Vertex AI Release Notes
Last updated: Feb 14, 2026
- Feb 10, 2026
- Date parsed from source:Feb 10, 2026
- First seen by Releasebot:Feb 14, 2026
February 10, 2026
Feature
GLM 5 is available as an experimental launch in Model Garden. This model is targeting complex systems engineering and long-horizon agentic tasks. GLM 5 is available as a managed API in Model Garden. To learn more, see GLM 5.
Original source Report a problem - Feb 4, 2026
- Date parsed from source:Feb 4, 2026
- First seen by Releasebot:Nov 25, 2025
- Modified by Releasebot:Feb 6, 2026
February 04, 2026
Feature
Anthropic's Claude Opus 4.6
Claude Opus 4.6 is available in Model Garden.
Original source Report a problem All of your release notes in one place
Join Releasebot and get updates from Google and hundreds of other software products.
- Jan 26, 2026
- Date parsed from source:Jan 26, 2026
- First seen by Releasebot:Jan 27, 2026
January 26, 2026
Announcement
Vertex AI Agent Builder
Sessions, Memory Bank, and Code Execution will begin charging for usage on Feburary 11, 2026 instead of January 28, 2026.
Original source Report a problem - Jan 23, 2026
- Date parsed from source:Jan 23, 2026
- First seen by Releasebot:Jan 24, 2026
- Modified by Releasebot:Jan 30, 2026
January 23, 2026
Feature
Virtual Try-On
Virtual Try-On is now generally available (GA). The new endpoint, virtual-try-on-001, replaces the previous endpoint, virtual-try-on-preview-08-04. We recommend changing to the new endpoint as soon as possible.
For more information, see Generate Virtual Try-On Images.
Original source Report a problem - Jan 22, 2026
- Date parsed from source:Jan 22, 2026
- First seen by Releasebot:Jan 24, 2026
January 22, 2026
Announcement
Codestral (25.01) and Mistral Large (24.11) are retired as of January 23, 2026.
Original source Report a problem - Jan 21, 2026
- Date parsed from source:Jan 21, 2026
- First seen by Releasebot:Jan 26, 2026
January 21, 2026
Feature
The Data Science Agent supports BigFrames, BigQuery ML, and Google Cloud Serverless for Apache Spark. Previously, these capabilities were supported only when using Colab Enterprise notebooks in BigQuery.
Original source Report a problem - Jan 20, 2026
- Date parsed from source:Jan 20, 2026
- First seen by Releasebot:Jan 23, 2026
January 20, 2026
Feature
GLM 4.7 GA is now available in Model Garden. This model is designed for core or vibe coding, tool use, and complex reasoning. GLM 4.7 is available as a managed API in Model Garden. To learn more, see GLM 4.7.
Original source Report a problem - Jan 16, 2026
- Date parsed from source:Jan 16, 2026
- First seen by Releasebot:Jan 21, 2026
January 16, 2026
Gemini CLI lands in Vertex AI Workbench, empowering terminal access to Gemini directly from your workspace. This open source AI agent lets you create and run notebooks, edit code, explain concepts, access local files, and interact with Google Cloud services from the command line.
Feature
The Gemini CLI is available in Vertex AI Workbench instances. The Gemini CLI is an open source AI agent that provides access to Gemini directly in a terminal. You can use the Gemini CLI to do tasks like the following:
- Create a new notebook.
- Run notebook cells.
- Write and edit a notebook's code and text cells.
- Explain code and technical concepts.
- Interact with a Vertex AI Workbench instance's local file system, including performing complex file operations that span multiple files based on a single, high-level instruction.
- Run basic shell commands.
- Run commands to interact with other Google Cloud services, such as Vertex AI and BigQuery.
To get started, see Use the Gemini CLI.
Original source Report a problem - Jan 13, 2026
- Date parsed from source:Jan 13, 2026
- First seen by Releasebot:Jan 14, 2026
January 13, 2026
Feature
Veo 3.1 reference-to-video update
Veo 3.1 Preview models now support the following features:
- 9:16 aspect ratio for reference-to-video.
- Upsampling for videos generated at 1080p and 4k resolutions.
For more information, see the following:
- Generate Veo videos from reference images
- Veo on Vertex AI video generation API
- Jan 6, 2026
- Date parsed from source:Jan 6, 2026
- First seen by Releasebot:Jan 8, 2026
January 06, 2026
Feature
GLM 4.7 is available as an experimental launch in Model Garden. This model is designed for core or vibe coding, tool use, and complex reasoning. GLM 4.7 is available as a managed API in Model Garden. To learn more, see GLM 4.7.
Original source Report a problem