2.248.0

class BedrockFoundationModel 🔹

LanguageType name
.NETAmazon.CDK.AWS.Bedrock.Alpha.BedrockFoundationModel
Gogithub.com/aws/aws-cdk-go/awsbedrockalpha/v2#BedrockFoundationModel
Javasoftware.amazon.awscdk.services.bedrock.alpha.BedrockFoundationModel
Pythonaws_cdk.aws_bedrock_alpha.BedrockFoundationModel
TypeScript (source)@aws-cdk/aws-bedrock-alpha » BedrockFoundationModel

Implements IBedrockInvokable

Bedrock models.

If you need to use a model name that doesn't exist as a static member, you can instantiate a BedrockFoundationModel object, e.g: new BedrockFoundationModel('my-model').

Example

const parserFunction = new lambda.Function(this, 'ParserFunction', {
  runtime: lambda.Runtime.PYTHON_3_10,
  handler: 'index.handler',
  code: lambda.Code.fromAsset('lambda'),
});

const agent = new bedrock.Agent(this, 'Agent', {
  foundationModel: bedrock.BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
  instruction: 'You are a helpful assistant.',
  promptOverrideConfiguration: bedrock.PromptOverrideConfiguration.withCustomParser({
    parser: parserFunction,
    preProcessingStep: {
      stepType: bedrock.AgentStepType.PRE_PROCESSING,
      useCustomParser: true
    }
  })
});

Initializer

new BedrockFoundationModel(value: string, props?: BedrockFoundationModelProps)

