AWS SageMaker

Route to your AWS Sagemaker models through Portkey

Sagemaker allows users to host any ML model on their own AWS infrastructure.

With Portkey you can manage/restrict access, log requests, and more.

Quick Start

Python

from portkey_ai import Portkey

# 1. Install: pip install portkey-ai
# 2. Add @sagemaker provider in Model Catalog
# 3. Use it:

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@sagemaker"
)

response = portkey.post(
    url="endpoints/{endpoint_name}/invocations",
    # You can pass any key value pair required by the model
    # (apart from `url`), they are passed to the Sagemaker endpoint
    inputs="my_custom_value",
    my_custom_key="my_custom_value"
)

print(response)

---

Add Provider in Model Catalog

1. Navigate to Model Catalog

   Go to Model Catalog → Add Provider in your Portkey dashboard.

2. Select AWS Sagemaker

   Find and select AWS Sagemaker from the provider list.

3. Configure AWS Credentials

   There are two authentication methods:

   Here’s how to find your AWS credentials:

   AWS Access Key

   Use your AWS Secret Access Key, AWS Access Key Id, and AWS Region to create your provider.

   Integration Guide

   AWS Assumed Role

   Take your AWS Assumed Role ARN and AWS Region to create the provider.

   Integration Guide

   Enter your AWS credentials and deployment details for your Sagemaker endpoint.

4. Save and Use

   Save your configuration. Your provider slug will be @sagemaker (or a custom name you specify).

---

Direct Integration Without Model Catalog

If you prefer not to store your AWS credentials in Portkey, you can pass them directly when instantiating the Portkey client.

Supported Parameters

These parameters are supported for Sagemaker (not required if you’re using Model Catalog):

Node SDK	Python SDK	REST Headers
awsAccessKeyId	aws_access_key_id	x-portkey-aws-access-key-id
awsSecretAccessKey	aws_secret_access_key	x-portkey-aws-secret-access-key
awsRegion	aws_region	x-portkey-aws-region
awsSessionToken	aws_session_token	x-portkey-aws-session-token
sagemakerCustomAttributes	sagemaker_custom_attributes	x-portkey-amzn-sagemaker-custom-attributes
sagemakerTargetModel	sagemaker_target_model	x-portkey-amzn-sagemaker-target-model
sagemakerTargetVariant	sagemaker_target_variant	x-portkey-amzn-sagemaker-target-variant
sagemakerTargetContainerHostname	sagemaker_target_container_hostname	x-portkey-amzn-sagemaker-target-container-hostname
sagemakerInferenceId	sagemaker_inference_id	x-portkey-amzn-sagemaker-inference-id
sagemakerEnableExplanations	sagemaker_enable_explanations	x-portkey-amzn-sagemaker-enable-explanations
sagemakerInferenceComponent	sagemaker_inference_component	x-portkey-amzn-sagemaker-inference-component
sagemakerSessionId	sagemaker_session_id	x-portkey-amzn-sagemaker-session-id
sagemakerModelName	sagemaker_model_name	x-portkey-amzn-sagemaker-model-name

Example

Python

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@sagemaker",
    aws_region="us-east-1",
    aws_access_key_id="AWS_ACCESS_KEY_ID",
    aws_secret_access_key="AWS_SECRET_ACCESS_KEY",
    sagemaker_inference_component="SAGEMAKER_INFERENCE_COMPONENT"
)

response = portkey.post(
    url="endpoints/{endpoint_name}/invocations",
    # You can pass any key value pair required by the model
    # (apart from `url`), they are passed to the Sagemaker endpoint
    inputs="my_custom_value",
    my_custom_key="my_custom_value"
)

print(response)

---

Next Steps

SDK Reference

Complete SDK documentation and API reference

Add Metadata

Add metadata to your Sagemaker requests

Gateway Configs

Configure advanced gateway features

Tracing

Trace and monitor your Sagemaker requests