AWS general documentation change
Summary
Updated service quotas for various Bedrock components including increased node limits, adjusted model inference thresholds, added new model entries, and modified rate limits
Security assessment
Changes primarily involve quota adjustments, model version updates, and operational limits without any explicit security vulnerability fixes or new security feature documentation
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index eaf345a55..495fd2d21 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -143 +143 @@ Agent Collaborators per Agent | Each supported Region: 10 | [Yes](https://conso -Agent nodes per flow | Each supported Region: 10 | No | The maximum number of agent nodes. +Agent nodes per flow | Each supported Region: 20 | No | The maximum number of agent nodes. @@ -205 +204,0 @@ CreateBlueprint - Max number of blueprints per account | Each supported Region: -CreateBlueprint - Throttle limit in transactions per second | Each supported Region: 1 | No | No Description Available @@ -207 +205,0 @@ CreateBlueprintVersion - Max number of Blueprint versions per Blueprint | Each s -CreateBlueprintVersion - Throttle limit in transactions per second | Each supported Region: 1 | No | No Description Available @@ -215,3 +212,0 @@ CreatePromptVersion requests per second | Each supported Region: 2 | No | The ma -Cross-Region InvokeModel requests per minute for Amazon Nova Lite | Each supported Region: 2,000 | No | The maximum number of requests 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. -Cross-Region InvokeModel requests per minute for Amazon Nova Micro | Each supported Region: 2,000 | No | The maximum number of requests 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. -Cross-Region InvokeModel requests per minute for Amazon Nova Pro | Each supported Region: 200 | No | The maximum number of requests 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. @@ -219,4 +214 @@ Cross-Region InvokeModel requests per minute for Anthropic Claude 3.5 Haiku | Ea -Cross-Region InvokeModel requests per minute for Anthropic Claude 3.5 Sonnet V2 | Each supported Region: 100 | 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. -Cross-Region InvokeModel tokens per minute for Amazon Nova Lite | Each supported Region: 4,000,000 | No | The maximum number of 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. -Cross-Region InvokeModel tokens per minute for Amazon Nova Micro | Each supported Region: 4,000,000 | No | The maximum number of 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. -Cross-Region InvokeModel tokens per minute for Amazon Nova Pro | Each supported Region: 800,000 | No | The maximum number of 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. +Cross-Region InvokeModel requests per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 500 Each of the other supported Regions: 100 | 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. @@ -224,2 +216,7 @@ Cross-Region InvokeModel tokens per minute for Anthropic Claude 3.5 Haiku | Each -Cross-Region InvokeModel tokens per minute for Anthropic Claude 3.5 Sonnet V2 | Each supported Region: 800,000 | 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. -Cross-region model inference requests per minute for Anthropic Claude 3.7 Sonnet V1 | Each supported Region: 250 | No | The maximum number of cross-region requests that you can submit for model inference in one minute for Anthropic Claude 3.7 Sonnet V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-Region InvokeModel tokens per minute for Anthropic Claude 3.5 Sonnet V2 | us-west-2: 4,000,000 Each of the other supported Regions: 800,000 | 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. +Cross-region InvokeModel requests per minute for Anthropic Claude 3.5 Sonnet | us-east-1: 100 us-east-2: 100 us-west-2: 500 ap-south-1: 100 ap-southeast-2: 100 eu-south-1: 100 Each of the other supported Regions: 40 | No | The maximum number of times that you can call model inference in one minute for Anthropic Claude 3.5 Sonnet. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region InvokeModel tokens per minute for Anthropic Claude 3.5 Sonnet | us-east-1: 800,000 us-east-2: 800,000 us-west-2: 4,000,000 ap-south-1: 800,000 ap-southeast-2: 800,000 eu-south-1: 800,000 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. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region model inference requests per minute for Amazon Nova Lite | Each supported Region: 2,000 | No | The maximum number of cross-region requests 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. +Cross-region model inference requests per minute for Amazon Nova Micro | Each supported Region: 2,000 | No | The maximum number of cross-region requests 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. +Cross-region model inference requests per minute for Amazon Nova Pro | Each supported Region: 200 | No | The maximum number of cross-region requests 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. +Cross-region model inference requests per minute for Anthropic Claude 3.7 Sonnet V1 | us-east-1: 250 us-east-2: 250 us-west-2: 250 Each of the other supported Regions: 100 | No | The maximum number of cross-region requests that you can submit for model inference in one minute for Anthropic Claude 3.7 Sonnet V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -226,0 +224,2 @@ Cross-region model inference requests per minute for DeepSeek R1 V1 | Each suppo +Cross-region model inference requests per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 400 | No | The maximum number of cross-region requests 