LLM Changelog

New extensions available in all Gemini countries and languagesWhat:Gemini can now connect to more apps and services on Android.With the new Spotify extension, you can play your favorite songs and discover playlists for any moodWith the Phone, Messages, and WhatsApp extensions, you can quickly make calls and draft, refine, and send messages with your default phone and messaging apps, as well as WhatsAppWith the Utilities extension, you can use Gemini to set alarms, control your device settings, and even open your camera to take a quick selfiePhone, Messages, WhatsApp, Utilities, Calendar, Tasks, and Keep extensions are now available in all Gemini languagesWhy:We're continuing to build new ways for Gemini to connect to the apps you rely on every day. Through these extensions, Gemini can help you get things done and take actions for you, better than ever.Learn more about extensions.

GeneralGPT-4.5was released to users on the Pro plan in ChatGPT.The temporary chat icon is now in top bar to make the temporary chat experience more accessible and clear.iOSLong press to selecttext on iOS and moved the message quick actions to always be visible below the message:Bug fixes and small improvements in the1.2025.056 iOS release.A setting to allow users to auto-submit transcriptions.OFF by default.AndroidImproved error handling for Play Integrity errors.

1. iOS widget (see below):
2. Text selection improvements: you can now select text across horizontal rulers.3. Performance improvements: Improved model header loading behavior. Conversation history and GPTs show up faster.4. Bug fix for logged-out users: 401s when dismissing tooltips 401s logging out users on Android.

Document upload is now available to all Gemini usersWhat:You can seamlessly upload multiple Google Docs, PDFs, and Word documents from Google Drive or your device into Gemini for quick summaries, personalized feedback, and actionable insights. Currently, Gemini offers a 32K context window (around 50 pages of text), with usage limits. Gemini Advanced users continue to have a 1 million token context window (around 1,500 pages of text) and much higher usage limits.Why:Unlock deeper insights from your documents and streamline your workflows with Gemini to save time and boost your productivity.

**AI Studio updates:**

- Support for [additional regions](https://ai.google.dev/gemini-api/docs/available-regions) (Kosovo, Greenland and Faroe Islands).

**API updates:**

- Support for [additional regions](https://ai.google.dev/gemini-api/docs/available-regions) (Kosovo, Greenland and Faroe Islands).

Set ChatGPT as default search engine in Safari.Confirmation dialog for logging out (iOS, web).Improved Android conversation parsing performance.iOS performance fixes.Updated launch animations and composer design on Android.Whisper (ChatGPT's voice-to-text feature) now shows a text preview of dictated text after recording:

Priority access with Gemini Advanced: Ask Gemini to look back at past chats for more tailored helpWhat:Starting today, Gemini can now use your past chats to give you more helpful responses. Ask a question about something you've discussed, or have Gemini summarize a previous conversation. It will use the information from relevant chats to craft its response. This means no more starting over, and you can build on top of previous conversations or projects you already started.You’re in control: easily review, delete, or decide how long to keep your chat history. You can also turn off Gemini Apps Activity altogether by going toMy Activity. Gemini may indicate when it uses your past chats in Sources and related content. This experience is starting to roll out in English forGemini Advancedsubscribers via Google One AI Premium Plan.Why:Conversations change, ideas evolve, and sometimes we need to revisit what’s been said. Think of Gemini as your personal AI assistant, always there to pick up where you left off. It becomes your thought partner, evolving alongside you to unlock new levels of helpfulness, that’s unique to you.

Users can now share a Canvas asset such as rendered React/HTML code, document, or code with another user, similar to how you share a conversation. You can do this from the Canvas toolbar when Canvas is open.
For more details about the canvas feature in ChatGPT, check out the following Help Center article!

**Model updates:**

- Released `gemini-2.0-flash-001`, a generally available (GA) version of [Gemini 2.0 Flash](https://ai.google.dev/gemini-api/docs/models/gemini#gemini-2.0-flash) that supports text-only output.
- Released `gemini-2.0-pro-exp-02-05`, an [experimental](https://ai.google.dev/gemini-api/docs/models/experimental-models) public preview version of Gemini 2.0 Pro.
- Released `gemini-2.0-flash-lite-preview-02-05`, an experimental public preview [model](https://ai.google.dev/gemini-api/docs/models/gemini#gemini-2.0-flash-lite) optimized for cost efficiency.

