Skip to main content
AWS Bedrock provides managed access to foundation models from Anthropic, Meta, Amazon, and others. It integrates with AWS IAM, VPC, CloudWatch, and other AWS services for enterprise deployments.

​
Supported Models

ModelBedrock IDProviderNotes
Claude Sonnet 3.5 v2anthropic.claude-3-5-sonnet-20241022-v2:0AnthropicDefault
Claude Haiku 3.5anthropic.claude-3-5-haiku-20241022-v1:0AnthropicFast/cheap
Llama 3.1 70Bmeta.llama3-1-70b-instruct-v1:0MetaOpen-source
Titan Text G1amazon.titan-text-express-v1AmazonNative AWS

​
Setup

1

Enable models in AWS Console

Go to AWS Console > Bedrock > Model access and request access to the models you need.
2

Create IAM credentials

Create an IAM user or role with the AmazonBedrockFullAccess policy (or a scoped policy for specific models).
3

Set environment variables

export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
export AWS_REGION=us-east-1
Or use an IAM role (EC2 instance profile, ECS task role, etc.) - no keys needed.
4

Configure profClaw

# profClaw auto-detects AWS credentials from environment
profclaw config provider add bedrock
profclaw doctor --provider bedrock

​
Environment Variables

​
AWS_ACCESS_KEY_ID
string
AWS access key ID. Not needed when using IAM roles.
​
AWS_SECRET_ACCESS_KEY
string
AWS secret access key. Not needed when using IAM roles.
​
AWS_REGION
string
AWS region where your Bedrock models are available (e.g., us-east-1, eu-west-1). Defaults to us-east-1.
​
AWS_SESSION_TOKEN
string
Temporary session token for STS-based credentials.

​
Configuration Example

AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
AWS_REGION=us-east-1

​
Model Aliases

AliasBedrock Model ID
bedrockanthropic.claude-3-5-sonnet-20241022-v2:0
bedrock-haikuanthropic.claude-3-5-haiku-20241022-v1:0
bedrock-llamameta.llama3-1-70b-instruct-v1:0

​
Usage Examples

profclaw chat --model bedrock "Review this security policy"
profclaw chat --model bedrock-haiku "Quick summarization task"
profclaw chat --model bedrock-llama "Open-source model analysis"

# Use any Bedrock model directly
profclaw chat --model bedrock/amazon.titan-text-express-v1 "Hello"

​
Notes

  • Bedrock is stable and recommended for enterprise AWS-native deployments.
  • Bedrock pricing is per-token, similar to direct API pricing, plus AWS fees.
  • Supports VPC endpoints for fully private traffic (no internet required).
  • Use AWS SCP (Service Control Policies) to restrict which models are accessible.
  • Cross-region inference is supported - specify a different region per request if needed.