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. +Cross-region model inference requests per minute for Meta Llama 3.1 8B Instruct | Each supported Region: 1,600 | No | The maximum number of cross-region requests that you can submit for model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -228 +227,4 @@ Cross-region model inference requests per minute for Meta Llama 3.3 70B Instruct -Cross-region model inference tokens per minute for Anthropic Claude 3.7 Sonnet V1 | Each supported Region: 1,000,000 | No | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude 3.7 Sonnet V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +Cross-region model inference tokens per minute for Amazon Nova Lite | Each supported Region: 4,000,000 | No | The maximum number of cross-region 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. +Cross-region model inference tokens per minute for Amazon Nova Micro | Each supported Region: 4,000,000 | No | The maximum number of cross-region 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. +Cross-region model inference tokens per minute for Amazon Nova Pro | Each supported Region: 800,000 | No | The maximum number of cross-region 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. +Cross-region model inference tokens per minute for Anthropic Claude 3.7 Sonnet V1 | us-east-1: 1,000,000 us-east-2: 1,000,000 us-west-2: 1,000,000 Each of the other supported Regions: 100,000 | No | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude 3.7 Sonnet V1. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -229,0 +232,2 @@ Cross-region model inference tokens per minute for DeepSeek R1 V1 | Each support +Cross-region model inference tokens per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 800,000 | No | The maximum number of cross-region 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. +Cross-region model inference tokens per minute for Meta Llama 3.1 8B Instruct | Each supported Region: 600,000 | No | The maximum number of cross-region tokens that you can submit for model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -237 +240,0 @@ DeleteAgentVersion requests per second | Each supported Region: 2 | No | The max -DeleteBlueprint - Throttle limit in transactions per second | Each supported Region: 1 | No | No Description Available @@ -259,2 +261,0 @@ GetAgentVersion requests per second | Each supported Region: 10 | No | The maxim -GetBlueprint - Throttle limit in transactions per second | Each supported Region: 5 | No | No Description Available -GetDataAutomationStatus - Throttle limit in transactions per second | Each supported Region: 5 | No | No Description Available @@ -278 +278,0 @@ InvokeDataAutomationAsync - Max number of open jobs | Each supported Region: 1,8 -InvokeDataAutomationAsync - Throttle limit in transactions per second | Each supported Region: 5 | No | No Description Available @@ -281 +281 @@ Iterator nodes per flow | Each supported Region: 1 | No | The maximum number of -Knowledge base nodes per flow | Each supported Region: 10 | No | The maximum number of knowledge base nodes. +Knowledge base nodes per flow | Each supported Region: 20 | No | The maximum number of knowledge base nodes. @@ -283 +283 @@ Knowledge bases per account | Each supported Region: 100 | No | The maximum numb -Lambda function nodes per flow | Each supported Region: 10 | No | The maximum number of Lambda function nodes. +Lambda function nodes per flow | Each supported Region: 20 | No | The maximum number of Lambda function nodes. @@ -290 +289,0 @@ ListAgents requests per second | Each supported Region: 10 | No | The maximum nu -ListBlueprint - Throttle limit in transactions per second | Each supported Region: 5 | No | No Description Available @@ -303 +302 @@ Maximum Levels of Field Hierarchy | Each supported Region: 1 | No | No Descripti -Maximum Number of pages per document | us-east-1: 1,500 Each of the other supported Regions: 1,000 | No | No Description Available +Maximum Number of pages per document | Each supported Region: 1,500 | No | No Description Available @@ -307,0 +307,10 @@ Maximum document file size (MB) | Each supported Region: 500 | No | No Descripti +Maximum hourly input token units for model claude-3-5-sonnet-20241022-v2 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-02989E0C) | Maximum input token units (x tokens-per-minute) for combined claude-3-5-sonnet-20241022-v2 PTv2 Provisions exceeding monthly committed input token units. +Maximum hourly input token units for model llama3-2-11b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4B9FCAF2) | Maximum input token units (x tokens-per-minute) for combined llama3-2-11b-instruct-v1 PTv2 Provisions exceeding monthly committed input token units. +Maximum hourly input token units for model llama3-2-1b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-27A6ECB4) | Maximum input token units (x tokens-per-minute) for combined llama3-2-1b-instruct-v1 PTv2 Provisions exceeding monthly committed input token units. +Maximum hourly input token units for model llama3-2-3b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-12CBE43C) | Maximum input token units (x tokens-per-minute) for combined llama3-2-3b-instruct-v1 PTv2 Provisions exceeding monthly committed input token units. +Maximum hourly input token units for model llama3-2-90b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-A3722B41) | Maximum input token units (x tokens-per-minute) for combined llama3-2-90b-instruct-v1 PTv2 Provisions exceeding monthly committed input token units. +Maximum hourly output token units for model claude-3-5-sonnet-20241022-v2 