**API updates:**

- Added [file input and graph output](https://ai.google.dev/gemini-api/docs/code-execution#input-output) support to code execution.

**SDK updates:**

- Released the [Google Gen AI SDK for Python](https://googleapis.github.io/python-genai/) to general availability (GA).

Try our 2.0 Flash Thinking Experimental modelsWhat:Starting today, Gemini app users have access to our 2.0 Flash Thinking Experimental model. Built on the speed and performance of 2.0 Flash, this model is trained to break down prompts into a series of steps to strengthen its reasoning capabilities and deliver better responses. 2.0 Flash Thinking Experimental shows its thought process to users so you can see why it responded in a certain way, what its assumptions were, and trace the model's line of reasoning.Users can also try 2.0 Flash Thinking Experimental with apps, our thinking model designed to give you access to agentic capabilities through the use of connected apps such as YouTube, Maps, and Search for complex multi-step questions. These connected apps already make the Gemini app a uniquely helpful AI-powered assistant, and we’re exploring how new reasoning capabilities can combine with your apps to help you do even more.Both 2.0 Flash Thinking Experimental models are now rolling out to the Gemini web and mobile app. We’ll expand access to enterprise accounts in the coming weeksThese experimental models are meant to be an early preview and may make mistakes. Additionally these models won't be compatible with some Gemini features in their experimental state.Why:We believe in rapid iteration and bringing the best of Gemini to the world. Your feedback helps us improve these models over time and learning from experimental launches informs how we release models more widely.Priority access with Gemini Advanced: Try our 2.0 Pro Experimental modelWhat:Gemini Advanced users can now try 2.0 Pro Experimental, our leading model designed to be exceptional at complex tasks, providing better factuality and stronger performance for coding and math prompts.Whether you’re tackling advanced coding challenges, like generating a specific program from scratch, or solving mathematical problems, like developing complex statistical models or quantum algorithms, 2.0 Pro Experimental wi

Imagen 3 just got an upgradeWhat:We’re excited to introduce an upgrade to our latest image generation model, Imagen 3, which currently ranks #1 on theImage Generation Leaderboard! This enhanced version delivers richer details and textures, and follows your instructions with greater accuracy to help bring your creative vision to life.Why:We’re committed to empowering your creativity. By providing access tostate-of-the-art modelslike Imagen 3, we aim to fuel your imagination and help you bring even more of your ideas to life.

Introducing Gemini 2.0 Flash to GeminiWhat:Gemini is now powered by 2.0 Flash, our latest model that is designed for the agentic era, delivering fast responses and stronger performance across a number of key benchmarks for everyday help with tasks like brainstorming, learning, or writing.In addition to 2.0 Flash, Gemini Advanced users will continue to have access to a 1M token context window for up to 1,500 pages of file uploads, priority access to features such as Deep Research and Gems, 2TB of storage, and more.Gemini 1.5 Flash and 1.5 Pro will remain available for the next few weeks.Why:With faster responses and improved performance, we’re making it easier for you to unlock new ways to create, interact, and collaborate with Gemini.

We've updated custom instructions to make it easier to customize how ChatGPT responds to you. With the new UI, you can tell ChatGPT the traits you want it to have, how you want it to talk to you, and any rules you want it to follow.
If you're already using custom instructions, this won't change your current settings.
The new UI is rolling out now onhttp://chatgpt.comand desktop on Windows, and is coming to mobile and desktop on MacOS in the next few weeks. Available soon to ChatGPT users in the EU, Norway, Iceland, Liechtenstein, and Switzerland.

Today we’re rolling out a beta version of tasks—a new way to ask ChatGPT to do things for you at a future time. Whether it's one-time reminders or recurring actions, tell ChatGPT what you need and when, and it will automatically take care of it.
Scheduled tasks is in early beta for Plus, Pro, and Teams. Eventually this will be available to anyone with a ChatGPT account.
For details see Scheduled tasks in ChatGPT.

**Model updates:**

- Released Gemini 2.0 Flash Thinking Mode for public preview. Thinking Mode is
a test-time compute model that lets you see the model's thought process
while it generates a response, and produces responses with stronger
reasoning capabilities.

Read more about Gemini 2.0 Flash Thinking Mode in our [overview
page](https://ai.google.dev/gemini-api/docs/thinking-mode).

