Gemini Apps FAQ

Gemini gives you direct access to Google AI. Get help with writing, planning, learning and more.

How Gemini works

The simple answer

When you enter a prompt into Gemini, it replies with a response using the information that it already knows or fetches from other sources, such as other Google services.

The technical answer

Gemini gives you access to large language models

  • The language models learn by 'reading' trillions of words that help them pick up on patterns that make up language. This allows them to pick up on and reply to your questions using common language patterns
  • They are always learning, which means that they also learn from your prompts, responses and feedback
  • Gemini will make mistakes and might even say something offensive

Ways to use Gemini

Here are some prompt examples that you can try out:

  • 'Explain projectile motion using everyday examples'
  • 'Which came first: the chicken or the egg?'
  • 'Help me brainstorm a title for my short story'

Gemini isn't human

It doesn't have its own thoughts or feelings, even though it might sound like a human. Remember:

  • Gemini can't replace important people in your life, such as family, friends, teachers or doctors
  • Gemini can't do your work for you
  • Gemini can't make important life decisions for you

Want to know more?

Get to know the tech behind Gemini through this essential reading list

Generative AI is a type of machine learning model. Generative AI is not a human being. It can't think for itself or feel emotions. It's just great at finding patterns.

In the past, AI was used to understand and recommend information. Now, generative AI can also help us create new content, like images, music and code.

How machine learning models are trained

Machine learning models, including generative AI, learn through a process of observation and pattern matching known as training. For a model to understand what trainers are, it's trained on millions of photos of trainers. Over time, it recognises that trainers are objects that humans wear on their feet with laces, soles and a logo.

The model can use training to:

  • Take an input like 'Generate an image of trainers with a goat charm'.
  • Connect what it's learned about trainers, goats and charms.
  • Generate an image, even if it hasn't seen an image like that before.

How large language models power generative AI

Generative AI and large language models (LLMs) are part of the same technology. Generative AI can be trained on any type of data, but LLMs use words as their main source of training data.

Experiences powered by LLMs, like Gemini, can predict words that might come next based on your prompt and the text that it's generated so far. They're given flexibility to pick probable next words that match patterns that they get from training. This flexibility lets them generate creative responses.

If you prompt them to fill in the phrase 'Harry [blank]', they might predict that the next word is 'Styles' or 'Potter'.

Take a look at Five must-knows for generative AIOpens in a new window to learn more about generative AI.

You might have heard that AI technology like Gemini can sometimes hallucinate. That’s a strange term, but it basically just means that Gemini sometimes gets things wrong or says things that aren’t true. These hallucinations can sound real, and Gemini might even say them confidently.

What do AI hallucinations look like?

AI hallucinations, or this made-up info, could be things like:

  • Made-up facts. 'Cats are actually canines – like dogs.' (That’s not true! They’re felines.)
  • Made-up people. 'The first person to walk on Mars was Sundar Pichai.' (No human has been to Mars yet!)
  • Statistics. '47% of all statistics are made up.' (No one could know that!)
  • Or any type of info really!

What can I do about AI hallucinations?

There’s more about this in another question (Why can Gemini get things wrong?), but basically double-check Gemini’s responses.

One way to double-check Gemini’s responses is to use the Google button. You’ll see this under a response. The Google button uses Google Search to find content that’s likely to be similar to or likely to be different from statements generated by Gemini Apps. How to double-check responses Opens in a new window

Remember to use your best judgement

Gemini is not a doctor, lawyer or a professional. It can help you learn how things work, but don’t rely on it for advice. If you need help or something doesn't seem right, talk to a trusted adult.

Generative AI and all of its possibilities are exciting, but it's still new. Gemini will make mistakes. Even though it's getting better, Gemini could provide inaccurate information or could even make offensive statements.

Double-check the information that you get from Gemini

Gemini has tools to help you identify potentially inaccurate statements. One way to double-check Gemini's responses is to use the Google button. This uses Google Search to find content that helps you to assess and further research the information that you get from Gemini.

Gemini's double-check feature can make mistakes

For example, the feature may show that Google Search found content that makes a similar statement to Gemini's. But the content may actually contradict Gemini. The web content may be inaccurate, too. You should read, review and evaluate the content identified by the double-check feature carefully, as well as its context.

Help make Gemini better

Google relies on people to give feedback on answers that don't seem right. That's why Gemini has built-in features to collect your feedback.

