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 95 Gemini releases · Updated
- Gemini Blog aidata-scientist ·
Google DeepMind experts share insights on Gemini Omni's capabilities
Google DeepMind research scientist Mohammad Babaeizadeh, product manager Anish Nangia, and research engineer Sarah Xu detail their vision for Gemini Omni. The team explains why they prioritized video generation for Omni's initial release, Gemini Omni Flash, and how it simplifies creating and editing videos from various inputs. They also explore the model's expansive potential for creators, emphasizing its adaptability beyond current applications. The discussion concludes with a look at future developments and the model's ongoing evolution.
announcement - Gemini Python SDK Releases sdkaigaengineer ·
Google's Python GenAI client library v2.18.0 adds Vertex AI deferred service tier
Version 2.18.0 of the googleapis/python-genai client library introduces several new features, including public availability of the deferred service tier on Vertex AI and support for JSON schema in the FunctionDeclaration parser. It also enhances automatic function calling in chat experiences and improves import and model validation performance. These updates primarily benefit developers working with Google's generative AI models and Vertex AI.
feature patch - Gemini Blog aigaengineer ·
Gemini expands app integrations to include more productivity, entertainment, and lifestyle services
Today, Google announced a significant expansion of connected apps for Gemini, allowing users to integrate a broader range of services directly into the AI assistant. These new integrations span productivity, creativity, entertainment, local services, music, home, health, and lifestyle categories, enabling users to manage tasks, plan activities, and stream content within Gemini. Rolling out over the next few weeks, the update empowers users to summarize meetings, book experiences, find home professionals, and more, streamlining workflows and enhancing convenience.
feature - endoflife.date eolgemini-models ·
Gemini model gemini-embedding-001 end-of-life date moved to 2028-05-14
The end-of-life date for Gemini model gemini-embedding-001 changed from 2026-07-14 to 2028-05-14.
deprecation - endoflife.date eolgemini-models ·
Gemini model embedding-2-preview has reached end of life
Gemini model embedding-2-preview reached end of life on 2026-08-10. It no longer receives fixes or security updates — plan the upgrade now.
deprecation - endoflife.date eolgemini-models ·
Gemini model imagen-4.0-fast-generate-001 reaches end of life in 6 days
Gemini model imagen-4.0-fast-generate-001 reaches end of life on 2026-08-17 (6 days from now).
deprecation - endoflife.date eolgemini-models ·
Gemini model imagen-4.0-ultra-generate-001 reaches end of life in 6 days
Gemini model imagen-4.0-ultra-generate-001 reaches end of life on 2026-08-17 (6 days from now).
deprecation - endoflife.date eolgemini-models ·
Gemini model gemini-robotics-er-1.6-preview reaches end of life in 20 days
Gemini model gemini-robotics-er-1.6-preview reaches end of life on 2026-08-31 (20 days from now).
deprecation - Gemini Blog ai ·
Gemini app surpasses 1 billion monthly users, highlights diverse usage patterns
The Gemini app has reached a significant milestone, exceeding 1 billion monthly active users and becoming Google's fastest-growing product. This widespread adoption showcases diverse usage, with 63% of users engaging via voice and strong interest from parents, DIYers, and students. Gemini facilitates real-time problem-solving with live camera feeds and generates over 150 million images daily for small businesses. It also automates tasks across more than 40 Android apps, demonstrating its utility across various platforms and user groups.
announcement - Genkit Releases sdkaigaengineer ·
Genkit v1.41.0 Enhances AI Development Tools with Metrics and Model Support
Genkit v1.41.0 introduces several new features and bug fixes, improving the developer experience for building generative AI applications. Key updates include adding runtime dimensions to metrics for better observability and support for new OpenAI GPT-5.x models. The release also refines integrations with other LLM providers like Anthropic and addresses various issues across the CLI and JavaScript SDK components. These changes benefit engineers working with Genkit to develop and deploy AI-powered features.