Priority access with Gemini Advanced: Upload your code repositoryWhat:In September, we made it possible for you to upload multiple code files to get help understanding, modifying, or debugging your code within Gemini Advanced. Today, we're excited to announce yet another upgrade: you can nowupload your code repository(up to 1 folder per conversation, with a maximum of 1,000 files and a maximum folder size of 100MB, can be uploaded at a time) directly from your device in one action. This means you'll get the same comprehensive code assistance, with the added benefit of Gemini Advanced understanding the full context of your project. The experience is available with Gemini Advanced as part of the Google One AI Premium Plan.Why:This improvement enables you to streamline your workflow and leverage the full power of Gemini Advanced's 1M token context window for more comprehensive and contextually relevant code analysis and debugging.

Priority access with Gemini Advanced: Try our latest 2.0 Experimental Advanced modelWhat:Gemini Advanced users can now try Gemini-exp-1206, our model designed to be exceptional at complex tasks such as coding, math, reasoning & instruction following. Whether you’re tackling advanced coding challenges, solving mathematical problems for school or personal projects, or providing detailed, multi-step instructions to craft a tailored business plan, 2.0 Experimental Advanced will help you navigate complex tasks with greater ease.This experimental model is meant to be an early preview and can have unexpected behaviors and may make mistakes. Additionally this model will not have access to real time information and won't be compatible with some Gemini features in its experimental state.You can access this experimental model in the Gemini model drop-down.Why:We believe in rapid iteration and bringing the best of Gemini to the world, and we want to give Gemini Advanced subscribers priority access to our latest AI innovations. Which is why we’re introducing Gemini-exp-1206 to enable users to experiment with cutting-edge models with our latest enhancements. Your feedback helps us improve these models over time and learning from experimental launches informs how we release models more widely.

Projects provide a new way to group files and chats for personal use, simplifying the management of work that involves multiple chats. You can set custom instructions and upload files in your Projects, and any conversations in your Project share context with your uploaded files and custom instructions. Chats in Projects use GPT-4o and support the following features:
CanvasAdvanced data analysisDALL•ESearch
ChatGPT Projects are available to all Plus, Team, and Pro users.

Today we started rolling out two updates to voice mode in ChatGPT:
Santa voice:You can now chat with Santa in ChatGPT! Until early January, you can find Santa in the list of available voices in settings or by tapping on a snowflake icon. We are rolling out Santa globally to all logged in users today, and you can chat with Santa everywhere you use voice mode.
The first time you chat with Santa, your advanced voice limit will reset one time. So, if you’ve already used up your advanced voice limit for the day or the month (based on your subscription plan), you can still chat with Santa for the first time using advanced voice.
Video and screenshare:In our latest mobile apps, we are starting to roll out real-time video, screen share, and image upload capabilities in advanced voice. We expect to complete this rollout to all Team and most Plus and Pro users, except for those in the European Union, Switzerland, Iceland, Norway, and Liechtenstein, over the next week. Video and screen share are subject to daily usage limits for all plans, and image uploads are subject to ChatGPT vision message limits.
Use the controls at the bottom of the screen, like the camera button below, to get started. You can find screen share and image upload controls under the “...” menu at the bottom of the screen.

**Model updates:**

- Released [Gemini 2.0 Flash Experimental](https://ai.google.dev/gemini-api/docs/models/gemini#gemini-2.0-flash) for public preview. Gemini 2.0 Flash Experimental's partial list of features includes:
- Twice as fast as Gemini 1.5 Pro
- Bidirectional streaming with our Live API
- Multimodal response generation in the form of text, images, and speech
- Built-in tool use with multi-turn reasoning to use features like code execution, Search, function calling, and more

Read more about Gemini 2.0 Flash in our [overview
page](https://ai.google.dev/gemini-api/docs/models/gemini-v2).