Parameters

Properties

NameTypeDescription
invokableArn🔹stringThe ARN used for invoking the model.
modelArn🔹stringThe ARN of the foundation model.
modelId🔹stringThe unique identifier of the foundation model.
supportsAgents🔹booleanWhether this model supports integration with Bedrock Agents.
supportsCrossRegion🔹booleanWhether this model supports cross-region inference.
supportsKnowledgeBase🔹booleanWhether this model supports integration with Bedrock Knowledge Base.
supportedVectorType?🔹VectorType[]The vector types supported by this model for embeddings.
vectorDimensions?🔹numberThe dimensionality of the vector embeddings produced by this model.
static AI21_JAMBA_1_5_LARGE_V1🔹BedrockFoundationModelAI21's Jamba 1.5 Large model optimized for text generation tasks. Suitable for complex language understanding and generation tasks.
static AI21_JAMBA_1_5_MINI_V1🔹BedrockFoundationModelAI21's Jamba 1.5 Mini model, a lighter version optimized for faster processing. Balances performance with efficiency for general text tasks.
static AI21_JAMBA_INSTRUCT_V1🔹BedrockFoundationModelAI21's Jamba Instruct model, specifically designed for instruction-following tasks. Optimized for understanding and executing specific instructions.
static AMAZON_NOVA_LITE_V1🔹BedrockFoundationModelAmazon's Nova Lite model, balancing performance with efficiency.
static AMAZON_NOVA_MICRO_V1🔹BedrockFoundationModelAmazon's Nova Micro model, a lightweight model optimized for efficiency.
static AMAZON_NOVA_PREMIER_V1🔹BedrockFoundationModelAmazon's Nova Premier model, the most advanced in the Nova series.
static AMAZON_NOVA_PRO_V1🔹BedrockFoundationModelAmazon's Nova Pro model, offering advanced capabilities for complex tasks.
static AMAZON_TITAN_PREMIER_V1_0🔹BedrockFoundationModelAmazon's Titan Text Premier model, designed for high-quality text generation. Offers enhanced capabilities for complex language tasks.
static AMAZON_TITAN_TEXT_EXPRESS_V1🔹BedrockFoundationModelAmazon's Titan Text Express model, optimized for fast text generation. Provides quick responses while maintaining good quality output.
static ANTHROPIC_CLAUDE_3_5_HAIKU_V1_0🔹BedrockFoundationModelAnthropic's Claude 3.5 Haiku model, optimized for quick responses. Lightweight model focused on speed and efficiency.
static ANTHROPIC_CLAUDE_3_5_SONNET_V1_0🔹BedrockFoundationModelAnthropic's Claude 3.5 Sonnet V1 model, balanced performance model. Offers good balance between performance and efficiency.
static ANTHROPIC_CLAUDE_3_5_SONNET_V2_0🔹BedrockFoundationModelAnthropic's Claude 3.5 Sonnet V2 model, optimized for agent interactions. Enhanced version with improved performance and capabilities.
static ANTHROPIC_CLAUDE_3_7_SONNET_V1_0🔹BedrockFoundationModelAnthropic's Claude 3.7 Sonnet model, latest in the Claude 3 series. Advanced language model with enhanced capabilities.
static ANTHROPIC_CLAUDE_HAIKU_4_5_V1_0🔹BedrockFoundationModelAnthropic's Claude Haiku 4.5 model, most cost-efficient and fastest. Delivers near-frontier performance with substantially lower cost and faster speeds.
static ANTHROPIC_CLAUDE_HAIKU_V1_0🔹BedrockFoundationModelAnthropic's Claude Haiku model, optimized for efficiency. Fast and efficient model for lightweight tasks.
static ANTHROPIC_CLAUDE_INSTANT_V1_2🔹BedrockFoundationModelAnthropic's Claude Instant V1.2 model, legacy version. Fast and efficient model optimized for quick responses.
static ANTHROPIC_CLAUDE_OPUS_4_1_V1_0🔹BedrockFoundationModelAnthropic's Claude Opus 4.1 model, most advanced for coding and agentic applications. Excels at independently planning and executing complex development tasks end-to-end. Drop-in replacement for Opus 4 with superior performance and precision.
static ANTHROPIC_CLAUDE_OPUS_4_5_V1_0🔹BedrockFoundationModelAnthropic's Claude Opus 4.5 model, the flagship model released November 2025. Excels at real-world programming tasks, scoring highest on SWE-bench Verified benchmarks. Demonstrates superior performance in long-horizon, goal-directed agentic work with fewer dead-ends.
static ANTHROPIC_CLAUDE_OPUS_4_6_V1🔹BedrockFoundationModelAnthropic's Claude Opus 4.6 model, the most intelligent model and the world's best model for coding, enterprise agents, and professional work. Supports both 200K and 1M context tokens (with the latter in preview). Excels in agentic workflows, complex coding projects, and enterprise applications requiring sophisticated reasoning.
static ANTHROPIC_CLAUDE_OPUS_4_V1_0🔹BedrockFoundationModelAnthropic's Claude Opus 4 model, next-generation frontier model. High-performance model for advanced reasoning and complex multi-step tasks.
static ANTHROPIC_CLAUDE_OPUS_V1_0🔹BedrockFoundationModelAnthropic's Claude Opus model, designed for advanced tasks. High-performance model with extensive capabilities.
