Generate text using the Gemini API

You can ask aGemini model to generate text from a text-only prompt ora multimodal prompt. When you useFirebase AI Logic, you can make thisrequest directly from your app.

Multimodal prompts can include multiple types of input(like text along with images, PDFs, plain-text files, audio, and video).

This guide shows how to generate text from a text-only prompt and from a basicmultimodal prompt that includes a file.

Jump to code for text-only input Jump to code for multimodal input Jump to code for streamed responses


See other guides for additional options for working with text
Generate structured outputMulti-turn chatBidirectional streamingGenerate text on-deviceGenerate images from text

Before you begin

Click yourGemini API provider to view provider-specific content and code on this page.

If you haven't already, complete thegetting started guide, which describes how toset up your Firebase project, connect your app to Firebase, add the SDK,initialize the backend service for your chosenGemini API provider, andcreate aGenerativeModel instance.

This guide assumes you're using the latestFirebase AI Logic SDKs. If you're still using the "Vertex AI in Firebase" SDKs, see themigration guide.

For testing and iterating on your prompts, we recommend usingGoogle AI Studio.

Generate text from text-only input

Before trying this sample, complete theBefore you begin section of this guide to set up your project and app.
In that section, you'll also click a button for your chosenGemini API provider so that you see provider-specific content on this page.

You can ask aGemini model to generate text by prompting with text-onlyinput.

Swift

You can callgenerateContent()to generate text from text-only input.

importFirebaseAI// Initialize the Gemini Developer API backend serviceletai=FirebaseAI.firebaseAI(backend:.googleAI())// Create a `GenerativeModel` instance with a model that supports your use caseletmodel=ai.generativeModel(modelName:"gemini-2.5-flash")// Provide a prompt that contains textletprompt="Write a story about a magic backpack."// To generate text output, call generateContent with the text inputletresponse=tryawaitmodel.generateContent(prompt)print(response.text??"No text in response.")

Kotlin

You can callgenerateContent()to generate text from text-only input.

For Kotlin, the methods in this SDK are suspend functions and need to be calledfrom aCoroutine scope.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casevalmodel=Firebase.ai(backend=GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash")// Provide a prompt that contains textvalprompt="Write a story about a magic backpack."// To generate text output, call generateContent with the text inputvalresponse=model.generateContent(prompt)print(response.text)

Java

You can callgenerateContent()to generate text from text-only input.

For Java, the methods in this SDK return aListenableFuture.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use caseGenerativeModelai=FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash");// Use the GenerativeModelFutures Java compatibility layer which offers// support for ListenableFuture and Publisher APIsGenerativeModelFuturesmodel=GenerativeModelFutures.from(ai);// Provide a prompt that contains textContentprompt=newContent.Builder().addText("Write a story about a magic backpack.").build();// To generate text output, call generateContent with the text inputListenableFuture<GenerateContentResponse>response=model.generateContent(prompt);Futures.addCallback(response,newFutureCallback<GenerateContentResponse>(){@OverridepublicvoidonSuccess(GenerateContentResponseresult){StringresultText=result.getText();System.out.println(resultText);}@OverridepublicvoidonFailure(Throwablet){t.printStackTrace();}},executor);

Web

You can callgenerateContent()to generate text from text-only input.

import{initializeApp}from"firebase/app";import{getAI,getGenerativeModel,GoogleAIBackend}from"firebase/ai";// TODO(developer) Replace the following with your app's Firebase configuration// See: https://firebase.google.com/docs/web/learn-more#config-objectconstfirebaseConfig={// ...};// Initialize FirebaseAppconstfirebaseApp=initializeApp(firebaseConfig);// Initialize the Gemini Developer API backend serviceconstai=getAI(firebaseApp,{backend:newGoogleAIBackend()});// Create a `GenerativeModel` instance with a model that supports your use caseconstmodel=getGenerativeModel(ai,{model:"gemini-2.5-flash"});// Wrap in an async function so you can use awaitasyncfunctionrun(){// Provide a prompt that contains textconstprompt="Write a story about a magic backpack."// To generate text output, call generateContent with the text inputconstresult=awaitmodel.generateContent(prompt);constresponse=result.response;consttext=response.text();console.log(text);}run();

Dart

You can callgenerateContent() to generate text from text-only input.