Introducing Gemini 2.0 Flash as an experimental model in GeminiWhat:Gemini users now have access to our latest experimental model, a chat optimized version of 2.0 Flash Experimental with improvements on a number of key academic benchmarks and speed. This experimental model is meant to be an early preview and can have unexpected behaviors and may make mistakes. Additionally, some Gemini features won't be compatible with this model in its experimental state.You can access this experimental model in the Gemini model drop-down.Why:We believe in rapid iteration and bringing the best of Gemini to the world. Which is why we want to give users access to cutting-edge models with our latest enhancements. Your feedback helps us improve these models over time and learning from experimental launches informs how we release models more widely.Priority access with Gemini Advanced: Your personal research assistant saves you hours of workWhat:Gemini Deep Research is your personal research assistant that helps you get up to speed on just about any topic. It’ll break down your prompt into a number of relevant research questions, automatically analyze sites on your behalf for relevant information, and create comprehensive multi-page reports on just about any topic—all in minutes. Your reports are presented in an immersive viewer that you can refine with Gemini and even open in Google Docs! It’s starting to roll out in English with Gemini Advanced as part of the Google One AI Premium Plan. Try it by selecting “Gemini 1.5 Pro with Deep Research” from the Gemini Advanced model drop-down.Why:Save hours of work with Deep Research, the most advanced way to research with Gemini. Instead of spending hours researching, let Gemini do the work for you – so you can get on to doing everything else.

Today we made Canvas available in 4o by default for all users, Free and Paid. Additionally, we launched a number of new capabilities for canvas, including:
Canvas in GPTs: Canvas can now be used with GPTs when enabled in the GPT creator. This toggle will be enabled for newly created GPTs by default.
Python code execution: You can now execute Python code in a canvas. ChatGPT will take a pass on fixing bugs in your code and provide comments on errors.​Canvas shortcut: You can now paste content into ChatGPT and instantly open it in canvas via a shortcut in the upper right corner of the composer.Canvas in Toolbox: Canvas has been added as an option in the toolbox.

Additional premade Gems available for Google Workspace customersWhat:We're excited to announce the launch of a series of new premade Gems, designed to give Gemini for Google Workspace subscribers access to AI-powered expertise across a variety of work related use cases, starting in English. The list of premade Gems includes Hiring consultant, Copy creator, Sales pitch ideator, Sentiment analyzer, and Outreach specialist.Why:Business users need an AI solution with a deeper understanding of core business outcomes, and a focus on formulas, metrics and role profiles. These Gems provide advanced capabilities to help you tackle complex tasks and streamline your workflow.

Priority access with Gemini Advanced: Play chess with our new Chess GemWhat:The Chess champ Gem brings a new, conversational way to experience chess within the Gemini app. Explore different openings, banter with your AI opponent, and see if you can beat it in a game. This experimental Gem is available in English in the Gemini web app for Gemini Advanced subscribers via Google One AI Premium Plan.Why:Experience chess in a whole new way! Chess champ lets you test your talent against a language model. Enjoy a full game of chess and chatting.Chess piece SVG images byGreenChess.net, used under CC BY-SA 3.0. No changes were made to the original SVG images.

Expanding Workspace extensions to more languages: Keep and TasksWhat:Over the coming days, more users around the world will be able to connect with more apps and services in 9 languages (Korean, Japanese, Spanish, French, German, Bahasa Indonesia, Hindi, Portuguese, and Chinese), letting you set reminders with Google Tasks, make and refine lists with Google Keep, and engage with playlists in YouTube Music.Learn more about extensions.Why:We're continuing to build new ways for Gemini to connect to the apps you rely on every day. Through these extensions, Gemini can coordinate across your apps and take actions for you, better than ever.Read moreabout how Gemini works with your favorite Assistant actions, including details on upcoming improvements.

We are rolling out the following updates over the next two weeks to all ChatGPT users.
Sidebar redesign
New floating mode added with soft dismiss behaviorRecent conversations are now limited in the sidebar, with an unlimited infinite scroll flyout for all conversationsRecent GPTs & Pinned GPT's are now displayed below conversationsSettings are now always in the bottom of the sidebarA small settings icon was added in larger viewports when the sidebar is not openNew transitions were added to create a more immersive feel
Other updates for ChatGPT on Web
The core underpinnings of the site were revamped, offering much better support for a larger variety of devices and sizesInitiating a new conversation now scrolls it into view at the top of the screenInitiating a new conversation no longer auto scrolls to the bottom while the message is generatingThe sidebar when pinned can now stay open with an active Canvas if enough space is availableA new composer bar layout now fades content underneath it as you scroll with an updated look & feelThe new chat button has been moved to the left of the Model Picker to be easier to accessThe system icon in conversations has been removed to make additional horizontal spaceDall-E focused view has an updated layoutGPT Creator has an updated layout
Improved Mobile Web Experience
The experience with the on-screen keyboard on mobile devices has been greatly improved across iOS & Android devicesThe new sidebar is always in floating mode and auto closes when switching threadsWe no longer focus the composer on mobile web when switching conversationsAn issue causing scroll to get stuck in certain situations should be resolved

**Model updates:**

- Released `gemini-exp-1121`, an even more powerful experimental Gemini API model.