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9A6D7799) | Maximum output token units (x tokens-per-minute) for combined claude-3-5-sonnet-20241022-v2 PTv2 Provisions exceeding monthly committed output token units. +Maximum hourly output token units for model llama3-2-11b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B7295400) | Maximum output token units (x tokens-per-minute) for combined llama3-2-11b-instruct-v1 PTv2 Provisions exceeding monthly committed output token units. +Maximum hourly output token units for model llama3-2-1b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-10205469) | Maximum output token units (x tokens-per-minute) for combined llama3-2-1b-instruct-v1 PTv2 Provisions exceeding monthly committed output token units. +Maximum hourly output token units for model llama3-2-3b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-A9AFC293) | Maximum output token units (x tokens-per-minute) for combined llama3-2-3b-instruct-v1 PTv2 Provisions exceeding monthly committed output token units. +Maximum hourly output token units for model llama3-2-90b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-66FAAC98) | Maximum output token units (x tokens-per-minute) for combined llama3-2-90b-instruct-v1 PTv2 Provisions exceeding monthly committed output token units. @@ -311 +320,11 @@ Maximum line length for distillation customization jobs | Each supported Region: -Maximum number of Blueprints per Start Inference request (Documents) | Each supported Region: 1 | No | No Description Available +Maximum monthly input token units for model claude-3-5-sonnet-20241022-v2 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E80E06C4) | Maximum input token units (x tokens-per-minute) for combined claude-3-5-sonnet-20241022-v2 PTv2 Reservations. +Maximum monthly input token units for model llama3-2-11b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0BDC8BBA) | Maximum input token units (x tokens-per-minute) for combined llama3-2-11b-instruct-v1 PTv2 Reservations. +Maximum monthly input token units for model llama3-2-1b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4BE65036) | Maximum input token units (x tokens-per-minute) for combined llama3-2-1b-instruct-v1 PTv2 Reservations. +Maximum monthly input token units for model llama3-2-3b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-CA6675AE) | Maximum input token units (x tokens-per-minute) for combined llama3-2-3b-instruct-v1 PTv2 Reservations. +Maximum monthly input token units for model llama3-2-90b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-03208695) | Maximum input token units (x tokens-per-minute) for combined llama3-2-90b-instruct-v1 PTv2 Reservations. +Maximum monthly output token units for model claude-3-5-sonnet-20241022-v2 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D6FE4366) | Maximum output token units (x tokens-per-minute) for combined claude-3-5-sonnet-20241022-v2 PTv2 Reservations. +Maximum monthly output token units for model llama3-2-11b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4ED5F5E3) | Maximum output token units (x tokens-per-minute) for combined llama3-2-11b-instruct-v1 PTv2 Reservations. +Maximum monthly output token units for model llama3-2-1b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-094C5DAD) | Maximum output token units (x tokens-per-minute) for combined llama3-2-1b-instruct-v1 PTv2 Reservations. +Maximum monthly output token units for model llama3-2-3b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-59EF624F) | Maximum output token units (x tokens-per-minute) for combined llama3-2-3b-instruct-v1 PTv2 Reservations. +Maximum monthly output token units for model llama3-2-90b-instruct-v1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-2DA363B5) | Maximum output token units (x tokens-per-minute) for combined llama3-2-90b-instruct-v1 PTv2 Reservations. +Maximum number of Blueprints per Start Inference request (Documents) | Each supported Region: 10 | No | No Description Available @@ -371,0 +391,3 @@ Model units per provisioned model for Anthropic Claude 3.5 Sonnet V2 51K | Each +Model units per provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 18K | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D09F1612) | The maximum number of model units that can be allotted to a provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 18K. +Model units per provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 200K | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F4131C39) | The maximum number of model units that can be allotted to a provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 200K. +Model units per provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 51K | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-0B0CDE73) | The maximum number of model units that can be allotted to a provisioned model for Anthropic Claude 3.7 V1.0 Sonnet 51K. @@ -383 +404,0 @@ Model units per provisioned model for Cohere Embed Multilingual | Each supported -Model units per provisioned model for DeepSeek R1 Distill Llama 3.3 70B | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-8519D248) | The maximum number of model units that can be allotted to a provisioned model for DeepSeek R1 Distill Llama 3.3 70B. @@ -392 +413,4 @@ Model units per provisioned model for Meta Llama 3.1 8B Instruct | Each supporte -Model units per provisioned model for Meta Llama 3.3 70B Instruct | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-52A668E3) | The maximum number of model units that can be allotted to a provisioned model for Meta Llama 3.3 70B Instruct. +Model units per provisioned model