  • Mark good responses
  • Mark bad ones
  • Use the Report legal issue button where appropriate

Be mindful of how you use Gemini

You have an opportunity to shape Gemini for others. Gemini will use the conversations that you have to improve future responses for everyone, so don't enter anything that you wouldn't want a reviewer to see or Google to use. Learn more at the Gemini Apps Privacy HubOpens in a new window

Sometimes, Gemini shows you sources and related content within and below its response. These include web sources with similar information and links for you to dig deeper. Sources and related content may include websites that Gemini quoted or that relate to parts of its response, files that you've uploaded or documents or emails from Google Workspace (if you've turned on the Google Workspace extension).

Gemini is designed to generate original content, but if it does directly quote at length from a web page, you'll see a quotation mark with the cited source and a link to that page. Sometimes, the same public content may be found on multiple web pages and Gemini attempts to point to a popular source. In the case of citations to code repositories, the citation may also reference an applicable open-source licence.

If Gemini's response includes a thumbnail of an image from the web, it will show the source and provide a link directly to it.

Even when Gemini shows sources or related content, it can still get things wrong. To get help double-checking the information in Gemini's response using Google Search, click the Google button. When a statement can be evaluated, you'll see it highlighted in Gemini's response and can click to learn more.

We'll continue to learn, iterate and improve the experience as we get feedback from a range of stakeholders, including people like you, publishers, creators and more.

Gemini can hallucinate and present inaccurate information as factual. One example is that Gemini often misrepresents how it works. We've seen this occur in a number of instances – for example, in response to prompts asking how it was trained or how it carries out various functions (like citing sources or providing fresh information).

Gemini responses may also occasionally claim that it uses personal information from Gmail or other private apps and services to train Gemini's generative machine-learning technologies. That's not accurate, and as an LLM interface, Gemini does not have the ability to determine these facts. We do not use personal data from your Gmail or other private apps and services to train Gemini's generative machine-learning technologies. More information about how we keep your data private, safe and secure can be found in the Google Privacy PolicyOpens in a new window.

We want to be as transparent as possible about the limitations of LLMs, including providing disclaimers within the Gemini experience. If you see a hallucination or something that isn't accurate, please click the thumbs-down button and provide your feedback. That's one of the ways in which Gemini will learn and improve.

Yes, Gemini can help with coding and topics about coding, but you are responsible for your use of the code or coding explanations. So, you should use discretion and carefully test and review all code for errors, bugs and vulnerabilities before relying on it. Code may also be subject to an open source license and Gemini provides related information. Read more about .

Gemini's ability to hold context is purposefully limited for now. As Gemini continues to learn, its ability to hold context during longer conversations will improve.

Google aspires to create technologies that solve important problems and help people in their daily lives. We are optimistic about the incredible potential for AI and other advanced technologies to empower people, widely benefit current and future generations and work for the common good. We believe that these technologies will promote innovation, and further our mission to organise the world's information and make it universally accessible and useful.

These same technologies also raise important challenges that need to be addressed clearly, thoughtfully and affirmatively. These AI PrinciplesOpens in a new window are a commitment to develop technology responsibly. Learn more about AI principles at GoogleOpens in a new window

One important part of developing responsibly is expanding participation, so more people can experience Gemini, provide feedback and help Gemini improve. You can rate responses as good or bad and send feedback each time Gemini responds.

For countries where Gemini is available:

Learn more about Gemini mobile app availability Opens in a new window

At the moment, Gemini Apps may not be available in your country, but we will be rolling out to new languages and countries over time.

Use Gemini on your work or school account

To use Gemini on your work or school Google Account, access must be enabled by your administrator. Learn more about how to use Gemini on your work or school Google Account.Opens in a new window.

Use Gemini Advanced

Gemini Advanced with our most capable AI models is available for over-18 users only as part of a new Google One AI Premium planOpens in a new window that also includes:

  • Gemini in Gmail, Docs and more
  • 2 TB of storage
  • and other benefits

You also need a personal Google Account that you manage on your own. How to upgradeOpens in a new window

Learn more about Gemini web app requirementsOpens in a new window and mobile apps requirementsOpens in a new window

Gemini Apps is available in more than 40 languages, including: English, Japanese, Korean, Arabic, Bahasa Indonesia, Bengali, Bulgarian, Chinese (Simplified/Traditional), Croatian, Czech, Danish, Dutch, Estonian, Farsi, Finnish, French, German, Gujarati, Greek, Hebrew, Hindi, Hungarian, Italian, Kannada, Latvian, Lithuanian, Malayalam, Marathi, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu and Vietnamese. We are continuing to teach Gemini how to respond in even more languages.