**Model updates:**

- Updated the `gemini-1.5-flash-latest` and `gemini-1.5-flash` model aliases to use `gemini-1.5-flash-002`.
- Change to `top_k` parameter: The `gemini-1.5-flash-002` model supports `top_k` values between 1 and 41 (exclusive). Values greater than 40 will be changed to 40.

Priority access with Gemini Advanced: Ask Gemini to remember the things you care about, and get help that’s unique to you.What:Starting today, you canask Gemini to rememberyour interests and preferences, whether it’s about your work, your hobbies, or your general aspirations in life. This helps Gemini provide even more helpful and relevant responses, tailored precisely to your needs. Think of it as giving Gemini a user manual, designed by you. You can share info and manage info saved with Gemini either through natural conversation or on the dedicated"Saved Info" page. You’re in control: easily view, edit, or delete any information you’ve shared with Gemini, and Gemini will display when it makes use of your saved info. Define how you want Gemini to interact with you, and it will adapt accordingly, giving you full authority over the information it saves and uses. The experience is available in English with Gemini Advanced as part of the Google One AI Premium Plan.Why:Saving info about your life and work empowers you to shape Gemini and unlock new levels of efficiency and creativity. Get more consistent, predictible results without repeating the same details, maintain control over your data, and experience Gemini that seemingly integrates into your workflow. Whether you’re a writer, developer, student, or someone who simply wants more control, now you can make Gemini truly your own.

Starting today, we’re beginning to roll out Advanced Voice Mode on web (already available on mobile and desktop apps). You can now start a voice chat on chatgpt.com on your desktop and have real-time, natural conversations with ChatGPT while doing tasks like shopping, planning, writing, and brainstorming.
We’re starting to roll out to all paid (Plus, Team, Enterprise, and Edu) users today, and expect it to take a few days.

Expanding the Gemini app as a core service with enterprise-grade data protection to more business and education customersWhat:The Gemini app (gemini.google.com) with enterprise-grade data protection is now included inmore Google Workspace editions.Why:By extending access to the Gemini app, more employees, educators and students can save time, deliver higher quality work, and learn confidently with a secure, AI-powered assistant at work or at school.

Try the new Gemini app on your iPhoneWhat:Today, we're launching a dedicated Gemini app on iPhones! Enjoy Gemini Live, create stunning images, easily find information across your favorite Google apps like YouTube, Gmail, Maps, and more. Need help solving a problem? Simply take a picture and ask Gemini questions about it. To get started, download the app from theApp Store.Learn more about language, country, device, and account availability in theHelp Center.Why:We're making it easy to access Gemini on your iPhone, including the latest experiences like Gemini Live and image generation.

Add files when creating your GemsWhat:Gemini Advanced subscribers can now upload files when creating a Gem, equipping the Gem to provide more tailored and contextually relevant responses. Starting in English, this feature is available for Gemini Advanced subscribers via Google One and Google Workspace.Why:Files serve as source material to help your Gems provide accurate and relevant responses. Referencing your files in your Gems can unlock a new level of customization, such as answering questions based on your files, assisting in content creation, or addressing business needs.Launching Gemini to Google Workspace for Education teen studentsWhat:Google Workspace for Education users 13+ (or theapplicable age in their country) can now access the Gemini app with added data protection. Education administrators manage access settings for these users via the Google Workspace Admin console.Why:Google is committed tomaking AI helpful for everyone, in the classroom and beyond. We want to both prepare teens with the skills and tools they need to thrive in a future where GenAI exists and help them learn how this technology can be used to unlock creativity and facilitate learning. Gemini can provide guided support to help students learn more confidently with in-the-moment assistance, practice materials and real-time feedback and ideas.

