Gemini Releases
Google Gemini product news and SDK releases. New features, breaking changes, security advisories and deprecations - each summarised in plain English and updated continuously.
Tracking 77 Gemini releases · Updated
- Gemini Python SDK Releases sdkaideprecation ·
Python Gemini API Client Updates to v2.9.0-rc0
The Python Gemini API client has released version 2.9.0-rc0, featuring a complete replacement of its interactions implementation with an unchanged public API surface. New features include support for Gemma local tokenizers and exposure of Computer Use API fields. This release also addresses several bugs, including compatibility issues with aiohttp and handling of API keys in websocket URLs.
feature patch - Gemini Python SDK Releases sdkai ·
Python GenAI SDK v2.11.0 adds new Gemini API features
The Python GenAI SDK has been updated to version 2.11.0, introducing new features for Gemini Enterprise API integration, including environment configuration and enhanced retrieval capabilities. This release also addresses several bug fixes, such as event loop mismatches and improved interaction handling, benefiting developers using Gemini models. Notably, it refactors how safety settings and labels are exposed, impacting how certain parameters are managed.
feature patch - Gemini Python SDK Releases sdkaipreviewmedia ·
Python Generative AI SDK 2.9.0-rc1: New Models and Audio Features
The Python Generative AI SDK has released version 2.9.0-rc1, introducing support for new models like gemini-3-flash-preview and enhancing audio transcription capabilities with features such as audioOffset and LanguageAuto. These updates benefit developers working with multimodal AI applications, particularly those involving audio processing. The release also broadens publisher model path checks, improving compatibility. This is a preview release.
feature - Gemini Python SDK Releases sdkaipreviewdeprecationengineermedia ·
Google GenAI Python SDK v2.9.0: Model updates and API enhancements
The Google GenAI Python SDK has been updated to v2.9.0, replacing the interactions implementation with an unchanged public API surface. Key features include support for new models like gemini-3-flash-preview and Gemma 4, enhanced audio transcription capabilities, and new interaction parameters. These updates benefit developers integrating Gemini models by providing access to the latest AI capabilities and improvements.
feature patch - Gemini Python SDK Releases sdkai ·
Google Python GenAI SDK v2.10.0 adds Agent Platform MCP, video generation, and safety policy controls
Version 2.10.0 of the Google Python GenAI SDK introduces support for Agent Platform MCP in async generate_content_stream, enabling more advanced agent integrations. It also adds parameters for video generation and response formats, alongside new controls for disabling safety policies. These updates benefit developers building AI-powered applications with expanded creative and safety management capabilities.
feature patch - Genkit Releases sdkaipreviewengineermedia ·
Genkit AI v1.39.0: New Agents API, Middleware, and Vercel Integration
Genkit AI v1.39.0 introduces a major overhaul with the removal of the beta Chat API and the introduction of a new, first-class Agents API. This new API offers enhanced capabilities for building multi-turn conversational experiences, including state management, tool integration, persistence, and streaming. The release also includes new middleware for agent orchestration and artifact handling, a Vercel AI SDK adapter for seamless UI integration, and a Firestore session store for enhanced persistence. This update is crucial for developers using Genkit, particularly those building complex conversational agents.
feature breaking - Genkit Releases sdkaiengineer ·
GenKit v1.38.0 adds Fable 5 support
GenKit version 1.38.0 introduces support for Fable 5 within its Anthropic plugin. This update is relevant for developers utilizing the GenKit framework, particularly those integrating with Anthropic services. The release signifies an enhancement to the framework's compatibility with evolving AI ecosystem components.
feature patch - Genkit Releases sdkai ·
Genkit Go v1.9.0: New models, tool support, and bug fixes
Genkit Go has released version 1.9.0, introducing support for new Google AI models including Imagen 4 and dedicated Gemini TTS models, alongside improvements to tool response mapping and concurrency safety. This update also enhances native constrained generation for tools and adds Claude Opus 4.5 and Llama models via Vertex AI's Model Garden. These changes benefit developers using Genkit for AI applications, particularly those integrating with Google Cloud's AI offerings.
feature patch - Gemini Blog aiengineer ·
Gemini app introduces study notebooks for personalized learning
The Gemini app now features study notebooks, a new personalized learning space designed to help users organize their study efforts and learn more efficiently. This feature provides bite-sized lessons tailored to individual knowledge gaps, includes practice quizzes to test understanding, and offers a progress dashboard for prioritizing study topics. This aims to help users master new subjects faster by reducing time spent on identifying focus areas.
feature - Gemini Blog ai ·
Coffee shop leverages Gemini for automation, content creation, and marketing
Henry's House of Coffee is using Google's Gemini AI to streamline operations and grow its business. Hrag Kalebjian, the owner, employs Gemini to automate data tracking, accelerate the creation of marketing materials, and generate engaging content for his weekly newsletter. These applications allow him to reclaim time and focus on customers, demonstrating Gemini's utility for small businesses.
