region model inference tokens per minute for Writer AI Palmyra X4 V1 | Each supported Region: 150,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FF1F238B) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Writer AI Palmyra X4 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 Writer AI Palmyra X5 V1 | Each supported Region: 150,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-90DFE70F) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Writer AI Palmyra X5 V1. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -386,4 +419,0 @@ DeleteAgentVersion requests per second | Each supported Region: 2 | No | The max -DeleteFlow requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlow requests per second. -DeleteFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowAlias requests per second. -DeleteFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowVersion requests per second. -DeletePrompt requests per second | Each supported Region: 2 | No | The maximum number of DeletePrompt requests per second. @@ -393,4 +422,0 @@ Endpoints per inference profile | Each supported Region: 5 | No | The maximum nu -Flow aliases per flow | Each supported Region: 10 | No | The maximum number of flow aliases. -Flow executions per account | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F1613626) | The maximum number of flow executions per account. -Flow versions per flow | Each supported Region: 10 | No | The maximum number of flow versions. -Flows per account | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D321719B) | The maximum number of flows per account. @@ -402,4 +427,0 @@ GetAgentVersion requests per second | Each supported Region: 10 | No | The maxim -GetFlow requests per second | Each supported Region: 10 | No | The maximum number of GetFlow requests per second. -GetFlowAlias requests per second | Each supported Region: 10 | No | The maximum number of GetFlowAlias requests per second. -GetFlowVersion requests per second | Each supported Region: 10 | No | The maximum number of GetFlowVersion requests per second. -GetPrompt requests per second | Each supported Region: 10 | No | The maximum number of GetPrompt requests per second. @@ -408,6 +429,0 @@ Inference profiles per account | Each supported Region: 1,000 | [Yes](https://c -Inline code nodes per flow | Each supported Region: 5 | No | The maximum number of inline code nodes per flow. -Input nodes per flow | Each supported Region: 1 | No | The maximum number of flow input nodes. -Iterator nodes per flow | Each supported Region: 1 | No | The maximum number of iterator nodes. -Knowledge base nodes per flow | Each supported Region: 20 | No | The maximum number of knowledge base nodes. -Lambda function nodes per flow | Each supported Region: 20 | No | The maximum number of Lambda function nodes. -Lex nodes per flow | Each supported Region: 5 | No | The maximum number of Lex nodes. @@ -419,4 +434,0 @@ ListAgents requests per second | Each supported Region: 10 | No | The maximum nu -ListFlowAliases requests per second | Each supported Region: 10 | No | The maximum number of ListFlowAliases requests per second. -ListFlowVersions requests per second | Each supported Region: 10 | No | The maximum number of ListFlowVersions requests per second. -ListFlows requests per second | Each supported Region: 10 | No | The maximum number of ListFlows requests per second. -ListPrompts requests per second | Each supported Region: 10 | No | The maximum number of ListPrompts requests per second. @@ -527,7 +538,0 @@ On-demand InvokeModel concurrent requests for Amazon Nova Sonic | Each supported -On-demand InvokeModel requests per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 250 Each of the other supported Regions: 50 | No | The maximum number of times that you can call model inference in one minute for Anthropic Claude 3.5 Sonnet V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. -On-demand InvokeModel requests per minute for Stability.ai Stable Diffusion 3 Large | Each supported Region: 15 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Diffusion 3 Large. -On-demand InvokeModel requests per minute for Stability.ai Stable Diffusion 3 Medium | Each supported Region: 60 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Diffusion 3 Medium -On-demand InvokeModel requests per minute for Stability.ai Stable Diffusion 3.5 Large | Each supported Region: 15 | No | The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream for Stability.ai Stable Diffusion 3.5 Large. -On-demand InvokeModel requests per minute for Stability.ai Stable Image Core | Each supported Region: 90 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Image Core. -On-demand InvokeModel requests per minute for Stability.ai Stable Image Ultra | Each supported Region: 10 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Image Ultra. -On-demand InvokeModel tokens per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 2,000,000 Each of the other supported Regions: 400,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Anthropic Claude 3.5 Sonnet V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -559,0 +565 @@ On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet | +On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 