AI_EXTRACT updates
AI_EXTRACT now delivers a 12.8% relative improvement in average extraction accuracy compared with the previous version in our evaluations. Extract fields, lists, and tables more accurately from complex documents, including forms, handwritten content, dense tables, and charts.
Also shipped Nov 2, 2026Snowflake in November 2026 →
Managed warehouse for MLflow (Beta)
Managed warehouse for MLflow is available in Beta, enabling users to view Unity Catalog traces in the MLflow UI without manually choosing a SQL warehouse.
Check out GitHub code without long-lived credentials on self-hosted agents
Self-hosted agents can now use temporary, read-only GitHub App tokens for repository checkout. This eliminates the need to distribute and rotate long-lived SSH keys or personal access tokens across your agent fleet.
Serving tuned Gemini 3.x models on global endpoints
Serving tuned Gemini 3.x models on global endpoints is available in General Availability (GA) . You can copy fine-tuned Gemini 3.x models to the global region using the Model Registry models:copy API, deploy them to global serving endpoints, and send inference requests directly to aiplatform.googleapis.com .
[Launched] Generally Available: Change from virtual network integration to a private endpoint capable network configuration in Azure Database for PostgreSQL flexible server
You now have greater flexibility in network design for Azure Database for PostgreSQL Flexible Server workloads. Now you can change existing VNet-integrated servers from delegated-subnet networking to a private endpoint-capable configuration, enabling secu
[Launched] Generally Available: Restart databases in Azure SQL DB via the Azure portal
You can now restart or fail over databases directly from the Azure portal, including single databases, Hyperscale databases, and databases in elastic pools, without writing scripts against the Rest API or contacting support. Learn more.
Lakehouse caching for cross-cloud data access is generally available (GA)
Lakehouse caching for cross-cloud data access is generally available (GA). Cross-cloud caching is disabled by default. You can opt in to caching on a Lakehouse federated catalog or a BigQuery cross-cloud connection to cache remote files in your Google Cloud region. This helps reduce cross-cloud egress costs and accelerate subsequent queries.
More from Snowflake Cortex AIEvery Snowflake Cortex AI release →
Cortex Training (Preview)
Cortex Training is now available in preview, allowing users to customize open-weight LLMs using a serverless service within Snowflake.
Cortex Agents Coding Agent thinking effort, system instructions, and stage mounts
The Cortex Agents Coding Agent agent:run API now supports three additional public controls when using the code_toolset_all tool, providing more granular configuration for coding tasks.
Cortex AI usage in Native App usage history
Developers can now track Cortex AI credit usage, including agent tokens and search embeddings, attributed to Snowflake Native Apps using the APPLICATION_DAILY_USAGE_HISTORY view.
AI_PARSE_DOCUMENT introduces AGENTIC mode for intelligent document processing (Public Preview)
Snowflake Cortex AI_PARSE_DOCUMENT now includes an AGENTIC mode in public preview. This feature allows users to extract information from complex documents, including charts and diagrams, using a single SQL call.
OpenAI GPT-5.6 Luna, GPT-5.6 Terra, and GPT-6 Luna in AI Functions (Preview)
The following OpenAI models are now in public preview in AI Functions:
Retrieve Cortex Search (Public Preview)
The CORTEX_SEARCH_RETRIEVE table function is now in public preview, allowing users to execute low-latency search queries directly from SQL for RAG and chatbot applications.
Responses API for the Cortex REST API (Preview)
The new Responses API in the Cortex REST API provides OpenAI-compatible endpoints for accessing models.
Coding agent MCP tool
Snowflake-managed MCP servers can now expose a coding agent that provides a managed coding sandbox attached to a conversation thread without requiring a stored agent object.