for Meta Llama 3.2 11B Instruct | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-1679CB40) | The maximum number of model units that can be allotted to a provisioned model for Meta Llama 3.2 11B Instruct. +Model units per provisioned model for Meta Llama 3.2 1B Instruct | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B547321D) | The maximum number of model units that can be allotted to a provisioned model for Meta Llama 3.2 1B Instruct. +Model units per provisioned model for Meta Llama 3.2 3B Instruct | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-12E68701) | The maximum number of model units that can be allotted to a provisioned model for Meta Llama 3.2 3B Instruct. +Model units per provisioned model for Meta Llama 3.2 90B Instruct | Each supported Region: 0 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-DEE3A9C7) | The maximum number of model units that can be allotted to a provisioned model for Meta Llama 3.2 90B Instruct. @@ -415,0 +440,4 @@ Number of prompts in a custom prompt dataset | Each supported Region: 1,000 | No +On-Demand, latency-optimized model inference requests per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 100 | No | The maximum number of on-demand, latency-optimized requests 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, latency-optimized model inference requests per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 100 | No | The maximum number of on-demand, latency-optimized requests that you can submit for model inference in one minute for Meta Llama 3.1 70B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-Demand, latency-optimized model inference tokens per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 40,000 | No | The maximum number of on-demand, latency-optimized 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, latency-optimized model inference tokens per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 40,000 | No | The maximum number of on-demand, latency-optimized tokens that you can submit for model inference in one minute for Meta Llama 3.1 70B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -429,3 +456,0 @@ On-demand InvokeModel requests per minute for Amazon Nova Canvas | Each supporte -On-demand InvokeModel requests per minute for Amazon Nova Lite | Each supported Region: 1,000 | No | The maximum number of requests 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 InvokeModel requests per minute for Amazon Nova Micro | Each supported Region: 1,000 | No | The maximum number of requests 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 InvokeModel requests per minute for Amazon Nova Pro | Each supported Region: 100 | No | The maximum number of requests 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. @@ -434 +459 @@ On-demand InvokeModel requests per minute for Amazon Titan Image Generator G1 | -On-demand InvokeModel requests per minute for Amazon Titan Image Generator G1 V2 | Each supported Region: 60 | No | The maximum number of times that you can call InvokeModel in one minute for Amazon Titan Image Generator G V2. +On-demand InvokeModel requests per minute for Amazon Titan Image Generator G1 V2 | Each supported Region: 60 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Amazon Titan Image Generator G1 V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -442 +466,0 @@ On-demand InvokeModel requests per minute for Anthropic Claude 3 Haiku | us-eas -On-demand InvokeModel requests per minute for Anthropic Claude 3 Opus | Each supported Region: 50 | No | The maximum number of times that you can call InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream requests for Anthropic Claude 3 Opus. @@ -444 +467,0 @@ On-demand InvokeModel requests per minute for Anthropic Claude 3 Sonnet | us-ea -On-demand InvokeModel requests per minute for Anthropic Claude 3.5 Haiku | us-west-1: 400 Each of the other supported Regions: 1,000 | No | The maximum number of times that you can call InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream tokens for Anthropic Claude 3.5 Haiku. @@ -460,2 +482,0 @@ On-demand InvokeModel requests per minute for Meta Llama 2 Chat 70B | Each suppo -On-demand InvokeModel requests per minute for Meta Llama 3 70B Instruct | Each supported Region: 400 | No | The maximum number of times that you can call InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream requests for Meta Llama 3 70B Instruct. -On-demand InvokeModel requests per minute for Meta Llama 3 8B Instruct | Each supported Region: 800 | No | The maximum number of times that you can call InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream requests for Meta Llama 3 8B Instruct. @@ -478,3 +498,0 @@ On-demand InvokeModel tokens per minute for AI21 Labs Jurassic-2 Ultra | Each su -On-demand InvokeModel tokens per minute for Amazon Nova Lite | Each supported Region: 2,000,000 | No | The maximum number of 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 InvokeModel tokens per minute for Amazon Nova Micro | Each supported Region: 2,000,000 | No | The maximum number of 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 InvokeModel tokens per minute for Amazon Nova Pro | Each supported Region: 400,000 | No | The maximum number of 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. @@ -482 +500 @@ On-demand InvokeModel tokens per minute for Amazon Titan Image Generator G1 | Ea -On-demand InvokeModel tokens per minute for Amazon Titan Image Generator G1 V2 | Each supported Region: 2,000 | No | The maximum number of tokens that you can provide through InvokeModel in one minute for Amazon Titan Image Generator G1 V2. +On-demand InvokeModel tokens per minute for Amazon Titan Image Generator G1 V2 | Each supported Region: 2,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Amazon Titan Image Generator G1 V2. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -490 +507,0 @@ On-demand InvokeModel tokens per minute for Anthropic Claude 3 Haiku | us-east- -On-demand InvokeModel tokens per minute for Anthropic Claude 3 Opus | Each supported Region: 400,000 | No | The maximum number of tokens that you can provide through InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream tokens for Anthropic Claude 3 Opus. @@ -492 +508,0 @@ On-demand InvokeModel tokens per minute for Anthropic Claude 3 Sonnet | us-east -On-demand InvokeModel tokens per minute for Anthropic Claude 3.5 Haiku | us-west-1: 300,000 Each of the other supported Regions: 2,000,000 | No | The maximum number of tokens that you can provide through InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream tokens for Anthropic Claude 3.5 Haiku. @@ -507,2 +522,0 @@ On-demand InvokeModel tokens per minute for Meta Llama 2 Chat 70B | Each support -On-demand InvokeModel tokens per minute for Meta Llama 3 70B Instruct | Each supported Region: 300,000 | No | The maximum number of tokens that you can provide through InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream tokens for Meta Llama 3 70B Instruct. -On-demand InvokeModel tokens per minute for Meta Llama 3 8B Instruct | Each supported Region: 300,000 | No | The maximum number of tokens that you can provide through InvokeModel and InvokeModelWithResponseStream in one minute. The quota considers the combined sum of InvokeModel and InvokeModelWithResponseStream tokens for Meta Llama 3 8B Instruct. @@ -515,4 +528,0 @@ On-demand latency-optimized InvokeModel tokens per minute for Anthropic Claude 3 -On-demand latency-optimized model inference requests per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 100 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.1 405B Instruct, if latency optimization is configured. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand latency-optimized model inference requests per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 100 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.1 70B Instruct, if latency optimization is configured. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand latency-optimized model inference tokens per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 40,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Meta Llama 3.1 405B Instruct, if latency optimization is configured. The quota considers the combined sum of tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand latency-optimized model inference tokens per minute for Meta Llama 3.1 70b Instruct | Each supported Region: 40,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Meta Llama 3.1 70b Instruct, if latency optimization is configured. The quota considers the combined sum of tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. @@ -520,3 +530,10 @@ On-demand model inference concurrent requests for Luma Ray V2 | Each supported R -On-demand model inference requests per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 200 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.1 405B Instruct. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand model inference requests per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 400 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.1 70B Instruct. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand model inference requests per minute for Meta Llama 3.1 8B Instruct | Each supported Region: 800 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. +On-demand model inference requests per minute for Amazon Nova Lite | Each supported Region: 1,000 | No | The maximum number of on-demand requests 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 requests per minute for Amazon Nova Micro | Each supported Region: 1,000 | No | The maximum number of on-demand requests 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 requests per minute for Amazon Nova Pro | Each supported Region: 100 | No | The maximum number of on-demand requests 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 requests per minute for Anthropic Claude 3 Opus | Each supported Region: 50 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Anthropic Claude 3 Opus. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for Anthropic Claude 3.5 Haiku | us-west-1: 400 Each of the other supported Regions: 1,000 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Anthropic Claude 3.5 Haiku. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for Meta Llama 3 70B Instruct | Each supported Region: 400 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Meta Llama 3 70B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for Meta Llama 3 8B Instruct | Each supported Region: 800 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Meta Llama 3 8B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for Meta Llama 3.1 405B Instruct | Each supported Region: 200 | No | The maximum number of on-demand requests 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 requests per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 400 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Meta Llama 3.1 70B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference requests per minute for Meta Llama 3.1 8B Instruct | Each supported Region: 800 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -524 +541 @@ On-demand model inference requests per minute for Meta Llama 3.2 11B Instruct | -On-demand model inference requests per minute for Meta Llama 3.2 1B Instruct | Each supported Region: 800 | No | The maximum number of times that you can call model inference in one minute for Meta Llama 3.2 1B Instruct. The quota considers the combined sum of requests for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. +On-demand model inference requests per minute for Meta Llama 3.2 1B Instruct | Each supported Region: 800 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Meta Llama 3.2 1B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -529 +546,10 @@ On-demand model inference requests per minute for Mistral Large 2407 | Each supp -On-demand model inference tokens per minute for Meta Llama 3.1 8B Instruct | Each supported Region: 300,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. +On-demand model inference tokens per minute for Amazon Nova Lite | Each supported Region: 2,000,000 | 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 | Each supported Region: 2,000,000 | 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 | Each supported Region: 400,000 | 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 Anthropic Claude 3 Opus | Each supported Region: 400,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Anthropic Claude 3 Opus. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Anthropic Claude 3.5 Haiku | us-west-1: 300,000 Each of the other supported Regions: 2,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Anthropic Claude 3.5 Haiku. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Meta Llama 3 70B Instruct | Each supported Region: 300,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3 70B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Meta Llama 3 8B Instruct | Each supported Region: 300,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3 8B 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 Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. +On-demand model inference tokens per minute for Meta Llama 3.1 70B Instruct | Each supported Region: 300,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3.1 70B 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 8B Instruct | Each supported Region: 300,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3.1 8B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -531 +557 @@ On-demand model inference tokens per minute for Meta Llama 3.2 11B Instruct | Ea -On-demand model inference tokens per minute for Meta Llama 3.2 1B Instruct | Each supported Region: 300,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Meta Llama 3.2 1B Instruct. The quota considers the combined sum of tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. +On-demand model inference tokens per minute for Meta Llama 3.2 1B Instruct | Each supported Region: 300,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Meta Llama 3.2 1B Instruct. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -536,3 +562 @@ On-demand model inference tokens per minute for Mistral Large 2407 | Each suppor -On-demand model inference tokens per minute for for Meta Llama 3.1 405B Instruct | Each supported Region: 400,000 | No | The maximum number of 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 tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -On-demand model inference tokens per minute for for Meta Llama 3.1 70B Instruct | Each supported Region: 300,000 | No | The maximum number of tokens that you can submit for model inference in one minute for Meta Llama 3.1 70B Instruct. The quota considers the combined sum of tokens for InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream. -Output nodes per flow | Each supported Region: 10 | No | The maximum number of flow output nodes. +Output nodes per flow | Each supported Region: 20 | No | The maximum number of flow output nodes. @@ -542,2 +566,2 @@ PrepareFlow requests per second | Each supported Region: 2 | No | The maximum nu -Prompt nodes per flow | Each supported Region: 10 | [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: 50 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B783C50B) | The maximum number of prompts. +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. @@ -625,0 +650,4 @@ Sum of training and validation records for a Meta Llama 3.1 8B Instruct v1 Fine- +Sum of training and validation records for a Meta Llama 3.2 11B Instruct v1 Fine-tuning job | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E5FD5C04) | The maximum combined number of training and validation records allowed for a Meta Llama 3.2 11B Instruct Fine-tuning job. +Sum of training and validation records for a Meta Llama 3.2 1B Instruct v1 Fine-tuning job | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-70B8359C) | The maximum combined number of training and validation records allowed for a Meta Llama 3.2 1B Instruct Fine-tuning job. +Sum of training and validation records for a Meta Llama 3.2 3B Instruct v1 Fine-tuning job | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-75A18A04) | The maximum combined number of training and validation records allowed for a Meta Llama 3.2 3B Instruct Fine-tuning job. +Sum of training and validation records for a Meta Llama 3.2 90B Instruct v1 Fine-tuning job | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-8076814C) | The maximum combined number of training and validation records allowed for a Meta Llama 3.2 90B Instruct Fine-tuning job. @@ -660 +687,0 @@ UpdateAgentKnowledgeBase requests per second | Each supported Region: 4 | No | T -UpdateBlueprint - Throttle limit in transactions per second | Each supported Region: 1 | No | No Description Available