Smart Routing: Cut AI costs by routing each task to the right model

BetaAug 13, 2026VerifiedAdded Sep 22, 2026

Smart Routing (Beta) automatically picks the right model and agent harness for each task, based on complexity, permissions, and budget. It shifts routine work to lower-cost models and reserves frontier models for hard problems, and every routing decision is visible and auditable.

AI agents LLMs Security Pricing Developer tools

Read Databricks's release notes

https://docs.databricks.com/aws/en/release-notes/unity-gateway#smart-routing-cut-ai-costs-by-routing-each-task-to-the-right-model

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Agent Bricks and Mosaic AI releases

Agent Bricks and Mosaic AIAug 13, 2026

Google Gemini 3.7 Flash is now available on Unity Gateway

Google Gemini 3.7 Flash is now available on Unity Gateway for fast, cost-efficient everyday tasks. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

UpdateLLMsSQLGovernanceSource

Agent Bricks and Mosaic AIAug 13, 2026

Block or redact sensitive data in requests and responses

The Sensitive Data Detection guardrail (Beta) detects structured sensitive data (such as Social Security numbers, credit card numbers, IBANs, and phone numbers) and either blocks the interaction or redacts the matched values in place.

PreviewAI agentsLLMsGovernanceSource

Agent Bricks and Mosaic AIAug 14, 2026

DeepSeek V4 Pro (0813) is now available on Unity Gateway

DeepSeek V4 Pro (0813) is now available on Unity Gateway for complex reasoning and agentic coding workflows. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

UpdateAI agentsSQLSecuritySource

Agent Bricks and Mosaic AIAug 12, 2026

Custom trace views in the MLflow trace explorer are in Beta

You can now build custom trace views in the Databricks MLflow trace explorer. Describe the layout you want in plain language, and Genie generates a reusable view that surfaces the trace fields, metrics, and feedback controls most relevant to your review workflow. See Build a custom trace view .

BetaBIObservabilitySource

Agent Bricks and Mosaic AIAug 11, 2026

ABAC GRANT policies now cover Unity Gateway resource types (Beta)

Attribute-based access control (ABAC) GRANT policies dynamically grant Unity Catalog privileges to securables whose governed tags match a condition. They now support model services, model provider services, Model Context Protocol (MCP) services, and agent services, which are the resource types Unity Gateway governs.

BetaAI agentsMCPGovernanceSource

Agent Bricks and Mosaic AIAug 10, 2026

DeepSeek V4 Flash (0731) is now available on Unity Gateway

DeepSeek V4 Flash (0731) is now available on Unity Gateway for fast, cost-efficient reasoning, coding, and agentic tool use. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

UpdateAI agentsSQLGovernanceSource

Agent Bricks and Mosaic AIAug 6, 2026

Moonshot AI Kimi K3 is now available on Unity Gateway

Moonshot AI Kimi K3 is now available on Unity Gateway for long-horizon coding, knowledge work, and reasoning, with native vision. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

UpdateSQLSecurityObservabilitySource

Agent Bricks and Mosaic AIAug 6, 2026

Unity Gateway API: Manage resources with SDKs, the CLI, and Terraform

You can manage Unity Gateway resources programmatically instead of clicking through the UI, with full create, read, update, list, and delete support for endpoints, model providers, and MCP servers.

UpdateMCPDeveloper toolsSource

Also shipped on Aug 13, 2026

Google Cloud BigQueryAug 13, 2026

BigQuery pipelines add automated metadata enrichment in preview

Semantic metadata defined in SQLX configurations now syncs with Knowledge Catalog, and the Data Engineering Agent can generate this metadata from your intent or context.

PreviewAI agentsSQLGovernanceSource

Google Cloud Gemini Enterprise Agent PlatformAug 13, 2026

Gemini 3.7 Flash is generally available

Gemini 3.7 Flash is now generally available (GA) and available for production use. For more information on 3.7 Flash, see the model page .

GALLMsSource

Google Cloud Gemini EnterpriseAug 13, 2026

Gemini Enterprise: Create, upload, and share custom skills

Skills are reusable custom instructions that help the Gemini Enterprise assistant perform specific tasks. End users can create, upload, and share skills. To enable this feature, administrators must turn on the skills and skill-sharing settings in Feature Management . Administrators can also configure skill availability and approve skill-sharing requests.

GALLMsSource

Google Cloud Gemini EnterpriseAug 13, 2026

Gemini Enterprise: Use Gemini 3.7 Flash

Gemini 3.7 Flash is generally available (GA) in the global , us , and eu regions. To make Gemini 3.7 Flash available to users in the Gemini Enterprise app, administrators must turn on the Gemini 3.7 Flash feature toggle in the Google Cloud console. Note: Gemini 3.7 Flash is not available in the Gemini Enterprise mobile app.

GAAI agentsLLMsNotebooksSource

Google Cloud Gemini APIAug 13, 2026

Gemini 3.7 Flash generally available (GA)

Released our most intelligent workhorse model yet for coding and agents: Gemini 3.7 Flash (gemini-3.7-flash): Substantial improvements across software engineering, web development, and agentic workflows, available at an introductory price through December 31, 2026. To get started, see the Gemini 3.7 Flash model page and the Latest model guide.

GAAI agentsLLMsPricingSource

OpenAI OpenAI APIAug 13, 2026

OpenAI announces Ultrafast mode for GPT-5.6 Sol in limited preview

Ultrafast mode is a new API service tier for GPT-5.6 Sol that runs up to 14x faster than Standard processing, available to select customers.

PreviewLLMsDeveloper toolsPerformanceSource