static ANTHROPIC_CLAUDE_SONNET_4_5_V1_0🔹BedrockFoundationModelAnthropic's Claude Sonnet 4.5 model, most intelligent in the Claude 4 series. Demonstrates advancements in agent capabilities with enhanced performance in tool handling, memory management, and context processing. Excels at autonomous long-horizon coding tasks.
static ANTHROPIC_CLAUDE_SONNET_4_6🔹BedrockFoundationModelAnthropic's Claude Sonnet 4.6 model. Improved performance for coding, agentic workflows, and browser-based automation.
static ANTHROPIC_CLAUDE_SONNET_4_V1_0🔹BedrockFoundationModelAnthropic's Claude Sonnet 4 model, next-generation frontier model. Advanced model with improved performance for production environments. Balances quality, cost-effectiveness, and responsiveness.
static ANTHROPIC_CLAUDE_SONNET_V1_0🔹BedrockFoundationModelAnthropic's Claude Sonnet model, legacy version. Balanced model for general-purpose tasks.
static ANTHROPIC_CLAUDE_V2🔹BedrockFoundationModelAnthropic's Claude V2 model, legacy version. Original Claude V2 model with broad capabilities.
static ANTHROPIC_CLAUDE_V2_1🔹BedrockFoundationModelAnthropic's Claude V2.1 model, legacy version. Improved version of Claude V2 with enhanced capabilities.
static COHERE_EMBED_ENGLISH_V3🔹BedrockFoundationModelCohere's English embedding model, optimized for English text embeddings. Specialized for semantic understanding of English content.
static COHERE_EMBED_MULTILINGUAL_V3🔹BedrockFoundationModelCohere's Multilingual embedding model, supporting multiple languages. Enables semantic understanding across different languages.
static DEEPSEEK_R1_V1🔹BedrockFoundationModelDeepseek's R1 model, designed for general language understanding. Balanced model for various language tasks.
static META_LLAMA_3_1_70B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3 70B Instruct model, large-scale instruction model. High-capacity model for complex language understanding.
static META_LLAMA_3_1_8B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3 1.8B Instruct model, compact instruction-following model. Efficient model optimized for instruction-based tasks.
static META_LLAMA_3_2_11B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3.2 11B Instruct model, mid-sized instruction model. Balanced model for general instruction processing.
static META_LLAMA_3_2_1B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3.2 1B Instruct model, ultra-lightweight model. Most compact model in the Llama 3.2 series.
static META_LLAMA_3_2_3B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3.2 3B Instruct model, compact efficient model. Lightweight model for basic instruction processing.
static META_LLAMA_3_3_70B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 3.3 70B Instruct model, latest large-scale model. Advanced model with enhanced capabilities.
static META_LLAMA_4_MAVERICK_17B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 4 Maverick 17B Instruct model, innovative mid-sized model. Specialized for creative and dynamic responses.
static META_LLAMA_4_SCOUT_17B_INSTRUCT_V1🔹BedrockFoundationModelMeta's Llama 4 Scout 17B Instruct model, analytical mid-sized model. Focused on precise and analytical responses.
static MISTRAL_7B_INSTRUCT_V0🔹BedrockFoundationModelMistral's 7B Instruct model, efficient instruction-following model. Balanced performance for instruction processing.
static MISTRAL_LARGE_2402_V1🔹BedrockFoundationModelMistral's Large 2402 model, high-capacity language model. Advanced model for complex language understanding.
static MISTRAL_LARGE_2407_V1🔹BedrockFoundationModelMistral's Large 2407 model, updated large-scale model. Enhanced version with improved capabilities.
static MISTRAL_MIXTRAL_8X7B_INSTRUCT_V0🔹BedrockFoundationModelMistral's Mixtral 8x7B Instruct model, mixture-of-experts architecture. Advanced model combining multiple expert networks.
static MISTRAL_PIXTRAL_LARGE_2502_V1🔹BedrockFoundationModelMistral's Pixtral Large 2502 model, specialized large model. Advanced model with cross-region support.
static MISTRAL_SMALL_2402_V1🔹BedrockFoundationModelMistral's Small 2402 model, compact efficient model. Optimized for quick responses and efficiency.
static TITAN_EMBED_TEXT_V1🔹BedrockFoundationModelAmazon's Titan Embed Text V1 model for text embeddings.
static TITAN_EMBED_TEXT_V2_1024🔹BedrockFoundationModelAmazon's Titan Embed Text V2 model with 1024-dimensional vectors.
static TITAN_EMBED_TEXT_V2_256🔹BedrockFoundationModelAmazon's Titan Embed Text V2 model with 256-dimensional vectors.
static TITAN_EMBED_TEXT_V2_512🔹BedrockFoundationModelAmazon's Titan Embed Text V2 model with 512-dimensional vectors.

