> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS SageMaker

> Route to your AWS Sagemaker models through Prisma AIRS AI Gateway

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

With the AI Gateway you can manage/restrict access, log requests, and more.

## Quick Start

<CodeGroup>
  ```sh cURL icon="square-terminal" theme={"system"}
  # 1. Add @sagemaker provider in Model Catalog
  # 2. Use it:

  curl https://aigw.portkey.ai/v1/endpoints/{endpoint_name}/invocations \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -d '{
      "inputs": "my_custom_value",
      "my_custom_key": "my_custom_value"
    }'
  ```
</CodeGroup>

***

## Add Provider in Model Catalog

<Steps>
  <Step title="Navigate to Model Catalog">
    Go to [**Model Catalog → Add Provider**](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager.
  </Step>

  <Step title="Select AWS Sagemaker">
    Find and select **AWS Sagemaker** from the provider list.
  </Step>

  <Step title="Configure AWS Credentials">
    There are two authentication methods:

    <Note>
      Here's how to find your AWS credentials:

      <CardGroup cols={2}>
        <Card title="AWS Access Key" href="/docs/integrations/llms/aws-bedrock#how-to-find-your-aws-credentials">
          Use your `AWS Secret Access Key`, `AWS Access Key Id`, and `AWS Region` to create your provider.

          [**Integration Guide**](/docs/integrations/llms/aws-bedrock#how-to-find-your-aws-credentials)
        </Card>

        <Card title="AWS Assumed Role" href="/docs/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role">
          Take your `AWS Assumed Role ARN` and `AWS Region` to create the provider.

          [**Integration Guide**](/docs/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role)
        </Card>
      </CardGroup>
    </Note>

    Enter your AWS credentials and deployment details for your Sagemaker endpoint.
  </Step>

  <Step title="Save and Use">
    Save your configuration. Your provider slug will be `@sagemaker` (or a custom name you specify).
  </Step>
</Steps>

***

## Direct Integration Without Model Catalog

If you prefer not to store your AWS credentials in the AI Gateway, you can pass them directly when instantiating the AI Gateway 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

<CodeGroup>
  ```sh cURL icon="square-terminal" theme={"system"}
  curl https://aigw.portkey.ai/v1/endpoints/{endpoint_name}/invocations \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -H "x-portkey-provider: @sagemaker" \
    -H "x-portkey-aws-access-key-id: $AWS_ACCESS_KEY_ID" \
    -H "x-portkey-aws-secret-access-key: $AWS_SECRET_ACCESS_KEY" \
    -H "x-portkey-aws-region: $AWS_REGION" \
    -H "x-portkey-amzn-sagemaker-inference-component: $SAGEMAKER_INFERENCE_COMPONENT" \
    -d '{
      "inputs": "my_custom_value",
      "my_custom_key": "my_custom_value"
    }'
  ```
</CodeGroup>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Add Metadata" icon="tag" href="/docs/aigw/product/observability/metadata">
    Add metadata to your Sagemaker requests
  </Card>

  <Card title="Gateway Configs" icon="sliders" href="/docs/aigw/product/ai-gateway/configs">
    Configure advanced gateway features
  </Card>

  <Card title="Tracing" icon="chart-line" href="/docs/aigw/product/observability/traces">
    Trace and monitor your Sagemaker requests
  </Card>
</CardGroup>


## Related topics

- [Enterprise Gateway](/docs/aigw/changelog/enterprise.md)
- [Put integrations by slug](/docs/aigw/api-reference/integrations/put-integrations-by-slug.md)
- [Post integrations](/docs/aigw/api-reference/integrations/post-integrations.md)
- [Prisma AIRS AI Gateway Models](/docs/aigw/product/model-catalog/gateway-models.md)
- [Supported Providers](/docs/aigw/api-reference/inference-api/supported-providers.md)