AWS general documentation change
Summary
Updated AWS Bedrock service quotas documentation with new model additions (GLM 5, MiniMax M2.5, NVIDIA Nemotron 3 Super 120B A12B, Z.ai GLM 5), regional quota adjustments for me-central-1 and other regions, and removal of some outdated quota entries.
Security assessment
The changes are routine service quota updates for new AI models and regional capacity adjustments. There is no evidence of security vulnerabilities, incidents, or security fixes. The only security-adjacent change is a quota adjustment for Guardrails regex entities in the Sensitive Information Filter, but this is a capacity limit change, not a security fix or vulnerability disclosure.
Diff
diff --git a/general/latest/gr/bedrock.md b/general/latest/gr/bedrock.md index 2c2c62b17..19d4da2d9 100644 --- a//general/latest/gr/bedrock.md +++ b//general/latest/gr/bedrock.md @@ -295 +295 @@ Name | Default | Adjustable | Description -(Guardrails) Regex entities in Sensitive Information Filter | Each supported Region: 30 | No | The maximum number of guardrail filter regexes that can be included in a sensitive information policy +(Guardrails) Regex entities in Sensitive Information Filter | me-central-1: 10 Each of the other supported Regions: 30 | No | The maximum number of guardrail filter regexes that can be included in a sensitive information policy @@ -424,0 +425 @@ Batch inference input file size (in GB) for GLM 4.7 Flash | Each supported Regio +Batch inference input file size (in GB) for GLM 5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for GLM 5. @@ -442,0 +444 @@ Batch inference input file size (in GB) for MiniMax M2.1 | Each supported Region +Batch inference input file size (in GB) for MiniMax M2.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for MiniMax M2.5. @@ -448,0 +451 @@ Batch inference input file size (in GB) for Mistral Small | Each supported Regio +Batch inference input file size (in GB) for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for NVIDIA Nemotron 3 Super 120B A12B. @@ -491,0 +495 @@ Batch inference job size (in GB) for GLM 4.7 Flash | Each supported Region: 5 | +Batch inference job size (in GB) for GLM 5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for GLM 5. @@ -509,0 +514 @@ Batch inference job size (in GB) for MiniMax M2.1 | Each supported Region: 5 | N +Batch inference job size (in GB) for MiniMax M2.5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for MiniMax M2.5. @@ -515,0 +521 @@ Batch inference job size (in GB) for Mistral Small | Each supported Region: 5 | +Batch inference job size (in GB) for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for NVIDIA Nemotron 3 Super 120B A12B. @@ -519 +525 @@ Batch inference job size (in GB) for NVIDIA Nemotron Nano 9B | Each supported Re -Batch inference job size (in GB) for Nova Lite V1 | Each supported Region: 100 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Nova Lite V1. +Batch inference job size (in GB) for Nova Lite V1 | me-central-1: 5 Each of the other supported Regions: 100 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Nova Lite V1. @@ -562 +567,0 @@ Cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V -Cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V1 1M Context Length | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-410BCACA) | The maximum number of cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -568 +572,0 @@ Cross-region model inference requests per minute for Anthropic Claude Sonnet 4.6 -Cross-region model inference requests per minute for Anthropic Claude Sonnet 4.6 1M Context Length | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-47DE5258) | The maximum number of cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -615 +618,0 @@ Cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 -Cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 1M Context Length | Each supported Region: 1,000,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-7DBBE6A1) | The maximum number of cross-region tokens that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1 1M Context Length. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -651,4 +654,4 @@ Global cross-region model inference requests per minute for Amazon Nova 2 Pro Pr -Global cross-region model inference requests per minute for Anthropic Claude Haiku 4.5 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E5084BBA) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Haiku 4.5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. -Global cross-region model inference requests per minute for Anthropic Claude Opus 4.5 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-58424D95) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. -Global cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-3DD46812) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. -Global cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V1 1M Context Length | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-CDA5906C) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Haiku 4.5 | me-central-1: 1,000 Each of the other supported Regions: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E5084BBA) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Haiku 4.5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Opus 4.5 | me-central-1: 500 Each of the other supported Regions: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-58424D95) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V1 | me-central-1: 500 Each of the other supported Regions: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-3DD46812) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Opus 4.6 V1 1M Context Length | eu-west-1: 1,000 Each of the other supported Regions: 5 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-CDA5906C) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Opus 4.6 V1 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -656,2 +659,2 @@ Global cross-region model inference requests per minute for Anthropic Claude Son -Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1 | Each supported Region: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-DB84CE56) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.5 V1. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. -Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-C0D53EFB) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1 | me-central-1: 1,000 Each of the other supported Regions: 10,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-DB84CE56) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.5 V1. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length | me-central-1: 5 Each of the other supported Regions: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-C0D53EFB) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -659 +662 @@ Global cross-region model inference requests per minute for Anthropic Claude Son -Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.6 1M Context Length | Each supported Region: 1,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B117CDDA) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. +Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.6 1M Context Length | us-east-2: 1,000 Each of the other supported Regions: 500 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B117CDDA) | The maximum number of global cross-region requests that you can submit for model inference in one minute for Anthropic Claude Sonnet 4.6 1M Context Length. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -666 +669 @@ 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: 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. +Global cross-region model inference tokens per day for Anthropic Claude Opus 4.6 V1 | me-central-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. @@ -671 +674 @@ 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: 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. +Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4.6 | me-central-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. @@ -679 +682 @@ 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: 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. +Global cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1 | me-central-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. @@ -684 +687 @@ 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: 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. +Global cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6 | me-central-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. @@ -713,0 +717 @@ Minimum number of records per batch inference job for GLM 4.7 Flash | Each suppo +Minimum number of records per batch inference job for GLM 5 | Each supported Region: 100 | No | The minimum number of records across all input files in a batch inference job for GLM 5. @@ -731,0 +736 @@ Minimum number of records per batch inference job for MiniMax M2.1 | Each suppor +Minimum number of records per batch inference job for MiniMax M2.5 | Each supported Region: 100 | No | The minimum number of records across all input files in a batch inference job for MiniMax M2.5. @@ -737,0 +743 @@ Minimum number of records per batch inference job for Mistral Small | Each suppo +Minimum number of records per batch inference job for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 100 | No | The minimum number of records across all input files in a batch inference job for NVIDIA Nemotron 3 Super 120B A12B. @@ -779 +784,0 @@ Model invocation max tokens per day for Anthropic Claude Opus 4.5 (doubled for c -Model invocation max tokens per day for Anthropic Claude Opus 4.6 1M Context Length (doubled for cross-region calls) | Each supported Region: 720,000,000 | No | Daily maximum tokens for model inference for Anthropic Claude Opus 4.6 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. @@ -802,0 +808 @@ Model invocation max tokens per day for Meta Llama 4 Scout V1 (doubled for cross +Model invocation max tokens per day for MiniMax M2.5 (doubled for cross-region calls) | Each supported Region: 144,000,000,000 | No | Daily maximum tokens for model inference for MiniMax M2.5. 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. @@ -815,0 +822 @@ Model invocation max tokens per day for Moonshot AI Kimi K2.5 (doubled for cross +Model invocation max tokens per day for NVIDIA Nemotron 3 Super 120B A12B (doubled for cross-region calls) | Each supported Region: 144,000,000,000 | No | Daily maximum tokens for model inference for NVIDIA Nemotron 3 Super 120B A12B. 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. @@ -829,0 +837 @@ Model invocation max tokens per day for Voxtral Small 1.0 (doubled for cross-reg +Model invocation max tokens per day for Z.ai GLM 5 (doubled for cross-region calls) | Each supported Region: 144,000,000,000 | No | Daily maximum tokens for model inference for Z.ai GLM 5. 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. @@ -942 +950 @@ On-demand model inference requests per minute for Anthropic Claude 3.5 Haiku | -On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet | us-east-1: 50 us-east-2: 50 us-west-2: 250 ap-northeast-2: 50 ap-south-1: 50 ap-southeast-2: 50 Each of the other supported Regions: 20 | 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. +On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet | us-west-2: 250 ap-northeast-1: 20 ap-southeast-1: 20 eu-central-1: 20 eu-west-1: 20 eu-west-3: 20 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. The quota considers the combined sum of Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -979,0 +988 @@ On-demand model inference requests per minute for Meta Llama 3.3 70B Instruct | +On-demand model inference requests per minute for MiniMax M2.5 | Each supported Region: 10,000 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for MiniMax M2.5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -992,0 +1002 @@ On-demand model inference requests per minute for Moonshot AI Kimi K2.5 | Each s +On-demand model inference requests per minute for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 10,000 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for NVIDIA Nemotron 3 Super 120B A12B. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -1029,0 +1040 @@ On-demand model inference requests per minute for Voxtral Small 1.0 | Each suppo +On-demand model inference requests per minute for Z.ai GLM 5 | Each supported Region: 10,000 | No | The maximum number of on-demand requests that you can submit for model inference in one minute for Z.ai GLM 5. This quota represents the total number of requests to the Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream actions. @@ -1052 +1063 @@ On-demand model inference tokens per minute for Anthropic Claude 3.5 Haiku | us -On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet | us-east-1: 400,000 us-east-2: 400,000 us-west-2: 2,000,000 ap-northeast-2: 400,000 ap-south-1: 400,000 ap-southeast-2: 400,000 Each of the other supported Regions: 200,000 | 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. +On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet | us-west-2: 2,000,000 ap-northeast-1: 200,000 ap-southeast-1: 200,000 eu-central-1: 200,000 eu-west-1: 200,000 eu-west-3: 200,000 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. @@ -1088,0 +1100 @@ On-demand model inference tokens per minute for Meta Llama 3.3 70B Instruct | Ea +On-demand model inference tokens per minute for MiniMax M2.5 | Each supported Region: 100,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for MiniMax M2.5. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -1101,0 +1114 @@ On-demand model inference tokens per minute for Moonshot AI Kimi K2.5 | Each sup +On-demand model inference tokens per minute for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 100,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for NVIDIA Nemotron 3 Super 120B A12B. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -1115,0 +1129 @@ On-demand model inference tokens per minute for Voxtral Small 1.0 | Each support +On-demand model inference tokens per minute for Z.ai GLM 5 | Each supported Region: 100,000,000 | No | The maximum number of on-demand tokens that you can submit for model inference in one minute for Z.ai GLM 5. The quota considers the combined sum of input and output tokens across all requests to Converse, ConverseStream, InvokeModel and InvokeModelWithResponseStream. @@ -1129,5 +1143,5 @@ Records per batch inference job for Claude 3.7 Sonnet | Each supported Region: 1 -Records per batch inference job for Claude Haiku 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-28612175) | The maximum number of records across all input files in a batch inference job for Claude Haiku 4.5. -Records per batch inference job for Claude Opus 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-2767B9A9) | The maximum number of records across all input files in a batch inference job for Claude Opus 4.5. -Records per batch inference job for Claude Opus 4.6 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9AA02BEF) | The maximum number of records across all input files in a batch inference job for Claude Opus 4.6. -Records per batch inference job for Claude Sonnet 4 | Each supported Region: 100,000 | [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. -Records per batch inference job for Claude Sonnet 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FFFEDD8D) | The maximum number of records across all input files in a batch inference job for Claude Sonnet 4.5. +Records per batch inference job for Claude Haiku 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-28612175) | The maximum number of records across all input files in a batch inference job for Claude Haiku 4.5. +Records per batch inference job for Claude Opus 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-2767B9A9) | The maximum number of records across all input files in a batch inference job for Claude Opus 4.5. +Records per batch inference job for Claude Opus 4.6 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9AA02BEF) | The maximum number of records across all input files in a batch inference job for Claude Opus 4.6. +Records per batch inference job for Claude Sonnet 4 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [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. +Records per batch inference job for Claude Sonnet 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FFFEDD8D) | The maximum number of records across all input files in a batch inference job for Claude Sonnet 4.5. @@ -1139,0 +1154 @@ Records per batch inference job for GLM 4.7 Flash | Each supported Region: 100,0 +Records per batch inference job for GLM 5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-64CF3679) | The maximum number of records across all input files in a batch inference job for GLM 5. @@ -1157,0 +1173 @@ Records per batch inference job for MiniMax M2.1 | Each supported Region: 100,00 +Records per batch inference job for MiniMax M2.