import'package:firebase_ai/firebase_ai.dart';import'package:firebase_core/firebase_core.dart';import'firebase_options.dart';// Initialize FirebaseAppawaitFirebase.initializeApp(options:DefaultFirebaseOptions.currentPlatform,);// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casefinalmodel=FirebaseAI.googleAI().generativeModel(model:'gemini-2.5-flash');// Provide a prompt that contains textfinalprompt=[Content.text('Write a story about a magic backpack.')];// To generate text output, call generateContent with the text inputfinalresponse=awaitmodel.generateContent(prompt);print(response.text);

Unity

You can callGenerateContentAsync()to generate text from text-only input.

usingFirebase;usingFirebase.AI;// Initialize the Gemini Developer API backend servicevarai=FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());// Create a `GenerativeModel` instance with a model that supports your use casevarmodel=ai.GetGenerativeModel(modelName:"gemini-2.5-flash");// Provide a prompt that contains textvarprompt="Write a story about a magic backpack.";// To generate text output, call GenerateContentAsync with the text inputvarresponse=awaitmodel.GenerateContentAsync(prompt);UnityEngine.Debug.Log(response.Text??"No text in response.");

Learn how to choose amodelappropriate for your use case and app.

Generate text from text-and-file (multimodal) input

Before trying this sample, complete theBefore you begin section of this guide to set up your project and app.
In that section, you'll also click a button for your chosenGemini API provider so that you see provider-specific content on this page.

You can ask aGemini model togenerate text by prompting with text and a file—providing eachinput file'smimeType and the file itself. Findrequirements and recommendations for input fileslater on this page.

The following example shows the basics of how to generate text from a file inputby analyzing a single video file provided as inline data (base64-encoded file).

Note that this example shows providing the file inline, but the SDKs alsosupportproviding a YouTube URL.

Need a sample video file?

You can use this publicly available file with a MIME type ofvideo/mp4(view or download file).https://storage.googleapis.com/cloud-samples-data/video/animals.mp4

Important:The total request size limit is 20 MB. To send large files, review theoptions for providing files in multimodal requests.

Swift

You can callgenerateContent()to generate text from multimodal input of text and video files.

importFirebaseAI// Initialize the Gemini Developer API backend serviceletai=FirebaseAI.firebaseAI(backend:.googleAI())// Create a `GenerativeModel` instance with a model that supports your use caseletmodel=ai.generativeModel(modelName:"gemini-2.5-flash")// Provide the video as `Data` with the appropriate MIME type.letvideo=InlineDataPart(data:tryData(contentsOf:videoURL),mimeType:"video/mp4")// Provide a text prompt to include with the videoletprompt="What is in the video?"// To generate text output, call generateContent with the text and videoletresponse=tryawaitmodel.generateContent(video,prompt)print(response.text??"No text in response.")

Kotlin

You can callgenerateContent()to generate text from multimodal input of text and video files.

For Kotlin, the methods in this SDK are suspend functions and need to be calledfrom aCoroutine scope.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casevalmodel=Firebase.ai(backend=GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash")valcontentResolver=applicationContext.contentResolvercontentResolver.openInputStream(videoUri).use{stream->stream?.let{valbytes=stream.readBytes()// Provide a prompt that includes the video specified above and textvalprompt=content{inlineData(bytes,"video/mp4")text("What is in the video?")}// To generate text output, call generateContent with the promptvalresponse=model.generateContent(prompt)Log.d(TAG,response.text?:"")}}

Java

You can callgenerateContent()to generate text from multimodal input of text and video files.

For Java, the methods in this SDK return aListenableFuture.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use caseGenerativeModelai=FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash");// Use the GenerativeModelFutures Java compatibility layer which offers// support for ListenableFuture and Publisher APIsGenerativeModelFuturesmodel=GenerativeModelFutures.from(ai);ContentResolverresolver=getApplicationContext().getContentResolver();try(InputStreamstream=resolver.openInputStream(videoUri)){FilevideoFile=newFile(newURI(videoUri.toString()));intvideoSize=(int)videoFile.length();byte[]videoBytes=newbyte[videoSize];if(stream!=null){stream.read(videoBytes,0,videoBytes.length);stream.close();// Provide a prompt that includes the video specified above and textContentprompt=newContent.Builder().addInlineData(videoBytes,"video/mp4").addText("What is in the video?").build();// To generate text output, call generateContent with the promptListenableFuture<GenerateContentResponse>response=model.generateContent(prompt);Futures.addCallback(response,newFutureCallback<GenerateContentResponse>(){@OverridepublicvoidonSuccess(GenerateContentResponseresult){StringresultText=result.getText();System.out.println(resultText);}@OverridepublicvoidonFailure(Throwablet){t.printStackTrace();}},executor);}}catch(IOExceptione){e.printStackTrace();}catch(URISyntaxExceptione){e.printStackTrace();}

