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

# Inference on Amazon Bedrock

> Run Clark AI inference through Amazon Bedrock so every prompt executes in your AWS account

## Overview

<Info>
  Inference through customer's Amazon Bedrock is available on [Cloud-Prem](/enterprise/cloud-prem/aws) deployments only.
</Info>

By default, Clark AI runs inference through models hosted in the Superblocks Cloud. Administrators can instead point Clark at **Amazon Bedrock**, so every prompt runs on models in your own AWS account.

Once configured, every prompt that every builder sends to Clark runs inference through Bedrock. Tokens burn down your existing AWS commitment and reduce Clark AI credit usage. Builders do not need to configure anything; they use Clark exactly as before.

## How it works

### 1. Admin configures Bedrock

In **Organization Settings**, an administrator connects Amazon Bedrock and supplies the necessary credentials and the models and regions Clark should use.

### 2. All builders inherit the configuration

Once saved, every builder in the organization automatically runs inference through Bedrock for all Clark interactions. There is no per-user or per-app setup required.

### 3. Inference burns down your commitment and reduces Clark credit usage

Every prompt a builder sends — whether exploring a database schema, generating a plan, or writing code — runs inference on Bedrock. Token consumption counts toward your existing AWS commitment and reduces Clark AI credit usage.

## What this means for your organization

* **Burn down your AWS commitment**: Inference runs on Bedrock, contributing to your AWS commitment and reducing Clark credit consumption
* **Inference runs in your network**: All model inference executes within your AWS account
* **No builder friction**: Builders use Clark identically regardless of the underlying provider