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-C4659D61) | The maximum number of records across all input files in a batch inference job for MiniMax M2.5. @@ -1163,0 +1180 @@ Records per batch inference job for Mistral Small | Each supported Region: 100,0 +Records per batch inference job for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-196A63C0) | The maximum number of records across all input files in a batch inference job for NVIDIA Nemotron 3 Super 120B A12B. @@ -1167,4 +1184,4 @@ Records per batch inference job for NVIDIA Nemotron Nano 9B | Each supported Reg -Records per batch inference job for Nova 2 Lite | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-ECCE76C6) | The maximum number of records across all input files in a batch inference job for Nova 2 Lite. -Records per batch inference job for Nova Lite V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-916C9264) | The maximum number of records across all input files in a batch inference job for Nova Lite V1. -Records per batch inference job for Nova Micro V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-57DC56A1) | The maximum number of records across all input files in a batch inference job for Nova Micro V1. -Records per batch inference job for Nova Pro V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-89197AE6) | The maximum number of records across all input files in a batch inference job for Nova Pro V1. +Records per batch inference job for Nova 2 Lite | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-ECCE76C6) | The maximum number of records across all input files in a batch inference job for Nova 2 Lite. +Records per batch inference job for Nova Lite V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-916C9264) | The maximum number of records across all input files in a batch inference job for Nova Lite V1. +Records per batch inference job for Nova Micro V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-57DC56A1) | The maximum number of records across all input files in a batch inference job for Nova Micro V1. +Records per batch inference job for Nova Pro V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-89197AE6) | The maximum number of records across all input files in a batch inference job for Nova Pro V1. @@ -1195,5 +1212,5 @@ Records per input file per batch inference job for Claude 3.7 Sonnet | Each supp -Records per input file per batch inference job for Claude Haiku 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9EDE6039) | The maximum number of records in an input file in a batch inference job for Claude Haiku 4.5. -Records per input file per batch inference job for Claude Opus 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F7440010) | The maximum number of records in an input file in a batch inference job for Claude Opus 4.5. -Records per input file per batch inference job for Claude Opus 4.6 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D8E451A7) | The maximum number of records in an input file in a batch inference job for Claude Opus 4.6. -Records per input file per batch inference job for Claude Sonnet 4 | Each supported Region: 100,000 | [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. -Records per input file per batch inference job for Claude Sonnet 4.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4DFF050E) | The maximum number of records in an input file in a batch inference job for Claude Sonnet 4.5. +Records per input file per batch inference job for Claude Haiku 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9EDE6039) | The maximum number of records in an input file in a batch inference job for Claude Haiku 4.5. +Records per input file per batch inference job for Claude Opus 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-F7440010) | The maximum number of records in an input file in a batch inference job for Claude Opus 4.5. +Records per input file per batch inference job for Claude Opus 4.6 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D8E451A7) | The maximum number of records in an input file in a batch inference job for Claude Opus 4.6. +Records per input file per batch inference job for Claude Sonnet 4 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [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. +Records per input file per batch inference job for Claude Sonnet 4.5 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4DFF050E) | The maximum number of records in an input file in a batch inference job for Claude Sonnet 4.5. @@ -1205,0 +1223 @@ Records per input file per batch inference job for GLM 4.7 Flash | Each supporte +Records per input file per batch inference job for GLM 5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-8A232422) | The maximum number of records in an input file in a batch inference job for GLM 5. @@ -1223,0 +1242 @@ Records per input file per batch inference job for MiniMax M2.1 | Each supported +Records per input file per batch inference job for MiniMax M2.5 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-BC9ED53F) | The maximum number of records in an input file in a batch inference job for MiniMax M2.5. @@ -1229,0 +1249 @@ Records per input file per batch inference job for Mistral Small | Each supporte +Records per input file per batch inference job for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-69AC41C2) | The maximum number of records in an input file in a batch inference job for NVIDIA Nemotron 3 Super 120B A12B. @@ -1233,4 +1253,4 @@ Records per input file per batch inference job for NVIDIA Nemotron Nano 9B | Eac -Records per input file per batch inference job for Nova 2 Lite | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4A832410) | The maximum number of records in an input file in a batch inference job for Nova 2 Lite. -Records per input file per batch inference job for Nova Lite V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B8626674) | The maximum number of records in an input file in a batch inference job for Nova Lite V1. -Records per input file per batch inference job for Nova Micro V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D56DF585) | The maximum number of records in an input file in a batch inference job for Nova Micro V1. -Records per input file per batch inference job for Nova Pro V1 | Each supported Region: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9B651738) | The maximum number of records in an input file in a batch inference job for Nova Pro V1. +Records