Web

You can callgenerateContent()to generate text from multimodal input of text and video files.

import{initializeApp}from"firebase/app";import{getAI,getGenerativeModel,GoogleAIBackend}from"firebase/ai";// TODO(developer) Replace the following with your app's Firebase configuration// See: https://firebase.google.com/docs/web/learn-more#config-objectconstfirebaseConfig={// ...};// Initialize FirebaseAppconstfirebaseApp=initializeApp(firebaseConfig);// Initialize the Gemini Developer API backend serviceconstai=getAI(firebaseApp,{backend:newGoogleAIBackend()});// Create a `GenerativeModel` instance with a model that supports your use caseconstmodel=getGenerativeModel(ai,{model:"gemini-2.5-flash"});// Converts a File object to a Part object.asyncfunctionfileToGenerativePart(file){constbase64EncodedDataPromise=newPromise((resolve)=>{constreader=newFileReader();reader.onloadend=()=>resolve(reader.result.split(',')[1]);reader.readAsDataURL(file);});return{inlineData:{data:awaitbase64EncodedDataPromise,mimeType:file.type},};}asyncfunctionrun(){// Provide a text prompt to include with the videoconstprompt="What do you see?";constfileInputEl=document.querySelector("input[type=file]");constvideoPart=awaitfileToGenerativePart(fileInputEl.files[0]);// To generate text output, call generateContent with the text and videoconstresult=awaitmodel.generateContent([prompt,videoPart]);constresponse=result.response;consttext=response.text();console.log(text);}run();

Dart

You can callgenerateContent() to generate text from multimodal input of text and video files.

import'package:firebase_ai/firebase_ai.dart';import'package:firebase_core/firebase_core.dart';import'firebase_options.dart';// Initialize FirebaseAppawaitFirebase.initializeApp(options:DefaultFirebaseOptions.currentPlatform,);// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casefinalmodel=FirebaseAI.googleAI().generativeModel(model:'gemini-2.5-flash');// Provide a text prompt to include with the videofinalprompt=TextPart("What's in the video?");// Prepare video for inputfinalvideo=awaitFile('video0.mp4').readAsBytes();// Provide the video as `Data` with the appropriate mimetypefinalvideoPart=InlineDataPart('video/mp4',video);// To generate text output, call generateContent with the text and imagesfinalresponse=awaitmodel.generateContent([Content.multi([prompt,...videoPart])]);print(response.text);

Unity

You can callGenerateContentAsync()to generate text from multimodal input of text and video files.

usingFirebase;usingFirebase.AI;// Initialize the Gemini Developer API backend servicevarai=FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());// Create a `GenerativeModel` instance with a model that supports your use casevarmodel=ai.GetGenerativeModel(modelName:"gemini-2.5-flash");// Provide the video as `data` with the appropriate MIME type.varvideo=ModelContent.InlineData("video/mp4",System.IO.File.ReadAllBytes(System.IO.Path.Combine(UnityEngine.Application.streamingAssetsPath,"yourVideo.mp4")));// Provide a text prompt to include with the videovarprompt=ModelContent.Text("What is in the video?");// To generate text output, call GenerateContentAsync with the text and videovarresponse=awaitmodel.GenerateContentAsync(new[]{video,prompt});UnityEngine.Debug.Log(response.Text??"No text in response.");

Learn how to choose amodelappropriate for your use case and app.

Stream the response

Before trying this sample, complete theBefore you begin section of this guide to set up your project and app.
In that section, you'll also click a button for your chosenGemini API provider so that you see provider-specific content on this page.

You can achieve faster interactions by not waiting for the entire result fromthe model generation, and instead use streaming to handle partial results.To stream the response, callgenerateContentStream.