250 Each of the other supported Regions: 50 | No | The maximum number of times that you can call model inference in one minute for Anthropic Claude 3.5 Sonnet V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -587,0 +594,3 @@ On-demand model inference requests per minute for Mistral Mixtral 8x7b Instruct +On-demand model inference requests per minute for Stability.ai Stable Diffusion 3 Large | Each supported Region: 15 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Diffusion 3 Large. +On-demand model inference requests per minute for Stability.ai Stable Diffusion 3 Medium | Each supported Region: 60 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Diffusion 3 Medium +On-demand model inference requests per minute for Stability.ai Stable Diffusion 3.5 Large | Each supported Region: 15 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Diffusion 3.5 Large. @@ -589,0 +599,2 @@ On-demand model inference requests per minute for Stability.ai Stable Diffusion +On-demand model inference requests per minute for Stability.ai Stable Image Core | Each supported Region: 90 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Image Core. +On-demand model inference requests per minute for Stability.ai Stable Image Ultra | Each supported Region: 10 | No | The maximum number of times that you can call InvokeModel in one minute for Stability.ai Stable Image Ultra. @@ -595,3 +606,3 @@ On-demand model inference tokens per minute for AI21 Labs Jurassic-2 Ultra | Eac -On-demand model inference tokens per minute for Amazon Nova Lite | us-east-1: 2,000,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Lite. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. -On-demand model inference tokens per minute for Amazon Nova Micro | us-east-1: 2,000,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Micro. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. -On-demand model inference tokens per minute for Amazon Nova Pro | us-east-1: 400,000 us-east-2: 400,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Pro. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Amazon Nova Lite | us-east-1: 2,000,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Lite. 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 Amazon Nova Micro | us-east-1: 2,000,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Micro. 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 Amazon Nova Pro | us-east-1: 400,000 us-east-2: 400,000 Each of the other supported Regions: 100,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Nova Pro. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -610,0 +622 @@ On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet | u +On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 2,000,000 Each of the other supported Regions: 400,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Anthropic Claude 3.5 Sonnet V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -625 +637 @@ On-demand model inference tokens per minute for Meta Llama 3 8B Instruct | Each -On-demand model inference tokens per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 400,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3.1 405B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 400,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3.1 405B Instruct. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -638 +649,0 @@ On-demand model inference tokens per minute for Mistral Large 2407 | Each suppor -Output nodes per flow | Each supported Region: 20 | No | The maximum number of flow output nodes. @@ -641,3 +651,0 @@ PrepareAgent requests per second | Each supported Region: 2 | No | The maximum n -PrepareFlow requests per second | Each supported Region: 2 | No | The maximum number of PrepareFlow requests per second. -Prompt nodes per flow | Each supported Region: 20 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0F2A24D7) | The maximum number of prompt nodes. -Prompts per account | Each supported Region: 500 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B783C50B) | The maximum number of prompts. @@ -690,2 +697,0 @@ Records per input file per batch inference job for Titan Text Embeddings V2 | Ea -S3 retrieval nodes per flow | Each supported Region: 10 | No | The maximum number of S3 retrieval nodes. -S3 storage nodes per flow | Each supported Region: 10 | No | The maximum number of S3 storage nodes. @@ -736 +741,0 @@ Throttle rate limit for UpdateDataAutomationProject | Each supported Region: 5 p -Total nodes per flow | Each supported Region: 40 | No | The maximum number of nodes in a flow. @@ -741,5 +745,0 @@ UpdateAgentKnowledgeBase requests per second | Each supported Region: 4 | No | T -UpdateFlow requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlow requests per second. -UpdateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlowAlias requests per second. -UpdatePrompt requests per second | Each supported Region: 2 | No | The maximum number of UpdatePrompt requests per second. -ValidateFlowDefinition requests per second | Each supported Region: 2 | No | The maximum number of ValidateFlowDefinition requests per second. -Versions per prompt | Each supported Region: 10 | No | The maximum number of versions per prompt.