invokableArn🔹

Type: string

The ARN used for invoking the model.

This is the same as modelArn for foundation models.

modelArn🔹

Type: string

The ARN of the foundation model.

Format: arn:${Partition}:bedrock:${Region}::foundation-model/${ResourceId}

modelId🔹

Type: string

The unique identifier of the foundation model.

supportsAgents🔹

Type: boolean

Whether this model supports integration with Bedrock Agents.

When true, the model can be used with Bedrock Agents for automated task execution.

supportsCrossRegion🔹

Type: boolean

Whether this model supports cross-region inference.

When true, the model can be used with Cross-Region Inference Profiles.

supportsKnowledgeBase🔹

Type: boolean

Whether this model supports integration with Bedrock Knowledge Base.

When true, the model can be used for knowledge base operations.

supportedVectorType?🔹

Type: VectorType[] (optional)

The vector types supported by this model for embeddings.

Defines whether the model supports floating-point or binary vectors.

vectorDimensions?🔹

Type: number (optional)

The dimensionality of the vector embeddings produced by this model.

Only applicable for embedding models.

static AI21_JAMBA_1_5_LARGE_V1🔹

Type: BedrockFoundationModel

AI21's Jamba 1.5 Large model optimized for text generation tasks. Suitable for complex language understanding and generation tasks.

Features:

  • Supports Bedrock Agents integration
  • Optimized for natural language processing
  • Best for: Content generation, summarization, and complex text analysis

static AI21_JAMBA_1_5_MINI_V1🔹

Type: BedrockFoundationModel

AI21's Jamba 1.5 Mini model, a lighter version optimized for faster processing. Balances performance with efficiency for general text tasks.

Features:

  • Supports Bedrock Agents integration
  • Faster response times compared to larger models
  • Best for: Quick text processing, basic content generation

static AI21_JAMBA_INSTRUCT_V1🔹

Type: BedrockFoundationModel

AI21's Jamba Instruct model, specifically designed for instruction-following tasks. Optimized for understanding and executing specific instructions.

Features:

  • Supports Bedrock Agents integration
  • Enhanced instruction understanding
  • Best for: Task-specific instructions, command processing

static AMAZON_NOVA_LITE_V1🔹

Type: BedrockFoundationModel

Amazon's Nova Lite model, balancing performance with efficiency.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: General-purpose language tasks, moderate complexity

static AMAZON_NOVA_MICRO_V1🔹

Type: BedrockFoundationModel

Amazon's Nova Micro model, a lightweight model optimized for efficiency.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: Quick processing tasks, basic language understanding

static AMAZON_NOVA_PREMIER_V1🔹

Type: BedrockFoundationModel

Amazon's Nova Premier model, the most advanced in the Nova series.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: High-end applications, complex analysis, premium performance

static AMAZON_NOVA_PRO_V1🔹

Type: BedrockFoundationModel

Amazon's Nova Pro model, offering advanced capabilities for complex tasks.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: Complex language tasks, professional applications

static AMAZON_TITAN_PREMIER_V1_0🔹

Type: BedrockFoundationModel

Amazon's Titan Text Premier model, designed for high-quality text generation. Offers enhanced capabilities for complex language tasks.

Features:

  • Supports Bedrock Agents integration
  • Advanced language understanding
  • Best for: Complex content generation, detailed analysis

static AMAZON_TITAN_TEXT_EXPRESS_V1🔹

Type: BedrockFoundationModel

Amazon's Titan Text Express model, optimized for fast text generation. Provides quick responses while maintaining good quality output.

Features:

  • Supports Bedrock Agents integration
  • Fast response times
  • Best for: Real-time applications, chatbots, quick content generation

static ANTHROPIC_CLAUDE_3_5_HAIKU_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude 3.5 Haiku model, optimized for quick responses. Lightweight model focused on speed and efficiency.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: Fast responses, lightweight processing

static ANTHROPIC_CLAUDE_3_5_SONNET_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude 3.5 Sonnet V1 model, balanced performance model. Offers good balance between performance and efficiency.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: General language tasks, balanced performance

static ANTHROPIC_CLAUDE_3_5_SONNET_V2_0🔹

Type: BedrockFoundationModel

Anthropic's Claude 3.5 Sonnet V2 model, optimized for agent interactions. Enhanced version with improved performance and capabilities.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: Agent-based applications, complex dialogue

static ANTHROPIC_CLAUDE_3_7_SONNET_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude 3.7 Sonnet model, latest in the Claude 3 series. Advanced language model with enhanced capabilities.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Complex reasoning, analysis, and content generation

static ANTHROPIC_CLAUDE_HAIKU_4_5_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Haiku 4.5 model, most cost-efficient and fastest. Delivers near-frontier performance with substantially lower cost and faster speeds.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Large-scale deployments, budget-conscious applications, real-time customer service, latency-sensitive use cases

static ANTHROPIC_CLAUDE_HAIKU_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Haiku model, optimized for efficiency. Fast and efficient model for lightweight tasks.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Optimized for agents
  • Best for: Quick responses, simple tasks

static ANTHROPIC_CLAUDE_INSTANT_V1_2🔹

Type: BedrockFoundationModel

Anthropic's Claude Instant V1.2 model, legacy version. Fast and efficient model optimized for quick responses.