View example: Stream generated text from text-only input

Swift

You can callgenerateContentStream()to stream generated text from text-only input.

importFirebaseAI// Initialize the Gemini Developer API backend serviceletai=FirebaseAI.firebaseAI(backend:.googleAI())// Create a `GenerativeModel` instance with a model that supports your use caseletmodel=ai.generativeModel(modelName:"gemini-2.5-flash")// Provide a prompt that contains textletprompt="Write a story about a magic backpack."// To stream generated text output, call generateContentStream with the text inputletcontentStream=trymodel.generateContentStream(prompt)fortryawaitchunkincontentStream{iflettext=chunk.text{print(text)}}

Kotlin

You can callgenerateContentStream()to stream generated text from text-only input.

For Kotlin, the methods in this SDK are suspend functions and need to be calledfrom aCoroutine scope.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casevalmodel=Firebase.ai(backend=GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash")// Provide a prompt that includes only textvalprompt="Write a story about a magic backpack."// To stream generated text output, call generateContentStream and pass in the promptvarresponse=""model.generateContentStream(prompt).collect{chunk->print(chunk.text)response+=chunk.text}

Java

You can callgenerateContentStream()to stream generated text from text-only input.

For Java, the streaming methods in this SDK return aPublisher type from theReactive Streams library.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use caseGenerativeModelai=FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash");// Use the GenerativeModelFutures Java compatibility layer which offers// support for ListenableFuture and Publisher APIsGenerativeModelFuturesmodel=GenerativeModelFutures.from(ai);// Provide a prompt that contains textContentprompt=newContent.Builder().addText("Write a story about a magic backpack.").build();// To stream generated text output, call generateContentStream with the text inputPublisher<GenerateContentResponse>streamingResponse=model.generateContentStream(prompt);// Subscribe to partial results from the responsefinalString[]fullResponse={""};streamingResponse.subscribe(newSubscriber<GenerateContentResponse>(){@OverridepublicvoidonNext(GenerateContentResponsegenerateContentResponse){Stringchunk=generateContentResponse.getText();fullResponse[0]+=chunk;}@OverridepublicvoidonComplete(){System.out.println(fullResponse[0]);}@OverridepublicvoidonError(Throwablet){t.printStackTrace();}@OverridepublicvoidonSubscribe(Subscriptions){}});

Web

You can callgenerateContentStream()to stream generated text from text-only input.

import{initializeApp}from"firebase/app";import{getAI,getGenerativeModel,GoogleAIBackend}from"firebase/ai";// TODO(developer) Replace the following with your app's Firebase configuration// See: https://firebase.google.com/docs/web/learn-more#config-objectconstfirebaseConfig={// ...};// Initialize FirebaseAppconstfirebaseApp=initializeApp(firebaseConfig);// Initialize the Gemini Developer API backend serviceconstai=getAI(firebaseApp,{backend:newGoogleAIBackend()});// Create a `GenerativeModel` instance with a model that supports your use caseconstmodel=getGenerativeModel(ai,{model:"gemini-2.5-flash"});// Wrap in an async function so you can use awaitasyncfunctionrun(){// Provide a prompt that contains textconstprompt="Write a story about a magic backpack."// To stream generated text output, call generateContentStream with the text inputconstresult=awaitmodel.generateContentStream(prompt);forawait(constchunkofresult.stream){constchunkText=chunk.text();console.log(chunkText);}console.log('aggregated response: ',awaitresult.response);}run();

Dart

You can callgenerateContentStream() to stream generated text from text-only input.

import'package:firebase_ai/firebase_ai.dart';import'package:firebase_core/firebase_core.dart';import'firebase_options.dart';// Initialize FirebaseAppawaitFirebase.initializeApp(options:DefaultFirebaseOptions.currentPlatform,);// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casefinalmodel=FirebaseAI.googleAI().generativeModel(model:'gemini-2.5-flash');// Provide a prompt that contains textfinalprompt=[Content.text('Write a story about a magic backpack.')];// To stream generated text output, call generateContentStream with the text inputfinalresponse=model.generateContentStream(prompt);awaitfor(finalchunkinresponse){print(chunk.text);}

Unity

You can callGenerateContentStreamAsync()to stream generated text from text-only input.

