How to Configure Amazon Bedrock with Continue

Discover Amazon Bedrock models here

Get started with Amazon Bedrock

Configuration

YAML

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: bedrock
    model: <MODEL_ID>
    env:
      region: us-east-1
      profile: bedrock
    roles:
      - chat

JSON (Deprecated)

config.json

{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "bedrock",
      "model": "<MODEL_ID>",
      "region": "us-east-1",
      "profile": "bedrock"
    }
  ]
}

Check out a more advanced configuration here

How to Enable Prompt Caching with Amazon Bedrock

Bedrock allows Claude models to cache tool payloads, system messages, and chat messages between requests. Enable this behavior by adding promptCaching: true under defaultCompletionOptions in your model configuration.

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: bedrock
    model: <MODEL_ID>
    defaultCompletionOptions:
      promptCaching: true

Prompt caching is not supported in JSON configuration files, so use the YAML syntax above to enable it.

How to Set Up Authentication for Amazon Bedrock

Bedrock API Keys

Bedrock API keys let you authenticate without IAM credentials. Set your API key via the apiKey field:

config.yaml

models:
  - name: Claude Sonnet
    provider: bedrock
    model: us.anthropic.claude-sonnet-4-20250514-v1:0
    apiKey: ${{ secrets.BEDROCK_API_KEY }}
    env:
      region: us-east-1
    roles:
      - chat

AWS Credentials

Authentication will be through temporary or long-term credentials in ~/.aws/credentials under a configured profile (e.g. “bedrock”).

[bedrock]
aws_access_key_id = abcdefg
aws_secret_access_key = hijklmno
aws_session_token = pqrstuvwxyz # Optional: means short term creds.

You can also use an AWS accessKeyId and secretAccessKey for authentication instead of a local credentials profile.

YAML

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: bedrock
    model: <MODEL_ID>
    env:
      region: us-east-1
      accessKeyId: ${{ secrets.AWS_ACCESS_KEY_ID }} # can also enter key inline here for local configs
      secretAccessKey: ${{ secrets.AWS_SECRET_ACCESS_KEY }} # can also enter key inline here for local configs
    roles:
      - chat

JSON (Deprecated)

config.json

{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "bedrock",
      "model": "<MODEL_ID>",
      "region": "us-east-1",
      "accessKeyId": "<YOUR_ACCESS_KEY_ID>",
      "secretAccessKey": "<YOUR_SECRET_ACCESS_KEY>" 
    }
  ]
}

How to Configure Custom Imported Models with Amazon Bedrock

To setup Bedrock using custom imported models, add the following to your config file:

YAML

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: bedrockimport
    model: <MODEL_ID>
    env:
      region: us-west-2
      profile: bedrock
      modelArn: arn:aws:bedrock:us-west-2:XXXXX:imported-model/XXXXXX

JSON (Deprecated)

config.json

{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "bedrockimport",
      "model": "<MODEL_ID>",
      "modelArn": "arn:aws:bedrock:us-west-2:XXXXX:imported-model/XXXXXX", 
      "region": "us-west-2",
      "profile": "bedrock"
    }
  ]
}

Authentication will be through temporary or long-term credentials in ~/.aws/credentials under a configured profile (e.g. “bedrock”).

[bedrock]
aws_access_key_id = abcdefg
aws_secret_access_key = hijklmno
aws_session_token = pqrstuvwxyz # Optional: means short term creds.