announcement feature - Gemini Blog aiengineer ·
Google Gemini AI News: June 2026 Updates
Google announced several advancements in its Gemini AI suite in June 2026, focusing on unified experiences and on-device capabilities. Key updates include the Gemma 4 12B model for local use, enhanced computer use in Gemini 3.5 Flash for automation, and new Gemini Image and video models via APIs. These features aim to assist users across various domains, from business and education to research and creative endeavors, with broader rollouts planned for Android devices and specific Google services.
feature announcement patch - Gemini Blog ai ·
Gemini Spark adds macOS app, connected apps, and real-time topic tracking
Gemini Spark has launched a new macOS application enabling users to automate desktop tasks and integrate with Google Workspace. The update also introduces expanded integrations with popular third-party apps like Canva and Dropbox, enhancing its utility across various services. Additionally, Gemini Spark can now intelligently track and react to topics in real-time, bringing users up-to-date information from multiple sources. The macOS app is in beta for Google AI Ultra subscribers in the US, while app integrations are rolling out globally.
feature announcement - Gemini Blog aimedia ·
Google launches Nano Banana 2 Lite image model and Gemini Omni Flash video model
Google has released Nano Banana 2 Lite, a faster and more cost-efficient image generation model, and Gemini Omni Flash, a new model for video generation and editing. These models aim to streamline creative workflows for developers building generative media experiences. Nano Banana 2 Lite is available now for developers and rolling out to Google consumer products, while Gemini Omni Flash is in public preview for developers via API and AI Studio. This release allows for integrated image-to-video workflows and enhanced multimedia content creation.
feature announcement - Gemini Blog aiengineer ·
Gemini app adds personalized image creation
The Gemini app now offers personalized image generation using Google tools like Gmail, Photos, YouTube, and Search, with user permission. This feature, connecting Personal Intelligence with Nano Banana and Google Photos, allows for creations that reflect user preferences and lifestyle. Initially available for free to eligible U.S. users, it simplifies prompts by drawing context from connected Google apps and user photos.
feature announcement - Gemini Blog ai ·
Gemini adds note-taking to Google Meet for Pro and Ultra subscribers
Gemini's "Take notes for me" feature is now available for Google AI Pro and Ultra subscribers in Google Meet, transcribing conversations and generating summaries with action items. This aims to help users focus on discussions by automating note-taking and saving them to Google Docs. The feature is accessible during calls or via Meet settings for eligible Workspace business customers.
feature - Gemini Blog aiengineer ·
Gemini App Helps Users Avoid Jetlag
The Gemini app can now help users avoid jetlag by analyzing Gmail and Calendar data for flight information. It then creates a personalized, jetlag-proof schedule and adds it to the user's calendar. This new capability leverages the Gemini 3.5 Flash model to combine intelligence with actionable planning for travelers.
feature announcement - Gemini Blog aiengineer ·
Google Parents Share 5 Ways They Use Gemini for Child-Rearing
This article highlights how Google employees are leveraging Gemini's capabilities to manage various aspects of parenting. Examples include using Gemini for educational support, trip planning, organizing complex schedules, creating custom social stories for children with disabilities, and planning family meals and introducing solids. These use cases demonstrate Gemini's versatility in reducing parental mental load and enhancing family activities.
announcement - Gemini Blog aiengineer ·
Google AI tools to streamline job hunting
Google is highlighting three AI tools to assist with job searching: Career Dreamer for role exploration, NotebookLM for resume and cover letter refinement, and Gemini Live for interview practice. These tools aim to simplify the job application process from identifying opportunities to preparing for interviews. They are available now and can be used by individuals seeking employment.
announcement - Gemini Blog aipreviewengineer ·
Gemini app adds study notebooks for personalized learning
Google is introducing study notebooks within the Gemini app, designed to offer personalized learning experiences for students. These notebooks assess knowledge gaps through diagnostic quizzes, provide bite-sized lessons, and track progress via a custom dashboard. The feature aims to help students pinpoint areas needing attention and prepare for exams, with additional visuals and support for more standardized tests coming soon.
feature announcement - Gemini Blog ai ·
Gemini 3.5 Flash Adds Native Computer Use Tool
Gemini 3.5 Flash now includes a built-in computer use tool, enhancing its ability to build agents that can see, reason, and act across different environments. This integration aims to improve performance for long-horizon and enterprise automation tasks, making it easier for developers and enterprises to build custom agents. The feature is available via the Gemini API and Gemini Enterprise Agent Platform, with enhanced safety measures for sensitive actions.
feature
About Gemini release tracking on ReleaseBytes
Google's Gemini models and APIs move fast: new model versions, pricing changes, SDK releases and capability launches arrive weekly. ReleaseBytes tracks the official Gemini and Google DeepMind announcement channels and SDK changelogs, so you can see every model update, deprecation notice and API change in one feed.
Frequently asked questions
How often are Gemini release notes updated on ReleaseBytes? ›
Continuously. ReleaseBytes monitors the official Gemini release channels around the clock and publishes a plain-English summary of each announcement shortly after it lands.
What kinds of Gemini 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 Gemini releases? ›
Set up a free email or Slack alert filtered to Gemini, 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 Gemini release data come from? ›
From the official sources: Google Gemini product news and SDK releases. Every item links back to the original vendor announcement.