usingFirebase;usingFirebase.AI;// Initialize the Gemini Developer API backend servicevarai=FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());// Create a `GenerativeModel` instance with a model that supports your use casevarmodel=ai.GetGenerativeModel(modelName:"gemini-2.5-flash");// Provide a prompt that contains textvarprompt="Write a story about a magic backpack.";// To stream generated text output, call GenerateContentStreamAsync with the text inputvarresponseStream=model.GenerateContentStreamAsync(prompt);awaitforeach(varresponseinresponseStream){if(!string.IsNullOrWhiteSpace(response.Text)){UnityEngine.Debug.Log(response.Text);}}

Learn how to choose amodelappropriate for your use case and app.

View example: Stream generated text from multimodal input

Swift

You can callgenerateContentStream()to stream generated text from multimodal input of text and a single video.

importFirebaseAI// Initialize the Gemini Developer API backend serviceletai=FirebaseAI.firebaseAI(backend:.googleAI())// Create a `GenerativeModel` instance with a model that supports your use caseletmodel=ai.generativeModel(modelName:"gemini-2.5-flash")// Provide the video as `Data` with the appropriate MIME typeletvideo=InlineDataPart(data:tryData(contentsOf:videoURL),mimeType:"video/mp4")// Provide a text prompt to include with the videoletprompt="What is in the video?"// To stream generated text output, call generateContentStream with the text and videoletcontentStream=trymodel.generateContentStream(video,prompt)fortryawaitchunkincontentStream{iflettext=chunk.text{print(text)}}

Kotlin

You can callgenerateContentStream()to stream generated text from multimodal input of text and a single video.

For Kotlin, the methods in this SDK are suspend functions and need to be calledfrom aCoroutine scope.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casevalmodel=Firebase.ai(backend=GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash")valcontentResolver=applicationContext.contentResolvercontentResolver.openInputStream(videoUri).use{stream->stream?.let{valbytes=stream.readBytes()// Provide a prompt that includes the video specified above and textvalprompt=content{inlineData(bytes,"video/mp4")text("What is in the video?")}// To stream generated text output, call generateContentStream with the promptvarfullResponse=""model.generateContentStream(prompt).collect{chunk->Log.d(TAG,chunk.text?:"")fullResponse+=chunk.text}}}

Java

You can callgenerateContentStream()to stream generated text from multimodal input of text and a single video.

For Java, the streaming methods in this SDK return aPublisher type from theReactive Streams library.
// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use caseGenerativeModelai=FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel("gemini-2.5-flash");// Use the GenerativeModelFutures Java compatibility layer which offers// support for ListenableFuture and Publisher APIsGenerativeModelFuturesmodel=GenerativeModelFutures.from(ai);ContentResolverresolver=getApplicationContext().getContentResolver();try(InputStreamstream=resolver.openInputStream(videoUri)){FilevideoFile=newFile(newURI(videoUri.toString()));intvideoSize=(int)videoFile.length();byte[]videoBytes=newbyte[videoSize];if(stream!=null){stream.read(videoBytes,0,videoBytes.length);stream.close();// Provide a prompt that includes the video specified above and textContentprompt=newContent.Builder().addInlineData(videoBytes,"video/mp4").addText("What is in the video?").build();// To stream generated text output, call generateContentStream with the promptPublisher<GenerateContentResponse>streamingResponse=model.generateContentStream(prompt);finalString[]fullResponse={""};streamingResponse.subscribe(newSubscriber<GenerateContentResponse>(){@OverridepublicvoidonNext(GenerateContentResponsegenerateContentResponse){Stringchunk=generateContentResponse.getText();fullResponse[0]+=chunk;}@OverridepublicvoidonComplete(){System.out.println(fullResponse[0]);}@OverridepublicvoidonError(Throwablet){t.printStackTrace();}@OverridepublicvoidonSubscribe(Subscriptions){}});}}catch(IOExceptione){e.printStackTrace();}catch(URISyntaxExceptione){e.printStackTrace();}

Web

You can callgenerateContentStream()to stream generated text from multimodal input of text and a single video.