Features:

  • Supports Bedrock Agents integration
  • Legacy model with EOL date
  • Optimized for agents
  • Best for: Quick responses, simple tasks, legacy applications

static ANTHROPIC_CLAUDE_OPUS_4_1_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Opus 4.1 model, most advanced for coding and agentic applications. Excels at independently planning and executing complex development tasks end-to-end. Drop-in replacement for Opus 4 with superior performance and precision.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Complex end-to-end development, agentic applications, research, advanced reasoning

static ANTHROPIC_CLAUDE_OPUS_4_5_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Opus 4.5 model, the flagship model released November 2025. Excels at real-world programming tasks, scoring highest on SWE-bench Verified benchmarks. Demonstrates superior performance in long-horizon, goal-directed agentic work with fewer dead-ends.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Software engineering, code migration, agentic workflows, financial modeling, deep research

static ANTHROPIC_CLAUDE_OPUS_4_6_V1🔹

Type: BedrockFoundationModel

Anthropic's Claude Opus 4.6 model, the most intelligent model and the world's best model for coding, enterprise agents, and professional work. Supports both 200K and 1M context tokens (with the latter in preview). Excels in agentic workflows, complex coding projects, and enterprise applications requiring sophisticated reasoning.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Financial analysis, cybersecurity, computer use workflows, long-horizon development, multi-tool orchestration

static ANTHROPIC_CLAUDE_OPUS_4_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Opus 4 model, next-generation frontier model. High-performance model for advanced reasoning and complex multi-step tasks.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Advanced reasoning, complex workflows, enterprise applications

static ANTHROPIC_CLAUDE_OPUS_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Opus model, designed for advanced tasks. High-performance model with extensive capabilities.

Features:

  • Supports Bedrock Agents integration
  • Optimized for agents
  • Best for: Complex reasoning, research, and analysis

static ANTHROPIC_CLAUDE_SONNET_4_5_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Sonnet 4.5 model, most intelligent in the Claude 4 series. Demonstrates advancements in agent capabilities with enhanced performance in tool handling, memory management, and context processing. Excels at autonomous long-horizon coding tasks.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Enhanced tool handling and memory management for long-running tasks
  • Best for: Complex agents, coding, autonomous long-horizon tasks, research and analysis, cybersecurity and finance applications

static ANTHROPIC_CLAUDE_SONNET_4_6🔹

Type: BedrockFoundationModel

Anthropic's Claude Sonnet 4.6 model. Improved performance for coding, agentic workflows, and browser-based automation.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Coding, agentic workflows, browser-based automation, enterprise applications

static ANTHROPIC_CLAUDE_SONNET_4_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Sonnet 4 model, next-generation frontier model. Advanced model with improved performance for production environments. Balances quality, cost-effectiveness, and responsiveness.

Features:

  • Supports vision (Image input modality)
  • Cross-region support
  • Supports Bedrock Agents
  • Best for: Production applications, complex language tasks, balanced performance and cost

static ANTHROPIC_CLAUDE_SONNET_V1_0🔹

Type: BedrockFoundationModel

Anthropic's Claude Sonnet model, legacy version. Balanced model for general-purpose tasks.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Legacy model with EOL date
  • Best for: General language tasks, standard applications

static ANTHROPIC_CLAUDE_V2🔹

Type: BedrockFoundationModel

Anthropic's Claude V2 model, legacy version. Original Claude V2 model with broad capabilities.

Features:

  • Supports Bedrock Agents integration
  • Legacy model with EOL date
  • Optimized for agents
  • Best for: General language tasks, legacy applications

static ANTHROPIC_CLAUDE_V2_1🔹

Type: BedrockFoundationModel

Anthropic's Claude V2.1 model, legacy version. Improved version of Claude V2 with enhanced capabilities.

