Model Routing Powered by Wisdom of the Market
OpenRouter has launched a new Auto router that uses market-based model decisions to route tasks. The router outperforms conventional task-based classifiers across a wide spectrum of tasks.
Also shipped Aug 10, 2026OpenRouter in August 2026 →
BigQuery supports gemini-3.1-flash-lite and gemini-3.5-flash GA models
Both models work in all BigQuery generative AI functions and are available on the us, eu and global multi-regional endpoints.
AI_MULTI_EMBED support for large video files in semantic video search (General availability)
Snowflake Cortex AI_MULTI_EMBED is now generally available for semantic video search with support for large video files up to 6 GB using the TwelveLabs Marengo Embed 3.0 model, enabling organizations to index and search production-grade video content directly in Snowflake.
Amazon S3 Tables Iceberg REST catalog integration (General availability)
Snowflake can now connect directly to the Amazon S3 Tables Iceberg REST endpoint, so you don’t need to create an AWS Glue integration. This capability is now generally available.
Request Access in Workspaces (Preview)
With this preview release, you can resolve access-related SQL errors in Workspaces by submitting access requests directly from Snowsight. When a query fails because of missing privileges and the user can’t self-resolve the issue by switching roles, the user can submit a request with a reason.
READ METADATA privilege is GA
The READ METADATA privilege is now generally available in Unity Catalog. READ METADATA provides read-only visibility into the same metadata available to the object's owner or a user with MANAGE , including security-sensitive information that BROWSE doesn't expose, such as privilege grants, row filters and column masks, and ABAC policies.
Notion connector (Beta)
The managed Notion connector in Lakeflow Connect is now available in Beta. The connector ingests pages, data sources, databases, blocks, comments, and users from Notion into Databricks. See Notion connector .
More from OpenRouterEvery OpenRouter release →
Ori Harness: The Best Way to Use OpenRouter with Any Harness
OpenRouter has released the ori CLI, allowing users to run supported harnesses with an optimized configuration out of the box after logging in once.
Understand your AI usage: every agent, model, and request
OpenRouter has launched the Analytics API and updated its dashboard to help teams track AI spend. Users can view costs per model, save custom charts, click bars to view underlying logs, and query usage data via the terminal.
Ori Eval: Find the Best Model for What You're Building
OpenRouter has launched Ori Eval, a tool that runs agents on custom prompts, checks the tools they call, and grades the answers to help developers choose the best model for their product.
Image Generation Models on OpenRouter
OpenRouter has introduced a dedicated /api/v1/images endpoint for image generation models, using the same billing and keys as chat completions.
Classifiers: Track What Your Agents Do and What It Costs
OpenRouter now allows users to define a taxonomy to tag generations by department, task type, or complexity, enabling filtered logs and grouped analytics.
Transcription on OpenRouter
OpenRouter has introduced an audio transcription API at /api/v1/audio/transcriptions, supporting base64 audio input and returning JSON text.
Every Modality Through One API
OpenRouter now supports chat, image generation, embeddings, and transcription through a single base URL and API key structure.
Give any model a terminal and files
OpenRouter released the shell server tool and Files API in beta, giving models hosted Linux containers to execute shell commands, manage output, and upload or download files.