feature patch - Gemini Blog aiga ·
Google details AI tools for state fair planning and on-site experience
Google has detailed how its AI-powered tools, including Gemini, Ask Maps, and AI Mode in Search, can enhance the state fair experience for attendees. These capabilities offer assistance with itinerary planning, real-time navigation within fairgrounds, and discovering top-rated food options. Users can also leverage Gemini Live to identify exhibits and create personalized digital keepsakes from photos. The company aims to showcase practical applications of its generative AI for seasonal events and user engagement.
announcement - endoflife.date eolgemini-models ·
Gemini model imagen-4.0-generate-001 reaches end of life in 7 days
Gemini model imagen-4.0-generate-001 reaches end of life on 2026-08-17 (7 days from now).
deprecation - Gemini Blog aiengineer ·
Google showcases 5 developer projects built with Gemini Omni Flash
Google details a selection of five innovative projects developers have created using Gemini Omni Flash. This post showcases various applications of the AI model, which was introduced at I/O and recently made available to developers. Builders are leveraging its capabilities for video editing, scene transformation, object animation, and style application. The examples demonstrate Omni's power in generating and editing realistic video content from diverse inputs.
announcement - Gemini Blog ai ·
Gemini Enhances Vacation Planning with Personalized Itineraries
Gemini now offers more detailed vacation planning by directly integrating with Google Maps, Hotels, and Flights, leveraging real-time data and user preferences. This feature aims to reduce the stress of trip organization by building personalized itineraries, factoring in existing bookings and user interests. The enhancements are available to users who leverage Gemini's capabilities and have Personal Intelligence enabled across Google apps.
feature - Gemini Python SDK Releases sdkaipreviewengineer ·
Python GenAI SDK Adds Gemini Robotics ER 2 Preview and Tool Call Support
The Python GenAI SDK has been updated to include the Gemini Robotics ER 2 Preview model and a new `TOO_MANY_TOOL_CALLS` finish reason, enhancing capabilities for robotic applications and error handling. This release also adds a top-level errors array to the Interaction resource for improved API response clarity. These changes are primarily relevant to developers using the Python SDK for Google's generative AI models, particularly those integrating with robotics or complex AI interactions.
feature patch - Gemini Blog ai ·
Google & Kaggle AI Agents Intensive Course Draws 353,000 Participants
Google and Kaggle hosted a "5-Day AI Agents: Intensive Vibe Coding Course" with over 353,000 participants, teaching how to program AI agents via natural language. The course covered the full lifecycle of designing, securing, and deploying AI agents in the cloud, with hundreds of thousands collaborating on Discord. All course content is now available as a self-paced guide for those who missed the live event.
announcement - Gemini Blog aiengineer ·
Google Recaps July 2026 AI Advancements for Developers, Consumers, and Society
This post details Google's AI developments from July 2026, highlighting efforts to support developers, simplify daily tasks, and protect communities. Key updates included more efficient Gemini models for AI agents and robotics, expanded creative tools, and enhanced app connectivity for Search and Gemini Spark. Google also announced a skilled trades alliance and new wildfire detection satellites, alongside a vision shared by Google DeepMind founder Demis Hassabis.
announcement - Genkit Releases sdkaipreviewengineermedia ·
Genkit Python SDK v0.9.0 adds Agents, reorganizes plugins
The Genkit Python SDK v0.9.0 introduces Agents for stateful, multi-turn AI workflows, alongside a reorganization of its plugins into dedicated PyPI packages. This update improves session persistence, human-in-the-loop capabilities, and observability for developers building AI applications. The changes are available now, with legacy plugins continuing to function but issuing warnings to encourage migration.
feature patch - Gemini Blog ai ·
Vibe-coded schedule app built with Gemini simplifies mornings
A creative technologist built a custom app called Glanceboard using Gemini 3.6 Flash and Nano Banana to transform daily morning routines. The app generates personalized illustrations based on family calendars and local weather, displayed on an e-ink screen to inform users about their schedule and attire. This open-source project aims to provide a serene, personalized, and engaging way to stay organized without relying on bright screens or cloud services.
announcement - Gemini Blog ai ·
Gemini App Updates: July Drop
The Gemini app's July release introduces several new features, including voice interaction on macOS and global availability for Gemini Spark. These updates enhance productivity and personalization for users by offering faster AI models, avatar-based image creation, and expanded app integrations.
feature announcement
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.