Features:

  • Supports Bedrock Agents integration
  • Legacy model with EOL date
  • Optimized for agents
  • Best for: General language tasks, legacy applications

static COHERE_EMBED_ENGLISH_V3🔹

Type: BedrockFoundationModel

Cohere's English embedding model, optimized for English text embeddings. Specialized for semantic understanding of English content.

Features:

  • Supports Knowledge Base integration
  • 1024-dimensional vectors
  • Supports both floating-point and binary vectors
  • Best for: English text embeddings, semantic search, content similarity

static COHERE_EMBED_MULTILINGUAL_V3🔹

Type: BedrockFoundationModel

Cohere's Multilingual embedding model, supporting multiple languages. Enables semantic understanding across different languages.

Features:

  • Supports Knowledge Base integration
  • 1024-dimensional vectors
  • Supports both floating-point and binary vectors
  • Best for: Cross-lingual embeddings, multilingual semantic search

static DEEPSEEK_R1_V1🔹

Type: BedrockFoundationModel

Deepseek's R1 model, designed for general language understanding. Balanced model for various language tasks.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: General language tasks, content generation

static META_LLAMA_3_1_70B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3 70B Instruct model, large-scale instruction model. High-capacity model for complex language understanding.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Complex instructions, advanced language tasks

static META_LLAMA_3_1_8B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3 1.8B Instruct model, compact instruction-following model. Efficient model optimized for instruction-based tasks.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Lightweight instruction processing, quick responses

static META_LLAMA_3_2_11B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3.2 11B Instruct model, mid-sized instruction model. Balanced model for general instruction processing.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: General instruction tasks, balanced performance

static META_LLAMA_3_2_1B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3.2 1B Instruct model, ultra-lightweight model. Most compact model in the Llama 3.2 series.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Simple instructions, fastest response times

static META_LLAMA_3_2_3B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3.2 3B Instruct model, compact efficient model. Lightweight model for basic instruction processing.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Basic instructions, efficient processing

static META_LLAMA_3_3_70B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 3.3 70B Instruct model, latest large-scale model. Advanced model with enhanced capabilities.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Complex reasoning, advanced language tasks

static META_LLAMA_4_MAVERICK_17B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 4 Maverick 17B Instruct model, innovative mid-sized model. Specialized for creative and dynamic responses.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Creative tasks, innovative solutions

static META_LLAMA_4_SCOUT_17B_INSTRUCT_V1🔹

Type: BedrockFoundationModel

Meta's Llama 4 Scout 17B Instruct model, analytical mid-sized model. Focused on precise and analytical responses.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Analytical tasks, precise responses

static MISTRAL_7B_INSTRUCT_V0🔹

Type: BedrockFoundationModel

Mistral's 7B Instruct model, efficient instruction-following model. Balanced performance for instruction processing.

Features:

  • Supports Bedrock Agents integration
  • Optimized for instruction tasks
  • Best for: General instruction processing, balanced performance

static MISTRAL_LARGE_2402_V1🔹

Type: BedrockFoundationModel

Mistral's Large 2402 model, high-capacity language model. Advanced model for complex language understanding.

Features:

  • Supports Bedrock Agents integration
  • Enhanced language capabilities
  • Best for: Complex reasoning, detailed analysis

static MISTRAL_LARGE_2407_V1🔹

Type: BedrockFoundationModel

Mistral's Large 2407 model, updated large-scale model. Enhanced version with improved capabilities.

Features:

  • Supports Bedrock Agents integration
  • Advanced language processing
  • Best for: Sophisticated language tasks, complex analysis

static MISTRAL_MIXTRAL_8X7B_INSTRUCT_V0🔹

Type: BedrockFoundationModel

Mistral's Mixtral 8x7B Instruct model, mixture-of-experts architecture. Advanced model combining multiple expert networks.

Features:

  • Supports Bedrock Agents integration
  • Specialized expert networks
  • Best for: Complex tasks, diverse language understanding

static MISTRAL_PIXTRAL_LARGE_2502_V1🔹

Type: BedrockFoundationModel

Mistral's Pixtral Large 2502 model, specialized large model. Advanced model with cross-region support.

