GCP Releases
Google Cloud releases and Terraform Google provider. New features, breaking changes, security advisories and deprecations - each summarised in plain English and updated continuously.
Tracking 819 GCP releases · Updated
- Google Cloud release notes aigcpgaengineer ·
Apigee API Hub Model Context Protocol now generally available
Apigee API Hub's Model Context Protocol (MCP) server has reached general availability, enabling AI agents to interact with your API ecosystem using natural language. The GA release expands read/write capabilities for APIs, specs, and deployments, and introduces a global endpoint for easier integration. It also adds granular OAuth scopes and Model Armor integration for enhanced security.
feature - Google Cloud release notes aigcppreviewengineergcp-vertex-ai ·
Cloud Billing: Early AI workload cost anomaly detection
Cloud Billing now offers early anomaly detection for AI workloads like Gemini API and Vertex AI, providing near real-time, service-level cost insights before final billing. This feature appears on the 'By service (Early signals)' tab of the Anomalies dashboard. It aims to give users proactive visibility into potential cost overruns for AI services, though user-configured thresholds are not applicable to these early signals.
feature - Google Cloud release notes aigcppreviewengineergovernment ·
Google Cloud Fraud Defense: reCAPTCHA Preview
Google Cloud Fraud Defense is now in preview with Policy Engine, Universal keys, and challenge policies. Policy Engine enables custom rules for triggering CAPTCHA challenges based on various risk factors, and a new AI-resistant QR code challenge is included. This preview aims to enhance bot detection and fraud prevention for developers integrating reCAPTCHA.
feature - Google Cloud release notes aigcpga ·
Gemini Enterprise Agent Platform adds Claude Opus 5
Gemini Enterprise Agent Platform now supports Anthropic's Claude Opus 5, enhancing its capabilities with advanced large language model features. This integration allows developers to leverage a more powerful model within their agent applications. Claude Opus 5 is available for use immediately.
feature - Google Cloud release notes aigaengineer ·
Gemini Enterprise: Document and presentation creation in Canvas now GA
Gemini Enterprise's Canvas assistant, used for creating and editing AI-generated documents and presentations, is now generally available. This feature allows users to generate content directly from chats and export it to various formats. Administrators must enable the 'Enable canvas' toggle for users to access it.
feature - Google Cloud Blog blogaigcpdeprecationengineerretailgcp-bigquerygcp-looker ·
Open Knowledge Format v0.2 enhances agentic trust and provenance
The Open Knowledge Format (OKF) has been updated to version 0.2, introducing new frontmatter fields to address concerns about agent-generated content trustworthiness. These additions enable consumers to assess provenance, trust, freshness, lifecycle, and attestation of knowledge assets. This release is particularly relevant for systems where agents continuously generate and consume knowledge, allowing for explicit signals to build accountability. The updates are optional and do not change the core format, maintaining compatibility with v0.1.
feature announcement - Google Cloud release notes aigcppreviewengineer ·
Cloud Location Finder integrates with Model Context Protocol in GCP Preview
Google Cloud's Cloud Location Finder now offers a built-in integration with the Model Context Protocol (MCP), currently available in Preview. This integration allows LLM-powered agents to securely access data through standard MCP tools like search and list cloud locations. This feature enables more robust and secure data retrieval for AI agents operating within the Google Cloud environment.
feature - Google Cloud release notes aigcpgaengineergcp-vertex-ai ·
Vertex AI Search: Lower configurable pricing thresholds
Users can now decrease storage size and queries per minute (QPM) subscription thresholds for Vertex AI Search's configurable pricing. This change, which takes effect at the start of the next billing cycle, offers more flexibility for cost management. The feature is now generally available and impacts users managing custom pricing for search applications.
feature - Google Cloud release notes aigcppreviewengineer ·
Gemini Enterprise Agent Platform: Image Models Retired
The Gemini Enterprise Agent Platform has retired the gemini-3.1-flash-image-preview and gemini-3-pro-image-preview models. Users must update their code to reference alternative image models to avoid disruption. This change affects users of these specific preview models.
breaking - Google Cloud Blog blogaiinfragcpengineer ·
GCP Introduces llm-d for Efficient RL Job Interleaving on Accelerators
Google Cloud has introduced llm-d, a new project designed to improve the efficiency of reinforcement learning (RL) jobs for large language models. By enabling co-operative time-slicing, llm-d interleaves independent RL jobs onto shared hardware, significantly increasing accelerator utilization from approximately 40% to 70% without impacting model convergence. This solution addresses critical infrastructure bottlenecks in distributed RL, benefiting teams pushing the boundaries of AI research and development by reducing wasted compute and lowering total cost of ownership. The system is designed to optimize both synchronous and asynchronous RL workloads.
feature announcement - Google Cloud Blog blogaigcpengineerhealthcaregcp-vertex-ai ·
Voicify leverages Google Cloud's Gemini and Vertex AI for AI-enabled ordering
Voicify has enhanced its AI-powered voice ordering system by integrating Google Cloud's Gemini Flash and Vertex AI, addressing challenges like transactional precision, traffic spikes, and latency. This migration provides enterprise-grade reliability and security, particularly beneficial for their healthcare and restaurant clients. The solution improves efficiency, reduces onboarding time, and ensures consistent service during peak usage.
