AWS Amazon Bedrock Service Limits

Minimum number of records per batch inference job for GLM 4.7 Flash

On-demand model inference tokens per minute for Amazon Titan Image Generator G1

Records per batch inference job for Claude Opus 4.5

On-demand model inference requests per minute for Mistral Large 3

(Model customization) Custom models per account

Cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1

On-demand model inference tokens per minute for Mistral Large 3

On-demand model inference tokens per minute for Cohere Command R Plus

On-demand model inference requests per minute for Meta Llama 2 Chat 70B

Model invocation max tokens per day for Nemotron Nano 3 30B (doubled for cross-region calls)

(Model customization) Sum of training and validation records for a Claude 3-5-Haiku v1 Fine-tuning job

Batch inference job size (in GB) for Gemma 3 12B

Model invocation max tokens per day for Z.ai GLM-4.7 (doubled for cross-region calls)

Batch inference job size (in GB) for Claude Sonnet 4.5

Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4.6

(Model customization) Total number of custom model deployments

ListAgentVersions requests per second

Records per batch inference job for Llama 3.1 405B Instruct

Cross-region model inference requests per minute for Anthropic Claude Haiku 4.5

On-demand model inference tokens per minute for Amazon Titan Text Express

Cross-region model inference requests per minute for Amazon Nova Lite

Model units per provisioned model for Anthropic Claude 3 Haiku 200K

Model invocation max tokens per day for Gemma 3 4B (doubled for cross-region calls)

Sum of in-progress and submitted batch inference jobs using a base model for Claude 3.7 Sonnet

DisassociateAgentKnowledgeBase requests per second

Records per batch inference job for Llama 3.2 1B Instruct

(Flows) Conditions per condition node

Cross-region model inference requests per minute for Anthropic Claude 3.7 Sonnet V1

On-demand model inference requests per minute for AI21 Labs Jamba Instruct

Batch inference input file size (in GB) for OpenAI GPT OSS 20b

Model units no-commitment Provisioned Throughputs across base models

Batch inference job size (in GB) for OpenAI GPT OSS 120b

Records per input file per batch inference job for Nova 2 Lite

Sum of in-progress and submitted batch inference jobs using a base model for Magistral Small 2509

Global cross-region model inference tokens per day for Amazon Nova 2 Pro Preview

(Flows) DeleteFlowVersion requests per second

(Advanced Prompt Optimization) Active jobs per account

Sum of in-progress and submitted batch inference jobs using a base model for Llama 3.1 405B Instruct

Batch inference input file size (in GB) for Claude 3.5 Sonnet v2

On-demand model inference requests per minute for NVIDIA Nemotron Nano 2

Batch inference input file size (in GB) for Claude Sonnet 4

Records per input file per batch inference job for Llama 4 Maverick

(Data Automation) Maximum number of Blueprints per Start Inference request (Audios)

Cross-region model inference tokens per minute for Meta Llama 4 Maverick V1

Minimum number of records per batch inference job for Claude 3 Opus

Throttle rate limit for GetDataAutomationProject

Batch inference input file size (in GB) for Llama 3.1 8B Instruct

(Model customization) Sum of training and validation records for a Claude 3 Haiku v1 Fine-tuning job

Global cross-region model inference requests per minute for Amazon Nova 2 Lite

Batch inference job size (in GB) for OpenAI GPT OSS Safeguard 20b

On-demand model inference tokens per minute for Amazon Titan Text Premier

Batch inference job size (in GB) for Llama 4 Maverick

Model invocation max tokens per day for Minimax M2 (doubled for cross-region calls)

Cross-region model inference tokens per minute for Anthropic Claude Opus 4.7

On-demand model inference requests per minute for GPT OSS Safeguard 20B

Batch inference job size (in GB) for Llama 3.2 3B Instruct

Records per input file per batch inference job for Qwen3 Coder Next

On-demand model inference requests per minute for Meta Llama 3 8B Instruct

On-demand model inference requests per minute for Minimax M2

On-demand model inference requests per minute for DeepSeek V3.2

(Knowledge Bases) RetrieveAndGenerate requests per second

Records per input file per batch inference job for Llama 3.2 90B Instruct

Batch inference job size (in GB) for Llama 3.1 8B Instruct

On-demand model inference requests per minute for AI21 Labs Jamba 1.5 Large

Model invocation max tokens per day for Ministral 3B 3.0 (doubled for cross-region calls)

(Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Micro

Characters in Agent instructions

Sum of in-progress and submitted batch inference jobs using a base model for DeepSeek V3.2

