TrueFoundry’s AI Gateway provides a secure and efficient way to integrate Large Language Models (LLMs) hosted on Databricks into your applications. This guide covers how to configure Databricks models in TrueFoundry AI Gateway.

​
Prerequisites

Before you begin, ensure you have:
  • Access to a TrueFoundry workspace with AI Gateway enabled
  • A Databricks workspace with appropriate permissions
  • Active Databricks serving endpoints (learn how to create them)
  • One of the following authentication methods:
    • Service Principal with necessary permissions
    • Personal Access Token (PAT) for your Databricks workspace

​
Adding Databricks Provider Account

​
1. Navigate to AI Gateway

  • In the TrueFoundry Dashboard, go to AI Gateway → Models
  • Select Databricks as your model provider
Screenshot2025 07 02at8 51 28PM Min Pn

​
2. Enter Authentication Details

Service Principal authentication is the recommended approach for production environments as it provides better security and access control.
  • Choose Service Principal Auth
  • Enter your Databricks Service Principal Client ID and OAuth Secret
Screenshot2025 07 02at8 55 51PM Min Pn

​
2.2. Personal Access Token (PAT)

Personal Access Tokens are suitable for development and testing environments.
  • Choose Databricks API Key Based Auth and enter your PAT
Screenshot2025 07 02at8 56 44PM Min Pn

​
3. Enter Base URL

Enter Databricks workspace URL (format:https://<workspace_id>.databricks.com )