Databricks introduces Smart Routing for AI models to optimize costs and performance
Databricks has launched Smart Routing in Beta, an automated system designed to select the most appropriate AI model and agent harness for specific tasks based on complexity, permissions, and budget. This feature aims to reduce AI operational costs by over 30% by directing routine work to lower-cost models while reserving advanced models for complex problems. It provides full visibility and auditable decisions for routing across proprietary and open models, including Claude Code and Codex, via Omnigent or ucode.
Features (1) ›
- Automated Smart Routing for AI Models (Beta)
Smart Routing (Beta) automatically selects the optimal AI model and agent harness for each task, considering factors like complexity, permissions, and budget. It shifts routine workloads to cost-effective models and reserves advanced models for challenging problems, with all routing decisions being visible and auditable. This functionality works with models like Claude Code and Codex when run through Omnigent or ucode, supporting routing across both proprietary and open models.
https://docs.databricks.com/aws/en/release-notes/product/2026/august#smart-routing-cut-ai-costs-by-routing-each-task-to-the-right-model
Related releases
- Databricks Unity Gateway API now supports programmatic resource management Databricks Release Notes ·
- Schema-level HTTP connections in Databricks Unity Catalog are now GA Databricks Release Notes ·
- Databricks-managed MCP Connectors Integrate with Unity Gateway in Beta Databricks Release Notes ·
- Databricks-managed MCP Connectors Integrated with Unity Gateway (Beta) Databricks Release Notes ·
- Databricks Unity Gateway Achieves General Availability for Enterprise AI Governance Databricks Release Notes ·
- Unity Gateway API: Manage resources with SDKs, CLI, and Terraform Databricks Release Notes ·