Cross-region model inference requests per minute for Anthropic Claude Opus 4 V1

Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length

Minimum number of records per batch inference job for Ministral 3B

Model units per provisioned model for Amazon Titan Text Premier V1 32K

GetAgentActionGroup requests per second

Model invocation max tokens per day for Anthropic Claude Sonnet 4.5 V1 1M Context Length (doubled for cross-region calls)

Global cross-region model inference tokens per day for Anthropic Claude Haiku 4.5

Custom models with a creating status per account

Minimum number of records per batch inference job for Claude Sonnet 4.6

Model invocation max tokens per day for Voxtral Mini 1.0 (doubled for cross-region calls)

Batch inference job size (in GB) for Ministral 3 8B

Model invocation max tokens per day for Amazon Nova Pro (doubled for cross-region calls)

On-demand model inference tokens per minute for Cohere Embed English

Model invocation max tokens per day for Anthropic Claude Opus 4.5 (doubled for cross-region calls)

Global cross-region model inference tokens per day for Anthropic Claude Opus 4.6 V1

On-demand InvokeModel concurrent requests for Amazon Nova Reel1.0

Model units per provisioned model for Amazon Titan Text Embeddings V2

On-demand model inference tokens per minute for Meta Llama 3.2 3B Instruct

Model units per provisioned model for the 300k context length variant for Amazon Nova Lite

Batch inference input file size (in GB) for Claude Opus 4.5

On-demand model inference tokens per minute for Z.ai GLM-4.7

Batch inference input file size (in GB) for Titan Text Embeddings V2

(Data Automation) InvokeDataAutomationAsync - Audio - Max number of concurrent jobs

Batch inference job size (in GB) for Nova Pro V1

Batch inference input file size (in GB) for Claude 3 Opus

Batch inference input file size (in GB) for Mistral Large 2 (24.07)

(Knowledge Bases) ListKnowledgeBases requests per second

(Model customization) Minimum number of prompts for distillation customization jobs

(Automated Reasoning) ListAutomatedReasoningPolicyBuildWorkflows requests per second

Model invocation max tokens per day for Z.ai GLM-4.7 Flash (doubled for cross-region calls)

Records per input file per batch inference job for OpenAI GPT OSS Safeguard 120b

Records per batch inference job for Nova Lite V1

Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4 V1

Records per input file per batch inference job for Claude Sonnet 4

On-demand model inference requests per minute for Anthropic Claude 3 Opus

On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet

(Knowledge Bases) DeleteKnowledgeBase requests per second

Cross-region model inference tokens per minute for Amazon Nova Micro

(Evaluation) Number of prompts in a custom prompt dataset

On-demand model inference requests per minute for Amazon Titan Text Lite

Records per batch inference job for Qwen3 Next 80B

On-demand model inference requests per minute for Stable Image Creative Upscale

Batch inference input file size (in GB) for Ministral 3 8B

On-demand model inference requests per minute for NVIDIA Nemotron 3 Super 120B A12B

(Flows) GetFlow requests per second

Batch inference job size (in GB) for Amazon Nova Premier

Batch inference job size (in GB) for Llama 3.2 11B Instruct

Model invocation max tokens per day for GPT OSS Safeguard 20B (doubled for cross-region calls)

Sum of in-progress and submitted batch inference jobs using a base model for Llama 3.2 3B Instruct

Batch inference job size (in GB) for GLM 4.7 Flash

(Model customization) Sum of training and validation records for a Titan Multimodal Embeddings G1 v1 Fine-tuning job

Enabled action groups per agent

Records per batch inference job for Writer Palmyra Vision 7B

Sum of in-progress and submitted batch inference jobs using a base model for Llama 4 Scout

(Evaluation) Number of models in a model evaluation job that uses human workers

Cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length

Model units per provisioned model for Meta Llama 3 70B Instruct

(Flows) DeleteFlow requests per second

Records per input file per batch inference job for GLM 5

On-demand model inference tokens per minute for Z.ai GLM 5

(Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Lite

Minimum number of records per batch inference job for OpenAI GPT OSS Safeguard 120b

Batch inference input file size (in GB) for NVIDIA Nemotron Nano 12B

Batch inference job size (in GB) for Writer Palmyra Vision 7B

(Knowledge Bases) Maximum number of files for Foundation Models as a parser

(Knowledge Bases) Concurrent IngestKnowledgeBaseDocuments and DeleteKnowledgeBaseDocuments requests per account

On-demand model inference tokens per minute for AI21 Labs Jurassic-2 Ultra

Model invocation max tokens per day for NVIDIA Nemotron Nano 2 (doubled for cross-region calls)

Cross-region model inference tokens per minute for Meta Llama 3.1 70B Instruct

Sum of in-progress and submitted batch inference jobs using a base model for GLM 4.7 Flash