per input file per batch inference job for Nova 2 Lite | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-4A832410) | The maximum number of records in an input file in a batch inference job for Nova 2 Lite. +Records per input file per batch inference job for Nova Lite V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B8626674) | The maximum number of records in an input file in a batch inference job for Nova Lite V1. +Records per input file per batch inference job for Nova Micro V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-D56DF585) | The maximum number of records in an input file in a batch inference job for Nova Micro V1. +Records per input file per batch inference job for Nova Pro V1 | me-central-1: 50,000 Each of the other supported Regions: 100,000 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-9B651738) | The maximum number of records in an input file in a batch inference job for Nova Pro V1. @@ -1261,5 +1281,5 @@ 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 Haiku 4.5 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-63020993) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Haiku 4.5. -Sum of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.5 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E83AC604) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.5. -Sum of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.6 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B0F56DCF) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.6. -Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4 | Each supported Region: 100 | [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. -Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4.5. | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-A0300844) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4.5. +Sum of in-progress and submitted batch inference jobs using a base model for Claude Haiku 4.5 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-63020993) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Haiku 4.5. +Sum of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.5 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E83AC604) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.5. +Sum of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.6 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B0F56DCF) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Opus 4.6. +Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4 | me-central-1: 20 Each of the other supported Regions: 100 | [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. +Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4.5. | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-A0300844) | The maximum number of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4.5. @@ -1271,0 +1292 @@ Sum of in-progress and submitted batch inference jobs using a base model for GLM +Sum of in-progress and submitted batch inference jobs using a base model for GLM 5 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-5BA88337) | The maximum number of in-progress and submitted batch inference jobs using a base model for GLM 5. @@ -1289,0 +1311 @@ Sum of in-progress and submitted batch inference jobs using a base model for Min +Sum of in-progress and submitted batch inference jobs using a base model for MiniMax M2.5 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-B49AA29C) | The maximum number of in-progress and submitted batch inference jobs using a base model for MiniMax M2.5. @@ -1295,0 +1318 @@ Sum of in-progress and submitted batch inference jobs using a base model for Mis +Sum of in-progress and submitted batch inference jobs using a base model for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-6D88F00E) | The maximum number of in-progress and submitted batch inference jobs using a base model for NVIDIA Nemotron 3 Super 120B A12B. @@ -1299,4 +1322,4 @@ Sum of in-progress and submitted batch inference jobs using a base model for NVI -Sum of in-progress and submitted batch inference jobs using a base model for Nova 2 Lite | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-10F69CA1) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova 2 Lite. -Sum of in-progress and submitted batch inference jobs using a base model for Nova Lite V1 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E2ED42E6) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Lite V1. -Sum of in-progress and submitted batch inference jobs using a base model for Nova Micro V1 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-564C017C) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Micro V1. -Sum of in-progress and submitted batch inference jobs using a base model for Nova Pro V1 | Each supported Region: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FE130012) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Pro V1. +Sum of in-progress and submitted batch inference jobs using a base model for Nova 2 Lite | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-10F69CA1) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova 2 Lite. +Sum of in-progress and submitted batch inference jobs using a base model for Nova Lite V1 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-E2ED42E6) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Lite V1. +Sum of in-progress and submitted batch inference jobs using a base model for Nova Micro V1 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-564C017C) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Micro V1. +Sum of in-progress and submitted batch inference jobs using a base model for Nova Pro V1 | me-central-1: 20 Each of the other supported Regions: 100 | [Yes](https://console.aws.amazon.com/servicequotas/home/services/bedrock/quotas/L-FE130012) | The maximum number of in-progress and submitted batch inference jobs using a base model for Nova Pro V1.