Expanding Workspace extensions in Beta for Google Workspace customers: Calendar, Keep and TasksWhat:Extensions are the tools that connect Gemini to other apps and services you rely on, letting you pull information and complete tasks directly from Gemini. Users accessing the Gemini app as a core service via their Google Workspace subscription or a Gemini for Workspace add-on can now use the Calendar, Keep and Tasks Workspace extensions in Beta in order to take actions, such as scheduling meetings, directly from the Gemini app.Why:Extensions help provide more contextual and relevant responses to your prompts and take certain actions, enhancing productivity and collaboration with the Gemini app.Access to Imagen 3 now available for Google Workspace customersWhat:Users accessing the Gemini app via their Google Workspace subscription or a Gemini for Workspace add-on can now create stunning images in Gemini with Imagen 3, our highest quality text-to-image model.And starting in English, Gemini for Workspace add-on subscribers unlock the added capability of generating images featuring people, empowering even more variety in your creations.Why:As we continue to build Gemini responsibly, we’re expanding access to more user profiles.Gemini is now SOC 2 and SOC 3 compliant for Google Workspace customersWhat:For Google Workspace users accessing the Gemini app as a core service, Gemini is now SOC 2 and SOC 3 compliant. Awarded by a third party (American Institute of Certified Public Accountants (AICPA)), SOC 2 and SOC 3 compliance ensures that sensitive business data is handled securely.Why:Users can be confident that Gemini meets the industry standard for handling financial data, data security, availability, processing integrity, confidentiality and privacy.

Introducing Imagen 3What:Create stunning images in Gemini with Imagen 3, our highest quality text-to-image model yet. Simply describe what you imagine, and watch as your ideas transform into visuals, bursting with vivid details and realism, in seconds.And starting in English, Gemini Advanced subscribers unlock the added capability of generating images featuring people, empowering even more variety in your creations.Why:Your imagination is limitless, and we want to place the power of creativity in your hands. We're also expanding image generation to more countries and languages, so even more people can bring their ideas to life with Gemini. While this model represents a leap forward in image generation quality and accuracy, we're constantly learning and will continue to improve to provide you the best experience possible.

Gemini can access helpful information from more apps and servicesWhat:Over the coming days, Gemini will connect to more apps and services, letting you set reminders with Google Tasks, make and refine lists with Google Keep, and engage with playlists in YouTube Music. Learn more about extensions.Learn more about extensions.Why:We’re continuing to build new ways for Gemini to connect to the apps you rely on every day. Through these extensions, Gemini can coordinate across your apps and take actions for you, better than ever.Read moreabout how Gemini works with your favorite Assistant actions, including details on upcoming improvements.

Gemini 1.5 Pro in Gemini Advanced just became more capableWhat:Gemini Advanced, with a chat optimized version of 1.5 Pro-002, now provides better and more accurate responses for prompts related to math and exploring complex topics that invite thoughtful conversation. Whether you’re providing detailed, multi-step instructions, or tackling advanced mathematical calculations, Gemini Advanced will help you navigate these challenges with greater ease.Why:We remain committed to rapid development and delivering the best of Gemini to our users. Through continuous model training and valuable user feedback, we’ve further enhanced the capabilities of Gemini 1.5 Pro, continuing to make Gemini Advanced better over time.Upgrade to Gemini Advanced

Priority access with Gemini Advanced: Upload your code filesWhat:In May, we upgraded Gemini Advanced to a 1 million token context window and added the ability to upload files and get answers and insights about documents. Today, we are adding the ability to upload multiple code files directly from Google Drive or your device to get help understanding, modifying, or debugging your code. We supportmost code file formatslike C, Python, SQL, and more.Why:Elevate your coding experience and accelerate development with Gemini Advanced's 1M token context window, now capable of processing up to 30k lines of code. Get assistance on complex coding questions, saving time and boosting productivity.

**Model updates:**

- Released `gemini-1.5-pro-002` and `gemini-1.5-flash-002`, two new stable versions of Gemini 1.5 Pro and 1.5 Flash, for general availability.
- Updated the `gemini-1.5-pro-latest` model code to use `gemini-1.5-pro-002` and the `gemini-1.5-flash-latest` model code to use `gemini-1.5-flash-002`.
- Released `gemini-1.5-flash-8b-exp-0924` to replace `gemini-1.5-flash-8b-exp-0827`.
- Released the [civic integrity safety filter](https://ai.google.dev/gemini-api/docs/safety-settings#safety-filters) for the Gemini API and AI Studio.
- Released support for two new parameters for Gemini 1.5 Pro and 1.5 Flash in Python and NodeJS: [`frequencyPenalty`](https://ai.google.dev/api/generate-content#FIELDS.frequency_penalty) and [`presencePenalty`](https://ai.google.dev/api/generate-content#FIELDS.presence_penalty).