Batch inference job size (in GB) for Mistral Large 3

Sum of in-progress and submitted batch inference jobs using a base model for Llama 4 Maverick

Model invocation max tokens per day for Mistral AI Mistral Small (doubled for cross-region calls)

Sum of in-progress and submitted batch inference jobs using a custom model for Titan Multimodal Embeddings G1

Cross-region model inference requests per minute for Anthropic Claude Opus 4.5

Cross-region model inference requests per minute for Mistral Pixtral Large 25.02 V1

Batch inference job size (in GB) for NVIDIA Nemotron Nano 3 30B

Model units per provisioned model for Anthropic Claude 3.5 Sonnet 200K

Model units per provisioned model for Amazon Nova 2 Lite V1.0 256K

Model units per provisioned model for Anthropic Claude V2 100K

(Model customization) Sum of on demand custom model deployment tokens per minute for Amazon Nova Micro

(Automated Reasoning) GetAutomatedReasoningPolicyTestResult requests per second

On-demand model inference requests per minute for Anthropic Claude 3.5 Haiku

Cross-region model inference tokens per minute for Meta Llama 3.2 1B Instruct

Records per input file per batch inference job for GLM 4.7

Sum of in-progress and submitted batch inference jobs using a base model for Voxtral Small 24B 2507

On-demand model inference requests per minute for Amazon Titan Text Embeddings

(Flows) Agent nodes per flow

(Knowledge Bases) Data sources per knowledge base

On-demand model inference requests per minute for Meta Llama 3.1 70B Instruct

(Automated Reasoning) GetAutomatedReasoningPolicy requests per second

Model units per provisioned model for Anthropic Claude 3.5 Haiku 16K

(Automated Reasoning) ExportAutomatedReasoningPolicyVersion requests per second

Model invocation max tokens per day for NVIDIA Nemotron Nano 2 VL (doubled for cross-region calls)

Cross-region model inference tokens per minute for Anthropic Claude Opus 4.5

Global cross-region model inference tokens per day for Cohere Embed V4

Records per batch inference job for GLM 5

On-demand model inference requests per minute for Ministral 3B 3.0

Cross-Region model inference tokens per minute for Anthropic Claude 3.5 Sonnet V2

Sum of in-progress and submitted batch inference jobs using a base model for Nova Lite V1

Cross-region model inference requests per minute for Stable Image Fast Upscale

Batch inference input file size (in GB) for Magistral Small 2509

On-demand model inference requests per minute for Stable Image Control Sketch

Records per batch inference job for Claude 3.5 Sonnet

Global cross-region model inference tokens per minute for Amazon Nova 2 Omni

On-demand model inference tokens per minute for Amazon Nova Micro

Sum of in-progress and submitted batch inference jobs using a base model for Qwen3 Next 80B

Sum of in-progress and submitted batch inference jobs using a base model for NVIDIA Nemotron Nano 9B

On-demand InvokeModel concurrent requests for Amazon Nova 2 Sonic

On-demand model inference tokens per minute for AI21 Labs Jamba Instruct

Sum of in-progress and submitted batch inference jobs using a base model for Qwen3 Coder Next

Cross-region model inference requests per minute for Stable Image Search and Recolor

On-demand model inference requests per minute for Amazon Nova Canvas

Model invocation max tokens per day for Amazon Nova 2 Pro Preview (doubled for cross-region calls)

On-demand model inference requests per minute for Amazon Titan Text Premier

Minimum number of records per batch inference job for Llama 3.3 70B Instruct

Records per input file per batch inference job for Nova Pro V1

Sum of in-progress and submitted batch inference jobs using a base model for Mistral Small

(Knowledge Bases) GetKnowledgeBase requests per second

Records per input file per batch inference job for Qwen3 Coder 30B

Batch inference input file size (in GB) for Amazon Nova 2 Multimodal Embeddings V1

Cross-region model inference tokens per minute for Amazon Nova 2 Pro Preview

Model units per provisioned model for Anthropic Claude 3.5 Sonnet 18K

Records per batch inference job for Gemma 3 4B

Minimum number of records per batch inference job for Nova 2 Lite

Minimum number of records per batch inference job for GLM 4.7

On-demand model inference tokens per minute for Minimax M2.1

Records per input file per batch inference job for Llama 3.1 405B Instruct

Sum of in-progress and submitted batch inference jobs using a base model for Titan Text Embeddings V2

(Guardrails) On-demand ApplyGuardrail Content filter policy text units per second

Model invocation max tokens per day for Meta Llama 3.2 1B Instruct (doubled for cross-region calls)

Records per input file per batch inference job for Mistral Large 2 (24.07)

