Monitor AI Model Usage & Spending on Databricks
Summary
Databricks AI Gateway enables admins to select which MCP server tools are exposed to agents and view their governance configuration. Usage tracking is automatically enabled to provide centralized visibility into model token consumption and spending metrics.
Summary generated by brickster.ai from the video transcript.
More from Databricks Skill Builder
NewsAI Usage Dashboard: Track Metrics & Performance!
Databricks offers an out-of-the-box usage dashboard that tracks aggregate AI usage metrics across an organization, including daily requests, token usage, and unique users. The dashboard displays model performance indicators like latency, time to first token, and tokens per minute, and is fully customizable for specific organizational needs.
NewsConfigure Budget Thresholds for AI Models
Databricks allows you to configure shared budget thresholds (with a $10,000 cap and usage blocking) to control overall AI model spending. You can also set per-user budget limits (such as $5,000) with alert notifications to monitor individual consumption when certain users dominate budget usage.
NewsAzure Pipelines: Triggering Deployments Based on Branches
Azure Pipelines YAML uses branch-specific triggers to automatically deploy code to different environments based on which branch receives the push. Dev branch deployments go to a dev workspace while main branch deployments go to prod workspace after PR approval.
NewsMonitor LLM Usage & Prevent Data Leaks with Traces
Databricks Unity AI gateway's traces feature lets admins monitor all LLM usage and verify that sensitive data hasn't leaked. Traces provide a comprehensive view of all LLM activities to ensure security and compliance across the platform.
NewsAI Runtime CLI | Serverless GPU LLM Training
Databricks AI Runtime is a CLI tool that enables distributed LLM training on serverless GPUs using YAML configuration files, supporting deployments up to 256 H100 GPUs with built-in MLflow experiment tracking and hardware metrics. Users develop training code locally in their preferred environment and submit jobs via CLI commands that automatically handle infrastructure provisioning, log streaming, and performance monitoring.
NewsSet AI Budgets & Control Spending in Databricks!
Databricks admins can configure spending budgets for individual users, workspaces, or groups through the AI Gateway's govern section to prevent overspending. The demo shows creating a named budget and selecting resource types like Unity AI Gateway to define which models and resources are subject to the budget limits.