Features:

  • Supports Bedrock Agents integration
  • Cross-region support
  • Best for: Advanced language tasks, distributed applications

static MISTRAL_SMALL_2402_V1🔹

Type: BedrockFoundationModel

Mistral's Small 2402 model, compact efficient model. Optimized for quick responses and efficiency.

Features:

  • Supports Bedrock Agents integration
  • Efficient processing
  • Best for: Quick responses, basic language tasks

static TITAN_EMBED_TEXT_V1🔹

Type: BedrockFoundationModel

Amazon's Titan Embed Text V1 model for text embeddings.

Features:

  • Supports Knowledge Base integration
  • 1536-dimensional vectors
  • Floating-point vector type
  • Best for: Text embeddings, semantic search, document similarity

static TITAN_EMBED_TEXT_V2_1024🔹

Type: BedrockFoundationModel

Amazon's Titan Embed Text V2 model with 1024-dimensional vectors.

Features:

  • Supports Knowledge Base integration
  • 1024-dimensional vectors
  • Supports both floating-point and binary vectors
  • Best for: High-dimensional embeddings, advanced semantic search

static TITAN_EMBED_TEXT_V2_256🔹

Type: BedrockFoundationModel

Amazon's Titan Embed Text V2 model with 256-dimensional vectors.

Features:

  • Supports Knowledge Base integration
  • 256-dimensional vectors
  • Supports both floating-point and binary vectors
  • Best for: Efficient embeddings with lower dimensionality

static TITAN_EMBED_TEXT_V2_512🔹

Type: BedrockFoundationModel

Amazon's Titan Embed Text V2 model with 512-dimensional vectors.

Features:

  • Supports Knowledge Base integration
  • 512-dimensional vectors
  • Supports both floating-point and binary vectors
  • Best for: Balanced performance and dimensionality

Methods

NameDescription
asArn()🔹Returns the ARN of the foundation model in the following format: arn:${Partition}:bedrock:${Region}::foundation-model/${ResourceId}.
asIModel()🔹Returns the IModel.
grantInvoke(grantee)🔹Gives the appropriate policies to invoke and use the Foundation Model in the stack region.
grantInvokeAllRegions(grantee)🔹Gives the appropriate policies to invoke and use the Foundation Model in all regions.
toString()🔹Returns a string representation of an object.
static fromCdkFoundationModel(modelId, props?)🔹Creates a BedrockFoundationModel from a FoundationModel.
static fromCdkFoundationModelId(modelId, props?)🔹Creates a BedrockFoundationModel from a FoundationModelIdentifier.

asArn()🔹

public asArn(): string

Returns

  • string

Returns the ARN of the foundation model in the following format: arn:${Partition}:bedrock:${Region}::foundation-model/${ResourceId}.

asIModel()🔹

public asIModel(): IModel

Returns

Returns the IModel.

grantInvoke(grantee)🔹

public grantInvoke(grantee: IGrantable): Grant

Parameters

Returns

Gives the appropriate policies to invoke and use the Foundation Model in the stack region.

[disable-awslint:no-grants]

grantInvokeAllRegions(grantee)🔹

public grantInvokeAllRegions(grantee: IGrantable): Grant

Parameters

Returns

Gives the appropriate policies to invoke and use the Foundation Model in all regions.

[disable-awslint:no-grants]

toString()🔹

public toString(): string

Returns

  • string

Returns a string representation of an object.

static fromCdkFoundationModel(modelId, props?)🔹

public static fromCdkFoundationModel(modelId: FoundationModel, props?: BedrockFoundationModelProps): BedrockFoundationModel

Parameters

Returns

Creates a BedrockFoundationModel from a FoundationModel.

Use this method when you have a foundation model from the CDK.

static fromCdkFoundationModelId(modelId, props?)🔹

public static fromCdkFoundationModelId(modelId: FoundationModelIdentifier, props?: BedrockFoundationModelProps): BedrockFoundationModel

Parameters

Returns

Creates a BedrockFoundationModel from a FoundationModelIdentifier.

Use this method when you have a model identifier from the CDK.

← PreviousNext →