Batch inference input file size (in GB) for Gemma 3 27B

Records per input file per batch inference job for Voxtral Small 24B 2507

Records per input file per batch inference job for Ministral 3 14B

(Knowledge Bases) GetIngestionJob requests per second

Model invocation max tokens per day for Meta Llama 4 Maverick V1 (doubled for cross-region calls)

(Prompt management) ListPrompts requests per second

On-demand model inference requests per minute for OpenAI GPT OSS 20B

Batch inference job size (in GB) for Mistral Small

Sum of in-progress and submitted batch inference jobs using a custom model for Titan Text Embeddings V2

Batch inference input file size (in GB) for Voxtral Mini 3B 2507

On-demand model inference requests per minute for Minimax M2.1

(Model customization) Sum of training and validation records for a Titan Text G1 - Lite v1 Continued Pre-Training job

Batch inference job size (in GB) for Ministral 3B

Cross-region model inference requests per minute for Twelve Labs Pegasus

On-demand model inference requests per minute for Kimi K2 Thinking

(Model customization) Maximum student model fine tuning context length for Amazon Nova V1 distillation customization jobs

Cross-region model inference tokens per minute for Anthropic Claude Haiku 4.5

Records per input file per batch inference job for OpenAI GPT OSS Safeguard 20b

Model invocation max tokens per day for Anthropic Claude Opus 4.6 V1 (doubled for cross-region calls)

(Data Automation) InvokeDataAutomationAsync - Document - Max number of concurrent jobs

(Data Automation) Maximum number of Blueprints per Start Inference request (Documents)

On-demand model inference requests per minute for Magistral Small 1.2

Batch inference input file size (in GB) for Qwen3 Coder 30B

Records per batch inference job for MiniMax M2.5

(Automated Reasoning) Annotations in policy

Minimum number of records per batch inference job for Llama 3.2 3B Instruct

Records per batch inference job for Qwen3 32B

(Flows) ListFlowAliases requests per second

Cross-region model inference tokens per minute for Amazon Nova Premier V1

(Guardrails) Word length in characters

Records per input file per batch inference job for Kimi K2 Thinking

On-demand model inference tokens per minute for Amazon Titan Text Embeddings

Records per batch inference job for MiniMax M2

Global cross-region model inference tokens per minute for Anthropic Claude Haiku 4.5

Batch inference input file size (in GB) for Ministral 3 14B

Minimum number of records per batch inference job for Ministral 3 8B

Cross-region model inference requests per minute for Anthropic Claude 3.5 Sonnet

(Flows) ListFlowVersions requests per second

Model units per provisioned model for Anthropic Claude V2.1 200K

(Knowledge Bases) GetKnowledgeBaseDocuments requests per second

Batch inference input file size (in GB) for Claude 3 Sonnet

Records per input file per batch inference job for Claude 3.5 Sonnet v2

Sum of in-progress and submitted batch inference jobs using a base model for Voxtral Mini 3B 2507

Cross-region model inference requests per minute for Anthropic Claude 3 Opus

Throttle rate limit for UpdateBlueprint

On-Demand, latency-optimized model inference tokens per minute for Amazon Nova Pro V1

On-demand model inference tokens per minute for Qwen3 Next 80B A3B

Global cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.5 V1 1M Context Length

Batch inference job size (in GB) for Claude 3 Opus

(Automated Reasoning) Source document size (MB)

Records per input file per batch inference job for Kimi K2.5

Records per input file per batch inference job for Magistral Small 2509

(Data Automation) Maximum audio length (Minutes)

(Data Automation) InvokeBlueprintOptimizationAsync - Max number of blueprint optimization jobs per day

On-demand model inference tokens per minute for Cohere Command R

On-demand model inference tokens per minute for Writer Palmyra Vision 7B

Model invocation max tokens per day for Amazon Nova 2 Lite (doubled for cross-region calls)

Records per batch inference job for MiniMax M2.1

Records per batch inference job for Nova Micro V1

Records per batch inference job for Llama 3.1 8B Instruct

(Evaluation) Number of concurrent automatic model evaluation jobs

On-demand model inference requests per minute for Mistral AI Mistral Small

(Prompt management) CreatePromptVersion requests per second

(Prompt management) Versions per prompt

Concurrent model import jobs

Global cross-region model inference requests per minute for Cohere Embed V4

Records per batch inference job for GLM 4.7 Flash

(Model customization) Scheduled customization jobs

Model invocation max tokens per day for MiniMax M2.5 (doubled for cross-region calls)

(Knowledge Bases) UpdateDataSource requests per second

(Model customization) Maximum number of prompts for distillation customization jobs