import{initializeApp}from"firebase/app";import{getAI,getGenerativeModel,GoogleAIBackend}from"firebase/ai";// TODO(developer) Replace the following with your app's Firebase configuration// See: https://firebase.google.com/docs/web/learn-more#config-objectconstfirebaseConfig={// ...};// Initialize FirebaseAppconstfirebaseApp=initializeApp(firebaseConfig);// Initialize the Gemini Developer API backend serviceconstai=getAI(firebaseApp,{backend:newGoogleAIBackend()});// Create a `GenerativeModel` instance with a model that supports your use caseconstmodel=getGenerativeModel(ai,{model:"gemini-2.5-flash"});// Converts a File object to a Part object.asyncfunctionfileToGenerativePart(file){constbase64EncodedDataPromise=newPromise((resolve)=>{constreader=newFileReader();reader.onloadend=()=>resolve(reader.result.split(',')[1]);reader.readAsDataURL(file);});return{inlineData:{data:awaitbase64EncodedDataPromise,mimeType:file.type},};}asyncfunctionrun(){// Provide a text prompt to include with the videoconstprompt="What do you see?";constfileInputEl=document.querySelector("input[type=file]");constvideoPart=awaitfileToGenerativePart(fileInputEl.files[0]);// To stream generated text output, call generateContentStream with the text and videoconstresult=awaitmodel.generateContentStream([prompt,videoPart]);forawait(constchunkofresult.stream){constchunkText=chunk.text();console.log(chunkText);}}run();

Dart

You can callgenerateContentStream() to stream generated text from multimodal input of text and a single video.

import'package:firebase_ai/firebase_ai.dart';import'package:firebase_core/firebase_core.dart';import'firebase_options.dart';// Initialize FirebaseAppawaitFirebase.initializeApp(options:DefaultFirebaseOptions.currentPlatform,);// Initialize the Gemini Developer API backend service// Create a `GenerativeModel` instance with a model that supports your use casefinalmodel=FirebaseAI.googleAI().generativeModel(model:'gemini-2.5-flash');// Provide a text prompt to include with the videofinalprompt=TextPart("What's in the video?");// Prepare video for inputfinalvideo=awaitFile('video0.mp4').readAsBytes();// Provide the video as `Data` with the appropriate mimetypefinalvideoPart=InlineDataPart('video/mp4',video);// To stream generated text output, call generateContentStream with the text and imagefinalresponse=awaitmodel.generateContentStream([Content.multi([prompt,videoPart])]);awaitfor(finalchunkinresponse){print(chunk.text);}

Unity

You can callGenerateContentStreamAsync()to stream generated text from multimodal input of text and a single video.

usingFirebase;usingFirebase.AI;// Initialize the Gemini Developer API backend servicevarai=FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());// Create a `GenerativeModel` instance with a model that supports your use casevarmodel=ai.GetGenerativeModel(modelName:"gemini-2.5-flash");// Provide the video as `data` with the appropriate MIME type.varvideo=ModelContent.InlineData("video/mp4",System.IO.File.ReadAllBytes(System.IO.Path.Combine(UnityEngine.Application.streamingAssetsPath,"yourVideo.mp4")));// Provide a text prompt to include with the videovarprompt=ModelContent.Text("What is in the video?");// To stream generated text output, call GenerateContentStreamAsync with the text and videovarresponseStream=model.GenerateContentStreamAsync(new[]{video,prompt});awaitforeach(varresponseinresponseStream){if(!string.IsNullOrWhiteSpace(response.Text)){UnityEngine.Debug.Log(response.Text);}}

Learn how to choose amodelappropriate for your use case and app.


Requirements and recommendations for input image files

Important:The total request size limit is 20 MB. To send large files, review theoptions for providing files in multimodal requests.

Note that a file provided as inline data is encoded to base64 in transit, whichincreases the size of the request. You get an HTTP 413 error if a request istoo large.

SeeSupported input files and requirements for theVertex AI Gemini APIto learn detailed information about the following:

  • Different options for providing a file in a request(either inline or using the file's URL or URI)
  • Supported file types
  • Supported MIME types and how to specify them
  • Requirements and best practices for files and multimodal requests


What else can you do?

Try out other capabilities

Learn how to control content generation

You can also experiment with prompts and model configurations and even get agenerated code snippet usingGoogle AI Studio.

Learn more about the supported models

Learn about themodels available for various use casesand theirquotas andpricing.


Give feedback about your experience withFirebase AI Logic


Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-10-03 UTC.