Quickstart

To run your first inference request

1. Sign up for an AWS account.

   If you already have an AWS account, skip this step.

2. Generate a short-term API key to authenticate your requests to Amazon Bedrock by opening the Amazon Bedrock service in the AWS Management Console.

   For the complete procedure, see the API keys section.

   For production applications, use IAM roles or temporary credentials.

3. Install the relevant SDK for the APIs you plan to use. Python must already be installed.

   Messages API

   pip install boto3 anthropic

   Responses/Chat Completions API

   pip install boto3 openai

   Invoke/Converse API

   pip install boto3

4. Set the following environment variables to use the API key for authentication.

   Messages API

   ANTHROPIC_API_KEY="<provide your Bedrock API key>"
   ANTHROPIC_BASE_URL="https://bedrock-mantle.<your-region>.api.aws/anthropic"

   Responses/Chat Completions API

   OPENAI_API_KEY="<provide your Bedrock API key>"
   OPENAI_BASE_URL="https://bedrock-runtime.<your-region>.amazonaws.com/openai/v1"

   Invoke/Converse API

   AWS_BEARER_TOKEN_BEDROCK="<provide your Bedrock API key>"

5. Choose a model and run your first inference request.

   1. Choose a model. Amazon Bedrock supports 100+ foundation models.

   2. Use the following Python code to run your first inference request.

      Messages API

      import anthropic
      
      client = anthropic.Anthropic()
      
      response = client.messages.create(
          model="anthropic.claude-opus-4-7",
          max_tokens=1024,
          messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}]
      )
      print(response)

      Responses API

      from openai import OpenAI
      
      client = OpenAI()
      
      response = client.responses.create(
          model="openai.gpt-oss-120b",
          input="Can you explain the features of Amazon Bedrock?"
          )
      print(response)

      Chat Completions API

      from openai import OpenAI
      
      client = OpenAI()
      
      response = client.chat.completions.create(
          model="openai.gpt-oss-120b",
          messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}]
          )
      print(response)

      Converse API

      import boto3
      
      client = boto3.client('bedrock-runtime', region_name='us-east-1')
      response = client.converse(
          modelId='anthropic.claude-opus-4-7',
          messages=[
              {
                  'role': 'user',
                  'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}]
              }
          ]
      )
      print(response)

      Invoke API

      import json
      import boto3
      
      client = boto3.client('bedrock-runtime', region_name='us-east-1')
      response = client.invoke_model(
          modelId='anthropic.claude-opus-4-7',
          body=json.dumps({
                  'anthropic_version': 'bedrock-2023-05-31',
                  'messages': [{ 'role': 'user', 'content': 'Can you explain the features of Amazon Bedrock?'}],
                  'max_tokens': 1024
          })
       )
       print(json.loads(response['body'].read()))

   3. Save the file as bedrock-first-request.py.

   4. Run the code with the following command:

      python3 bedrock-first-request.py

      You should see the output of your inference request.