How to Deploy Your ML Model to AWS (Step-by-Step Guide)

A developer provides a step-by-step guide to deploying machine learning models to AWS using SageMaker, covering model packaging, S3 upload, endpoint creation, and inference testing. The guide includes code examples for saving models, creating inference scripts, and invoking endpoints, along with troubleshooting tips and cost considerations.

I've trained more ML models than I've deployed. There's something comforting about the local loop— model.fit , model.evaluate , hitting 94% accuracy, then staring at the screen wondering, "Okay, how do I make this actually useful?" If you're stuck there right now, this guide will help. Note: I wrote this based on AWS documentation and standard SageMaker patterns. If you try it, drop a comment about what worked or broke . model.pkl or .joblib requirements.txt with your dependencies aws configure python import joblib joblib.dump model, 'model.pkl' Create a requirements.txt file: sklearn==1.2.0 pandas==1.5.0 numpy==1.23.0 Keep both files in the same folder. python import boto3 s3 = boto3.client 's3' bucket name = 'my-unique-ml-bucket-12345' Make this unique s3.create bucket Bucket=bucket name, CreateBucketConfiguration={ 'LocationConstraint': 'us-east-1' } s3.upload file 'model.pkl', bucket name, 'models/model.pkl' s3.upload file 'requirements.txt', bucket name, 'models/requirements.txt' model s3 path = f's3://{bucket name}/models/model.pkl' Save this as inference.py : python import json import joblib import numpy as np import os model = None def model fn model dir : return joblib.load os.path.join model dir, 'model.pkl' def input fn input data, content type : if content type == 'application/json': data = json.loads input data return np.array data 'features' raise ValueError f"Unsupported content type: {content type}" def predict fn input data, model : return model.predict input data def output fn prediction, content type : return json.dumps {'predictions': prediction.tolist } These four functions are what SageMaker calls when someone hits your endpoint. Run this in a Python script: python from sagemaker.sklearn.model import SKLearnModel from sagemaker import get execution role sklearn model = SKLearnModel model data=model s3 path, role=get execution role , instance type='ml.m5.large', entry point='inference.py', py version='py3' sklearn model.deploy initial instance count=1, instance type='ml.m5.large', endpoint name='my-model-endpoint' This takes 5–10 minutes. You'll see Creating → In Service . python import boto3 import json runtime = boto3.client 'sagemaker-runtime' response = runtime.invoke endpoint EndpointName='my-model-endpoint', ContentType='application/json', Body=json.dumps {'features': 5.1, 3.5, 1.4, 0.2 } result = json.loads response 'Body' .read .decode print result If you see {'predictions': ... } , it worked. Endpoints cost money even when idle: aws sagemaker delete-endpoint --endpoint-name my-model-endpoint aws sagemaker delete-endpoint-config --endpoint-config-name my-model-endpoint Error | Fix | |---|---| NoCredentialsError | Run aws configure again | InvalidRoleException | IAM role needs S3 + SageMaker permissions | ModelError | Check inference.py for missing imports | Endpoint stuck on Creating | Wait 5–10 more minutes | Your IAM role needs: s3:GetObject , s3:PutObject sagemaker:CreateModel , sagemaker:CreateEndpoint Resource | Cost | |---|---| ml.m5.large | ~$0.20/hour ~$6/month if 24/7 | | S3 storage | ~$0.02/GB/month | Delete when not using. I've seen $50 surprises from idle endpoints. If you're following this, check: pip show boto3 sagemaker os , joblib , numpy are installedIf something breaks, comment below with the error. I'll update this guide. Deploying ML feels intimidating until you do it once. SageMaker handles most of the complexity. You just upload your model to S3, point SageMaker at it, and deploy. I've trained models that sat on my laptop for months because I didn't know how to deploy them. Now I tell people: "Just run this script, it's not that hard." If you're building something with this, drop a comment. I love seeing what people deploy.