Cross-region model inference requests per minute for Stable Image Outpaint

Records per batch inference job for Claude 3.7 Sonnet

Number of custom prompt routers per account

Batch inference input file size (in GB) for Claude Haiku 4.5

On-demand model inference tokens per minute for Meta Llama 3.1 70B Instruct

On-demand model inference requests per minute for Stable Image Search and Recolor

On-demand model inference tokens per minute for Z.ai GLM-4.7 Flash

Minimum number of records per batch inference job for Llama 3.2 11B Instruct

(Model customization) Sum of training and validation records for a Amazon Nova Micro Fine-tuning job

Batch inference input file size (in GB) for Gemma 3 4B

(Data Automation) CreateBlueprintVersion - Max number of Blueprint versions per Blueprint

Sum of in-progress and submitted batch inference jobs using a base model for Claude 3 Haiku

Records per batch inference job for NVIDIA Nemotron Nano 9B

Model invocation max tokens per day for Mistral Devstral 2 123b (doubled for cross-region calls)

Batch inference input file size (in GB) for Devstral 2 123B

Records per batch inference job for Qwen3 VL 235B

Cross-region model inference tokens per minute for Mistral Pixtral Large 25.02 V1

(Data Automation) Maximum instruction field length for Audio Blueprint - (Characters)

Sum of in-progress and submitted batch inference jobs using a base model for Kimi K2 Thinking

Cross-region model inference requests per minute for Stable Image Style Transfer

Cross-Region model inference requests per minute for Anthropic Claude 3.5 Sonnet V2

Records per batch inference job for Claude Sonnet 4.5

Model invocation max tokens per day for Anthropic Claude 3.5 Haiku (doubled for cross-region calls)

Batch inference input file size (in GB) for Qwen3 VL 235B

Batch inference input file size (in GB) for Nova 2 Lite

Batch inference input file size (in GB) for Voxtral Small 24B 2507

(Knowledge Bases) Knowledge bases per account

(Automated Reasoning) GetAutomatedReasoningPolicyNextScenario requests per second

ListAgentAliases requests per second

Minimum number of records per batch inference job for Nova Pro V1

Records per input file per batch inference job for NVIDIA Nemotron Nano 3 30B

Batch inference job size (in GB) for Llama 3.3 70B Instruct

Records per input file per batch inference job for Llama 3.2 1B Instruct

Global cross-region model inference tokens per day for Anthropic Claude Sonnet 4.5 V1

Records per input file per batch inference job for Claude 3.5 Sonnet

Cross-region model inference requests per minute for Anthropic Claude Sonnet 4 V1

Global cross-region model inference requests per minute for Anthropic Claude Sonnet 4 V1

Cross-region model inference tokens per minute for Anthropic Claude Opus 4.1

Minimum number of records per batch inference job for Llama 4 Maverick

Records per input file per batch inference job for Claude 3.5 Haiku

(Knowledge Bases) Concurrent ingestion jobs per account

(Guardrails) Words per word policy

Sum of in-progress and submitted batch inference jobs using a base model for Nova Pro V1

Model units per provisioned model for Amazon Titan Image Generator G2

Batch inference job size (in GB) for Mistral Large 2 (24.07)

Model units per provisioned model for AI21 Labs Jurassic-2 Ultra

Model invocation max tokens per day for Mistral AI Mistral 7B Instruct (doubled for cross-region calls)

Records per batch inference job for Claude 3 Haiku

(Model customization) Maximum input file size for distillation customization jobs

(Evaluation) Number of evaluation jobs

Sum of in-progress and submitted batch inference jobs using a base model for Claude 3.5 Sonnet v2

On-demand model inference tokens per minute for Meta Llama 2 Chat 70B

Records per input file per batch inference job for Titan Multimodal Embeddings G1

PrepareAgent requests per second

Cross-region model inference requests per minute for Meta Llama 4 Maverick V1

On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet

On-demand model inference requests per minute for Moonshot AI Kimi K2.5

Throttle rate limit for CreateDataAutomationProject

(Data Automation) InvokeDataAutomationAsync - Max number of open jobs

Model units, with commitment, for Provisioned Throughout created for Meta Maverick 4 Scout 17B Instruct 1M

Records per batch inference job for Kimi K2.5

Cross-region model inference requests per minute for Amazon Nova Premier V1

Model units per provisioned model for Meta Llama 3 8B Instruct

Records per batch inference job for Llama 3.2 11B Instruct

On-demand model inference tokens per minute for Meta Llama 3 8B Instruct

Batch inference job size (in GB) for Llama 3.1 405B Instruct

Minimum number of records per batch inference job for Gemma 3 4B

Throttle rate limit for ListDataAutomationProjects

(Flows) UpdateFlowAlias requests per second

Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4 V1 1M Context Length

(Model customization) Maximum number of training records for an Amazon Nova Canvas Fine-tuning job

