Supported Regions and models for Amazon Bedrock Guardrails - Amazon Bedrock
Services or capabilities described in AWS documentation might vary by Region. To see the differences applicable to the AWS European Sovereign Cloud Region, see the AWS European Sovereign Cloud User Guide.

Supported Regions and models for Amazon Bedrock Guardrails

Amazon Bedrock Guardrails applies to foundation models that you invoke on the bedrock-runtime endpoint through the InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream operations. Within those requests, a guardrail can evaluate both text and image content — for image content, see Block harmful images with content filters. The bedrock-mantle endpoint doesn't support Amazon Bedrock Guardrails.

Most models in the Amazon Bedrock catalog support guardrails. The following models don't.

Provider Model Model ID Model type

Amazon

Titan Embeddings G1 - Text

amazon.titan-embed-text-v1

Text embeddings

Amazon

Titan Text Embeddings V2

amazon.titan-embed-text-v2:0

Text embeddings

Amazon

Titan Multimodal Embeddings G1

amazon.titan-embed-image-v1

Multimodal embeddings

Amazon

Amazon Nova Multimodal Embeddings

amazon.nova-2-multimodal-embeddings-v1:0

Multimodal embeddings

Amazon

Rerank 1.0

amazon.rerank-v1:0

Reranking

Amazon

Nova 2 Sonic

amazon.nova-2-sonic-v1:0

Speech

Amazon

Nova 2.5 Sonic

amazon.nova-2-5-sonic

Speech

Cohere

Embed English

cohere.embed-english-v3

Text embeddings

Cohere

Embed Multilingual

cohere.embed-multilingual-v3

Text embeddings

Cohere

Embed v4

cohere.embed-v4:0

Multimodal embeddings

Cohere

Rerank 3.5

cohere.rerank-v3-5:0

Reranking

Luma AI

Ray2

luma.ray-v2:0

Video generation

OpenAI

GPT 5.4

openai.gpt-5.4

Text

OpenAI

GPT 5.5

openai.gpt-5.5

Text

TwelveLabs

Marengo Embed v2.7

twelvelabs.marengo-embed-2-7-v1:0

Multimodal embeddings

TwelveLabs

Marengo Embed 3.0

twelvelabs.marengo-embed-3-0-v1:0

Multimodal embeddings

TwelveLabs

Pegasus v1.5

twelvelabs.pegasus-1-5-v1:0

Video understanding

Point-version model IDs follow their base model. For example, amazon.titan-embed-text-v2:0:8k doesn't support guardrails because amazon.titan-embed-text-v2:0 doesn't.

A request that references a guardrail with one of these models fails with the following error, even though the same request succeeds when you omit the guardrail parameters:

ValidationException: Guardrail is not supported with the chosen model
Note

Don't infer guardrail support from the model type. Models of the same type can differ — TwelveLabs Pegasus v1.2 supports guardrails while Pegasus v1.5 doesn't — and the Stability AI image generation models do support guardrails.

To evaluate content without invoking a model, use the ApplyGuardrail operation. It applies a guardrail to content that you supply directly, so it isn't tied to any model and works regardless of which models your application uses.

To confirm support for a specific model, go to models at a glance, choose the model, and check the Capabilities and Features section of its model card.