anthropic-aws/models

20 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Claude Platform on AWS language model creation

To create models that call the Anthropic Messages API on AWS, use the provider instance: const model = anthropicAws('claude-sonnet-4-6');

Claude Platform on AWS model IDs

Model IDs for Claude Platform on AWS are identical to the first-party Anthropic API. See the Anthropic provider docs for the full list of language model options.

Claude Platform on AWS generateText example

Example using Claude Platform on AWS with generateText: import { anthropicAws } from '@ai-sdk/anthropic-aws'; import { generateText } from 'ai'; const { text } = await generateText({ model: anthropicAws('claude-sonnet-4-6'), prompt: 'Invent a new holiday and describe its traditions.', });

Bedrock language model creation syntax

Create language models using the provider instance with the model ID as the first argument. Example: `amazonBedrock('meta.llama3-70b-instruct-v1:0')`.

Bedrock language model capabilities table

Amazon Bedrock language models support different capabilities. Models are listed with columns: Image Input, Object Generation, Tool Usage, Tool Streaming. Check the model table in documentation for specific model capabilities. Examples: `amazon.titan-tg1-large` supports none of these; `anthropic.claude-3-5-sonnet-20241022-v2:0` supports all four; `meta.llama3-70b-instruct-v1:0` supports none.

Bedrock embedding model creation

Create embedding models using `amazonBedrock.embedding('model-id')`. Example: `const model = amazonBedrock.embedding('amazon.titan-embed-text-v1');`

Bedrock embedding model capabilities table

Bedrock embedding models and capabilities: `amazon.titan-embed-text-v1` (default dimensions 1536, no custom dimensions), `amazon.titan-embed-text-v2:0` (default dimensions 1024, supports custom dimensions), `amazon.nova-embed-text-v2:0` (default dimensions 1024, supports custom dimensions), `cohere.embed-english-v3` (default dimensions 1024, no custom dimensions), `cohere.embed-multilingual-v3` (default dimensions 1024, no custom dimensions).

Bedrock reranking model creation

Create reranking models using `amazonBedrock.reranking('model-id')`. Example: `const model = amazonBedrock.reranking('cohere.rerank-v3-5:0');`

Bedrock reranking model capabilities table

Bedrock reranking models: `amazon.rerank-v1:0`, `cohere.rerank-v3-5:0`.

Bedrock image model creation

Create image models using `amazonBedrock.image('model-id')`. Example: `const model = amazonBedrock.image('amazon.nova-canvas-v1:0');`

Amazon Nova Canvas model availability

The `amazon.nova-canvas-v1:0` model is available in the `us-east-1`, `eu-west-1`, and `ap-northeast-1` regions.

Bedrock Anthropic language model creation

Create Bedrock Anthropic models using `bedrockAnthropic('model-id')`. Example: `const model = bedrockAnthropic('us.anthropic.claude-3-5-sonnet-20241022-v2:0');`

Bedrock Anthropic reasoning support

Anthropic has reasoning support for Claude 3.7 and Claude 4 models on Bedrock including: us.anthropic.claude-sonnet-5, us.anthropic.claude-fable-5, us.anthropic.claude-opus-4-8, us.anthropic.claude-opus-4-7, us.anthropic.claude-opus-4-6-v1, us.anthropic.claude-opus-4-5-20251101-v1:0, us.anthropic.claude-sonnet-4-5-20250929-v1:0, us.anthropic.claude-opus-4-20250514-v1:0, us.anthropic.claude-sonnet-4-20250514-v1:0, us.anthropic.claude-opus-4-1-20250805-v1:0, us.anthropic.claude-haiku-4-5-20251001-v1:0.

Bedrock Anthropic model capabilities table

Bedrock Anthropic models support different capabilities with columns: Image Input, Object Generation, Tool Usage, Computer Use, Reasoning. Models listed: us.anthropic.claude-sonnet-5, us.anthropic.claude-fable-5, us.anthropic.claude-opus-4-8, us.anthropic.claude-opus-4-7, us.anthropic.claude-opus-4-6-v1, us.anthropic.claude-opus-4-5-20251101-v1:0, us.anthropic.claude-sonnet-4-5-20250929-v1:0, us.anthropic.claude-opus-4-20250514-v1:0, us.anthropic.claude-sonnet-4-20250514-v1:0, us.anthropic.claude-opus-4-1-20250805-v1:0, us.anthropic.claude-haiku-4-5-20251001-v1:0, us.anthropic.claude-3-5-sonnet-20241022-v2:0 (all support Image Input and Object Generation and Tool Usage; newer models support Computer Use and Reasoning; Claude 3.5 Sonnet v2 does not support Computer Use or Reasoning).

Bedrock Mantle model creation methods

Models can be created using bedrockMantle('model-id') which defaults to Chat Completions API, bedrockMantle.chat('model-id') for explicit Chat Completions API, or bedrockMantle.responses('model-id') for the Responses API. Not all Mantle models support the Responses API.

Bedrock Mantle model capabilities table

Bedrock Mantle models and their API support: | Model | Chat Completions | Responses API | | --- | --- | --- | | openai.gpt-oss-20b | Supported | Supported | | openai.gpt-oss-120b | Supported | Supported | | openai.gpt-oss-safeguard-20b | Supported | Not supported | | openai.gpt-oss-safeguard-120b | Supported | Not supported |

Bedrock Mantle exclusive models

Some models are only available through the Mantle endpoint, such as openai.gpt-oss-120b. These models may not be available through the Bedrock Converse API.

Bedrock Mantle model listing API discovery

To discover all available models on the Mantle endpoint, use the Mantle endpoint's model listing API, as available models may differ from those available through the Bedrock Converse API.

PDF chat example model identifier

The model identifier 'anthropic/claude-sonnet-4' is used in the streamText function to specify Claude Sonnet 4 for processing PDFs.

amazon.nova-canvas-v1:0 image model capabilities

Amazon Bedrock's amazon.nova-canvas-v1:0 image model supports custom image sizes with the following constraints: - Size range: 320-4096 pixels per side - Dimensions must be divisible by 16 - Aspect ratio range: 1:4 to 4:1 - Maximum total pixels: 4.2M

Give your agent this brain