(Model customization) Sum of training and validation records for a Meta Llama 2 70B v1 Fine-tuning job

On-demand model inference tokens per minute for MiniMax M2.5

On-demand model inference requests per minute for Stable Image Conservative Upscale

Batch inference job size (in GB) for NVIDIA Nemotron Nano 12B

Records per input file per batch inference job for Qwen3 VL 235B

Records per batch inference job for Nova 2 Lite

Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4 V1

Model units per provisioned model for Anthropic Claude 3.5 Haiku 64K

Minimum number of records per batch inference job for Claude Opus 4.6

GetAgent requests per second

Records per batch inference job for DeepSeek V3.2

ListAgents requests per second

Batch inference input file size (in GB) for Llama 3.2 3B Instruct

(Data Automation) Minimum Audio Sample Rate (Hz)

Model invocation max tokens per day for Amazon Nova Premier V1 (doubled for cross-region calls)

On-demand latency-optimized model inference requests per minute for Anthropic Claude 3.5 Haiku

Model units per provisioned model for Anthropic Claude V2 18K

Records per batch inference job for Qwen3 Coder Next

Records per batch inference job for Kimi K2 Thinking

(Model customization) Sum of training and validation records for a Meta Llama 2 13B v1 Fine-tuning job

Model invocation max tokens per day for AI21 Labs Jamba 1.5 Mini (doubled for cross-region calls)

Batch inference input file size (in GB) for Claude 3.5 Sonnet

Batch inference job size (in GB) for MiniMax M2.1

Cross-region model inference requests per minute for Meta Llama 4 Scout V1

Cross-region model inference requests per minute for Anthropic Claude Opus 4.1

(Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Pro

Minimum number of records per batch inference job for GLM 5

On-demand latency-optimized model inference tokens per minute for Anthropic Claude 3.5 Haiku

On-demand InvokeModel concurrent requests for Twelve Labs Marengo

Batch inference job size (in GB) for Qwen3 Next 80B

Batch inference input file size (in GB) for Mistral Small

On-demand model inference requests per minute for Amazon Nova Pro

Records per batch inference job for Llama 3.3 70B Instruct

On-demand model inference requests per minute for Anthropic Claude 3.5 Sonnet V2

Sum of in-progress and submitted batch inference jobs using a base model for Amazon Nova 2 Multimodal Embeddings V1

Records per input file per batch inference job for Mistral Large 3

Records per input file per batch inference job for DeepSeek V3.2

Model invocation max tokens per day for Mistral AI Mixtral 8X7B Instruct (doubled for cross-region calls)

Batch inference job size (in GB) for Claude 3.5 Sonnet

Records per input file per batch inference job for Amazon Nova Premier

Model invocation max tokens per day for Anthropic Claude Haiku 4.5 (doubled for cross-region calls)

(Guardrails) Automated Reasoning policies per guardrail

Global cross-region model inference tokens per minute for Anthropic Claude Opus 4.6 V1

Minimum number of records per batch inference job for Devstral 2 123B

Records per input file per batch inference job for Claude 3 Sonnet

UpdateAgent requests per second

(Guardrails) On-demand ApplyGuardrail Denied topic policy text units per second (standard)

(Data Automation) InvokeDataAutomation(Sync) - Image - Max number of requests

(Flows) ListFlows requests per second

Model invocation max tokens per day for Meta Llama 3.2 90B Instruct (doubled for cross-region calls)

On-demand model inference requests per minute for AI21 Labs Jamba 1.5 Mini

Cross-region model inference requests per minute for Meta Llama 3.3 70B Instruct

Batch inference input file size (in GB) for Titan Multimodal Embeddings G1

(Advanced Prompt Optimization) Inactive jobs per account

(Automated Reasoning) UpdateAutomatedReasoningPolicyAnnotations requests per second

Associated knowledge bases per Agent

(Automated Reasoning) StartAutomatedReasoningPolicyTestWorkflow requests per second

(Guardrails) Contextual grounding response length in text units

Minimum number of records per batch inference job for Nova Micro V1

Cross-region model inference tokens per minute for Anthropic Claude 3.7 Sonnet V1

Batch inference job size (in GB) for NVIDIA Nemotron 3 Super 120B A12B

Cross-region model inference requests per minute for Anthropic Claude Sonnet 4.5 V1

On-demand model inference requests per minute for Amazon Titan Text Embeddings V2

(Knowledge Bases) GetDataSource requests per second

(Model customization) Sum of training and validation records for a Titan Image Generator G1 V2 Fine-tuning job

Sum of in-progress and submitted batch inference jobs using a base model for Nova 2 Lite

(Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova 2 Lite

Minimum number of records per batch inference job for Qwen3 32B

(Model customization) Sum of training and validation records for a Amazon Nova Pro Fine-tuning job

Records per batch inference job for Claude Sonnet 4

Sum of in-progress and submitted batch inference jobs using a base model for Claude 3 Opus

(Automated Reasoning) GetAutomatedReasoningPolicyAnnotations requests per second

On-demand model inference tokens per minute for OpenAI GPT OSS 120B

Batch inference input file size (in GB) for DeepSeek V3.2

Model invocation max tokens per day for Gemma 3 27B (doubled for cross-region calls)

Minimum number of records per batch inference job for Claude 3 Sonnet

Cross-region model inference requests per minute for Stable Image Creative Upscale

Minimum number of records per batch inference job for NVIDIA Nemotron Nano 3 30B

Sum of in-progress and submitted batch inference jobs using a base model for NVIDIA Nemotron 3 Super 120B A12B

Model units per provisioned model for the 24k context length variant for Amazon Nova Pro

(Automated Reasoning) Concurrent policy builds per account

Minimum number of records per batch inference job for Claude 3.7 Sonnet

(Guardrails) Regex length in characters

Model invocation max tokens per day for Ministral 8B 3.0 (doubled for cross-region calls)

Batch inference input file size (in GB) for Claude Sonnet 4.6

Records per input file per batch inference job for NVIDIA Nemotron 3 Super 120B A12B

On-demand model inference requests per minute for Gemma 3 27B

(Flows) Inline code nodes per flow

Batch inference job size (in GB) for Qwen3 32B

Batch inference input file size (in GB) for Qwen3 Next 80B

(Flows) S3 storage nodes per flow

Sum of in-progress and submitted batch inference jobs using a base model for Amazon Nova Premier

Batch inference job size (in GB) for Llama 3.2 90B Instruct

(Model customization) Sum of training and validation records for a Titan Text G1 - Express v1 Continued Pre-Training job

Records per batch inference job for NVIDIA Nemotron Nano 3 30B

Records per batch inference job for NVIDIA Nemotron Nano 12B

On-demand model inference requests per minute for Meta Llama 3.2 90B Instruct

Minimum number of records per batch inference job for Claude Sonnet 4.5.

Batch inference job size (in GB) for Kimi K2 Thinking

Model invocation max tokens per day for AI21 Labs Jamba 1.5 Large (doubled for cross-region calls)

On-demand model inference tokens per minute for Ministral 8B 3.0

Batch inference input file size (in GB) for Claude 3.5 Haiku

Minimum number of records per batch inference job for Nova Lite V1

On-demand model inference requests per minute for Qwen3 32B V1

Minimum number of records per batch inference job for Qwen3 Coder Next

(Automated Reasoning) CreateAutomatedReasoningPolicy requests per second

On-demand model inference tokens per minute for AI21 Labs Jamba 1.5 Large

Records per batch inference job for Qwen3 Coder 30B

Model units per provisioned model for Anthropic Claude 3 Sonnet 28K

(Knowledge Bases) DeleteKnowledgeBaseDocuments requests per second

Model units, with commitment, for Provisioned Throughout created for Meta Maverick 4 Scout 17B Instruct 128K

Model invocation max tokens per day for Anthropic Claude Sonnet 4 V1 1M Context Length (doubled for cross-region calls)

Throttle rate limit for Bedrock Data Automation: ListTagsForResource

Model units per provisioned model for Meta Llama 2 Chat 70B

Throttle rate limit for Bedrock Data Automation: UntagResource

Records per input file per batch inference job for Claude Haiku 4.5

(Flows) Flow versions per flow

On-demand model inference requests per minute for Nemotron Nano 3 30B

On-demand model inference tokens per minute for Anthropic Claude 3 Sonnet

(Data Automation) Maximum Blueprints per Project (Videos)

On-demand model inference tokens per minute for Amazon Nova Lite

(Data Automation) Maximum JSON Blueprint Size (Characters)

Sum of in-progress and submitted batch inference jobs using a base model for OpenAI GPT OSS 20b

On-demand model inference requests per minute for Meta Llama 3 70B Instruct

Records per batch inference job for Gemma 3 27B

Sum of in-progress and submitted batch inference jobs using a base model for Devstral 2 123B

Minimum number of records per batch inference job for MiniMax M2

Minimum number of records per batch inference job for OpenAI GPT OSS 120b

(Model customization) In-progress custom model deployments

Model units per provisioned model for Stability.ai Stable Diffusion XL 0.8

On-demand model inference tokens per minute for Meta Llama 3 70B Instruct

Global cross-region model inference tokens per minute for Anthropic Claude Opus 4.7

