Amazon Nova Micro: The Fastest Text Model on AWS Bedrock

import boto3
import json

bedrock = boto3.client("bedrock-runtime", region_name="us-east-1")

def classify_intent(user_message: str) -> str:
    response = bedrock.invoke_model(
        modelId="amazon.nova-micro-v1:0",
        body=json.dumps({
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {
                            "text": f"""Classify this customer message into one category.
Categories: BILLING, TECHNICAL, SHIPPING, RETURNS, OTHER

Message: {user_message}

Respond with only the category name."""
                        }
                    ]
                }
            ],
            "inferenceConfig": {
                "maxTokens": 10,
                "temperature": 0.0,
            }
        }),
    )
    result = json.loads(response["body"].read())
    return result["output"]["message"]["content"][0]["text"].strip()

# Example usage
intent = classify_intent("I was charged twice for my order last week")
print(intent)  # BILLING

def intelligent_route(user_query: str) -> str:
    # Step 1: Nova Micro classifies complexity (cost: ~$0.000035 per call)
    complexity_check = bedrock.invoke_model(
        modelId="amazon.nova-micro-v1:0",
        body=json.dumps({
            "messages": [{"role": "user", "content": [{"text": f"""Is this query simple or complex?
Simple: factual questions, short extraction, yes/no answers
Complex: multi-step reasoning, analysis, synthesis, long generation

Query: {user_query}
Answer with one word: SIMPLE or COMPLEX"""}]}],
            "inferenceConfig": {"maxTokens": 5, "temperature": 0.0},
        }),
    )
    complexity = json.loads(complexity_check["body"].read())["output"]["message"]["content"][0]["text"].strip()

    # Step 2: Route accordingly
    if complexity == "SIMPLE":
        model_id = "amazon.nova-micro-v1:0"  # $0.035/1M
    else:
        model_id = "amazon.nova-pro-v1:0"    # $0.800/1M

    # Step 3: Generate actual response
    response = bedrock.invoke_model(
        modelId=model_id,
        body=json.dumps({
            "messages": [{"role": "user", "content": [{"text": user_query}]}],
            "inferenceConfig": {"maxTokens": 1024},
        }),
    )
    return json.loads(response["body"].read())["output"]["message"]["content"][0]["text"]

bedrock_client = boto3.client("bedrock", region_name="us-east-1")

job = bedrock_client.create_model_invocation_job(
    modelId="amazon.nova-micro-v1:0",
    jobName="nightly-classification-job",
    inputDataConfig={"s3InputDataConfig": {"s3Uri": "s3://my-bucket/input/"}},
    outputDataConfig={"s3OutputDataConfig": {"s3Uri": "s3://my-bucket/output/"}},
)