feature announcement - Google Cloud Blog blogaigcpengineergcp-bigquerygcp-spanner ·
Google Cloud's Agentic Data Cloud for Scalable AI
Google Cloud introduced its Agentic Data Cloud at Next 2026, aiming to bridge the gap between AI model capabilities and enterprise data context. This new approach unifies data, AI models, and operational databases, addressing infrastructure limitations that hinder AI scalability and operational efficiency. It leverages native engines like BigQuery and Spanner to provide agents with seamless, low-latency access to fragmented data sources, reducing manual effort and enabling trust through enriched context and real-time data access.
feature announcement - Google Cloud release notes aipreview ·
Gemini Enterprise: Unauthenticated Custom MCP Server Data Stores (Preview)
Gemini Enterprise now supports unauthenticated Custom MCP Server data stores, allowing connections to MCP servers that do not require authentication. This feature is currently in Public Preview and is useful for engineers setting up custom MCP server data stores without authentication requirements.
feature - Google Cloud Blog blogaigcpengineergovernmentenergy ·
Google commits $40M to boost AI for scientific discovery in Genesis Mission
Google is committing $40 million in AI tokens and cloud credits to accelerate scientific research as part of the White House's Genesis Mission. This initiative provides Department of Energy National Laboratories with access to frontier AI tools like AlphaEvolve, AlphaFold 3, and Gemini for Government. The goal is to leverage AI to double the pace of American scientific discovery, with early results showing significant time savings and expanded research capabilities for scientists.
announcement feature - Google Cloud release notes aigcpgaengineer ·
Gemini Enterprise updates: Gemini 3.6 Flash, 3.5 Flash removal
Gemini Enterprise now offers Gemini 3.6 Flash in the global region, accessible after administrators enable the feature toggle. This new model is also integrated into Agent Designer workflows, with updates propagating within a day. Concurrently, Gemini 3.5 Flash will be removed from the global region in Gemini Enterprise on August 4, 2026, impacting users of specific editions.
feature announcement - Google Cloud release notes aigcpdeprecationengineer ·
Gemini Enterprise Agent Platform deprecates open model endpoints
Google Cloud is deprecating several open model endpoints within the Gemini Enterprise Agent Platform, scheduled for retirement on October 21, 2026. This change affects users relying on these specific endpoints for their AI applications, prompting a need to migrate to alternative models. The deprecation notice provides a comprehensive list of affected models, emphasizing the deadline for migration.
deprecation - Google Cloud Blog blogaigcppreviewengineer ·
AlloyDB boosts pgvector HNSW vector search speed by 4x
AlloyDB introduces columnar engine accelerated HNSW for pgvector, achieving up to 4x higher queries per second (QPS) for vector search compared to standard PostgreSQL. This enhancement is crucial for enterprise AI applications that require maximizing QPS without sacrificing search accuracy. The feature is now available in preview for demanding workloads and requires no application code changes.
feature patch - Google Cloud release notes aisecuritygcpengineer ·
Sensitive Data Protection: SWITZERLAND_PASSPORT infoType now in all regions
The SWITZERLAND_PASSPORT infoType detector for Sensitive Data Protection is now available globally. This enhances the tool's capability to identify sensitive Swiss passport information across all supported regions. Users previously limited by regional availability can now leverage this detector universally for data scanning and protection efforts.
feature - Google Cloud release notes aigcpsecurity-advisoryengineer ·
Gemini Enterprise Agent Platform Security Update
A Server-Side Request Forgery (SSRF) vulnerability in Agent Studio's auto-generated API proxy backend has been fixed. This addresses a potential security risk for web applications generated before July 1, 2026. Users who created applications before this date should regenerate and redeploy their apps from Agent Studio to incorporate the security patch, which includes strict domain allowlist validation.
security - Google Cloud Blog blogaigcpgapreviewengineerhealthcaregcp-bigquerygcp-cloud-storagegcp-vertex-ai ·
BigQuery Enhances Unstructured Data Analysis with New Search Capabilities
BigQuery has launched new features to simplify the process of extracting insights from unstructured data like PDFs, audio, and images. This aims to reduce the complexity of building AI-powered search and RAG pipelines by managing embedding generation and offering enhanced search functions. These updates are particularly beneficial for enterprises managing large volumes of diverse data, such as in the healthcare sector, and are now generally available or in public preview.
feature patch
About GCP release tracking on ReleaseBytes
Google Cloud publishes release notes per product — BigQuery, GKE, Cloud Run, Cloud SQL, Vertex AI and dozens more — which makes platform-wide awareness hard. ReleaseBytes aggregates the official GCP release notes and the Terraform Google provider changelog into a single feed, with a plain-English summary of each update and tags for breaking changes, deprecations and security fixes.
Frequently asked questions
How often are GCP release notes updated on ReleaseBytes? ›
Continuously. ReleaseBytes monitors the official GCP release channels around the clock and publishes a plain-English summary of each announcement shortly after it lands.
What kinds of GCP changes does ReleaseBytes track? ›
New features, enhancements, bug fixes, security advisories, breaking changes, deprecations and end-of-life announcements. Every item is tagged by type so you can filter to just the changes that need action.
How can I get alerts for new GCP releases? ›
Set up a free email or Slack alert filtered to GCP, subscribe to the weekly digest, or follow the RSS feed. Teams can also install the ReleaseBytes GitHub App or connect via MCP.
Where does the GCP release data come from? ›
From the official sources: Google Cloud releases and Terraform Google provider. Every item links back to the original vendor announcement.