Gemini Advanced is available and optimised in 40+ languages, and it will be rolling out to additional languages over time.

The Gemini mobile app is beginning to roll out to selected locations, languages and devices. Learn more about availabilityOpens in a new window

Gemini has usage limits that are designed to ensure an optimal experience for everyone. This means that we may, at times, have to cap the number of prompts and conversations that you can have within a specific time frame. Your capacity replenishes regularly, so you can get back to chatting with Gemini soon.

The number of prompts that you can use before hitting the limit varies and depends on factors like how long and complex your prompts are, the size and number of files that you upload, and the length of your conversations with Gemini.

We will also alert you when you are close to reaching your chat capacity for a given period.

We are committed to rolling out Gemini responsibly. Some features may not be available in all countries, territories and languages, but we will work on expanding availability over time.

The Google Terms of ServiceOpens in a new window and the Generative AI prohibited use policyOpens in a new window apply to this service. Bear in mind that if you export conversations from Gemini, the terms and policies of the service that you export to will apply to the copy. Go to the Gemini Apps Privacy HubOpens in a new window to learn more about how Google uses your Gemini Apps data.

Yes, Gemini Apps can fulfil your requests with tools, apps and services on your mobile devices and the web. For example, you can choose to connect Google Workspace, so that Gemini Apps can find, summarise or answer questions about your content from Docs, Drive and Gmail, or help you to manage notes and lists in Google Keep and reminders in Google Tasks.

Gemini Apps will choose the best extension to respond to your prompt or you can request a specific one. We are working continuously to help you connect more apps and improve your experience. Some features are still rolling out to more devices and languages. Learn more about your data and extensionsOpens in a new window.

You can turn off any of these extensions from the Extensions page.

To learn more about how Gemini works and how Google uses your Gemini Apps data, review the Gemini Apps Privacy HubOpens in a new window.

Tackle your most complex projects with Gemini Advanced, your pass to Google's next-gen AI. Experience our most capable AI models, priority access to new features, and a one million token context window.

Gemini Advanced with our most capable AI models is available only for users aged over 18, as part of a Google One AI Premium planOpens in a new window that also includes:

  • Gemini in Gmail, Docs and more
  • 2 TB of storage
  • and other benefits

You also need a personal Google Account that you manage on your own. How to upgradeOpens in a new window

Gemini Advanced with our most capable AI models is available for over-18 users only as part of a new Google One AI Premium planOpens in a new window that also includes:

  • Gemini in Gmail, Docs and more
  • 2 TB of storage
  • and other benefits

You also need a personal Google Account that you manage on your own.

If you're eligible, you can upgrade to Gemini Advanced nowOpens in a new window. You can also upgrade from inside Gemini Apps: you should see an upgrade button in the menu.

Yes, but there might be some feature differences between the Gemini mobile app and Gemini web app. Currently:

  • You can only create, edit or delete custom GemsOpens in a new window in the Gemini web app. You can use Gems in the Gemini web and mobile apps.

If you want to manage your Gemini Advanced subscription in the mobile app, tap your profile picture to access the Settings menu. Learn how to upgradeOpens in a new window.

We believe in using the right model for the right task. We use various models at hand for specific tasks based on what we think will provide the best experience.

With Gemini AdvancedOpens in a new window, you have access to our most capable AI models.

Gems are a simple way to customise Gemini for your specific needs. You can customise a pre-made Gem and create your own by listing specific instructions, detailed goals, how you want the responses to sound or even step-by-step workflows.

Gems are available in most languages for Gemini Advanced users and Gemini for Google Workspace add-on subscribers.

The Gemini mobile app is an AI assistant that's available on your phone.

Download the Gemini app on Android from the Google Play Store and on iOS from the App Store.

The Gemini mobile app is beginning to roll out to selected locations, languages and devices. Learn more about availabilityOpens in a new window

Gemini Live is a more natural way to have free-flowing voice conversations with Gemini on your phone. Express your thoughts freely. Interrupt, add details, ask follow-up questions or come back to the conversation later – Gemini listens, understands and adapts to your conversational style in real time.

Not all of the Gemini features are available in Gemini Live, but we are continuously working on improving the experience.

Learn how to go Live with GeminiOpens in a new window