(Knowledge Bases) ListKnowledgeBaseDocuments requests per second

Batch inference job size (in GB) for Gemma 3 27B

(Model customization) Sum of on demand custom model deployment tokens per day for Amazon Nova 2 Lite

(Guardrails) On-demand ApplyGuardrail requests per second

Sum of in-progress and submitted batch inference jobs using a base model for MiniMax M2.1

Cross-region model inference tokens per minute for Anthropic Claude 3 Opus

Records per batch inference job for Claude Haiku 4.5

(Model customization) Sum of training and validation records for a Titan Text G1 - Lite v1 Fine-tuning job

(Automated Reasoning) Versions per policy

Cross-region model inference requests per minute for Meta Llama 3.2 1B Instruct

Model invocation max tokens per day for Z.ai GLM 5 (doubled for cross-region calls)

Batch inference input file size (in GB) for GLM 5

Minimum number of records per batch inference job for NVIDIA Nemotron 3 Super 120B A12B

On-demand model inference tokens per minute for Anthropic Claude 3.5 Sonnet V2

Model units per provisioned model for the 128k context length variant for Amazon Nova Micro

Model units per provisioned model for Stability.ai Stable Diffusion XL 1.0

On-Demand, latency-optimized model inference requests per minute for Meta Llama 3.1 70B Instruct

Sum of in-progress and submitted batch inference jobs using a base model for Nova Micro V1

Cross-region model inference tokens per minute for Anthropic Claude Sonnet 4.6

Throttle rate limit for CreateBlueprint

(Knowledge Bases) Ingestion job file size

(Automated Reasoning) StartAutomatedReasoningPolicyBuildWorkflow requests per second

On-demand model inference requests per minute for Meta Llama 2 Chat 13B

Records per input file per batch inference job for Ministral 3B

(Automated Reasoning) Source document tokens

Global cross-region model inference tokens per minute for Amazon Nova 2 Lite

On-demand model inference tokens per minute for Amazon Titan Multimodal Embeddings G1

On-demand model inference requests per minute for OpenAI GPT OSS 120B

On-demand model inference requests per minute for Stable Image Search and Replace

On-demand model inference requests per minute for Qwen3 Next 80B A3B

Batch inference job size (in GB) for Claude Haiku 4.5

Global cross-region model inference tokens per minute for Anthropic Claude Sonnet 4 V1

Sum of in-progress and submitted batch inference jobs using a base model for Ministral 3B

Records per input file per batch inference job for Nova Lite V1

Sum of in-progress and submitted batch inference jobs using a base model for Ministral 3 8B

Cross-region model inference requests per minute for Meta Llama 3.1 8B Instruct

Model invocation max tokens per day for Meta Llama 3.2 11B Instruct (doubled for cross-region calls)

Batch inference input file size (in GB) for Llama 3.2 1B Instruct

(Guardrails) Versions per guardrail

On-demand model inference requests per minute for Qwen3 VL 235B A22B

Cross-region model inference requests per minute for Meta Llama 3.2 3B Instruct

(Evaluation) Number of custom metrics

Records per input file per batch inference job for Qwen3 Next 80B

Cross-region model inference requests per minute for Stable Image Conservative Upscale

UpdateAgentKnowledgeBase requests per second

(Model customization) Maximum line length for distillation customization jobs

Cross-region model inference requests per minute for Anthropic Claude 3 Haiku

Sum of in-progress and submitted batch inference jobs using a base model for Claude Sonnet 4.6

Sum of in-progress and submitted batch inference jobs using a base model for Qwen3 Coder 30B

Records per batch inference job for Claude 3.5 Sonnet v2

(Knowledge Bases) Concurrent ingestion jobs per knowledge base

Cross-region model inference requests per minute for Cohere Embed V4

Batch inference job size (in GB) for Claude 3.7 Sonnet

Global cross-region model inference tokens per minute for Cohere Embed V4

On-demand model inference tokens per minute for Meta Llama 3.2 11B Instruct

On-demand model inference requests per minute for Mistral 7B Instruct

Records per input file per batch inference job for Voxtral Mini 3B 2507

Minimum number of records per batch inference job for Claude 3.5 Haiku

On-demand model inference requests per minute for AI21 Labs Jurassic-2 Mid

On-demand model inference requests per minute for Anthropic Claude 3 Sonnet

(Flows) DeleteFlowAlias requests per second

(Flows) Flow aliases per flow

(Knowledge Bases) Files to add or update per ingestion job

Records per input file per batch inference job for OpenAI GPT OSS 20b

Model invocation max tokens per day for Ministral 14B 3.0 (doubled for cross-region calls)