The availability of generative AI models frequently changes — new, better models are released and older, less capable models are retired.
When you access generative AI models directly from a mobile or web app using Firebase AI Logic , it's critical that you configure your app to accommodate these frequent model changes. Not all of your users will update to the latest version of your app to start using the model you need them to use.
Firebase Remote Config lets you update parameter values in your app (like a model name) dynamically and remotely from the Firebase console, without the need to release a new version of your app.
Note that changing a model name is a critical use case for using Remote Config with Firebase AI Logic , but you can also use Remote Config to dynamically and even conditionally control parameters in your app , like model generation configuration (maximum tokens, temperature, etc.), safety settings, system instructions, and prompt data.
This guide describes how to implement Remote Config in your app, specifically to control the model name used in your app.
Step 1: Set the parameter value in the Firebase console
Create a Remote Config
client template and configure a model_name
parameter and its value to fetch and use in the app.
-
Open your Firebase project in the Firebase console. Then, from the navigation menu, expand Runand select Remote Config .
-
Ensure that Clientis selected from the Client/Serverselector at the top of the page.
-
Start a client template by clicking Create Configuration(or Add parameterif you've previously used client templates).
-
Define the
model_nameparameter:Parameter name Description Type Default value model_nameModel name. See available model names . String gemini-2.5-flash -
After adding this parameter, click Publish changes. If this is not a new Remote Config template, review the changes and click Publish changesagain.
Step 2: Add and initialize Remote Config in your app
Add the Remote Config library and set up Remote Config within your app.
Swift
As part of Firebase AI Logic setup , you've already added the Firebase SDK to your app, but will also need to add Remote Config .
-
In Xcode, with the project open, navigate to File > Add Package Dependencies.
-
Select firebase-ios-sdkand then click Add package.
-
From the Project navigator, select your app > Targets> your app.
-
From the Generaltab, scroll to Frameworks, Libraries, and Embedded Content.
-
Click +and choose FirebaseRemoteConfig, then click Add.
-
Add the
FirebaseRemoteConfigimport to your code:import FirebaseRemoteConfig -
Inside the appropriate class for your app, initialize Firebase and add Remote Config to your main application logic.
Here, you'll include Remote Config and the Remote Config real-time listener as imports so that the app can fetch new values in real-time, and add a minimum fetch interval:
let remoteConfig = RemoteConfig . remoteConfig () let settings = RemoteConfigSettings () settings . minimumFetchInterval = 3600 remoteConfig . configSettings = settings
Kotlin
-
Add the Remote Config dependency to your module (app-level) Gradle file (usually
app/build.gradle.ktsorapp/build.gradle):dependencies { implementation ( platform ( "com.google.firebase:firebase-bom:34.5.0" )) implementation ( "com.google.firebase:firebase-ai" ) implementation ( "com.google.firebase:firebase-config" ) // ... other dependencies } -
Add Remote Config to your main application logic. Here, you'll initialize Remote Config and add a minimum fetch interval:
val remoteConfig : FirebaseRemoteConfig = Firebase . remoteConfig val configSettings = remoteConfigSettings { minimumFetchIntervalInSeconds = 3600 } remoteConfig . setConfigSettingsAsync ( configSettings )
Java
-
Add the Remote Config dependency to your module (app-level) Gradle file (usually
app/build.gradle.ktsorapp/build.gradle):dependencies { implementation ( platform ( "com.google.firebase:firebase-bom:34.5.0" )) implementation ( "com.google.firebase:firebase-ai" ) implementation ( "com.google.firebase:firebase-config" ) // ... other dependencies } -
Add Remote Config to your main application logic. Here, you'll initialize Remote Config and add a minimum fetch interval:
FirebaseRemoteConfig mFirebaseRemoteConfig = FirebaseRemoteConfig . getInstance (); FirebaseRemoteConfigSettings configSettings = new FirebaseRemoteConfigSettings . Builder () . setMinimumFetchIntervalInSeconds ( 3600 ) . build (); mFirebaseRemoteConfig . setConfigSettingsAsync ( configSettings );
Web
-
Open your code in a text editor and import Remote Config :
import { getRemoteConfig } from 'firebase/remote-config' ; -
Inside your primary function and after the Firebase app is initialized for Firebase AI Logic SDK, initialize Remote Config :
// Initialize Remote Config and get a reference to the service const remoteConfig = getRemoteConfig ( app ); -
Set a minimum fetch interval:
remoteConfig . settings . minimumFetchIntervalMillis = 3600000 ;
Dart
-
From your Flutter project directory, install and add Remote Config using the following command:
flutter pub add firebase_remote_config -
Open
./lib/main.dartand add the import after the other imports you added to support Firebase AI Logic :import 'package:firebase_vertexai/firebase_ai.dart' ; import 'package:firebase_core/firebase_core.dart' ; import 'package:firebase_remote_config/firebase_remote_config.dart' ; -
Add the
_modelNamevariable to your app so that you can use it later:late final String _modelName ; late final String _systemInstructions ; late final String _prompt ; -
Get the Remote Config object instance and set the minimum fetch interval to allow for frequent refreshes. Make sure to add this after Firebase is initialized.
final remoteConfig = FirebaseRemoteConfig . instance ; await remoteConfig . setConfigSettings ( RemoteConfigSettings ( fetchTimeout: const Duration ( seconds: 3600 ), minimumFetchInterval: const Duration ( seconds: 3600 ), ));
Unity
-
Add Remote Config to your Unity project, following these instructions .
-
Get the Remote Config object instance and set the minimum fetch interval to allow for frequent refreshes. Make sure to add this after Firebase is initialized.
var remoteConfig = FirebaseRemoteConfig . DefaultInstance ; const int MillisecondsPerSecond = 1000 ; await remoteConfig . SetConfigSettingsAsync ( new ConfigSettings () { FetchTimeoutInMilliseconds = 3600 * MillisecondsPerSecond , MinimumFetchIntervalInMilliseconds = 3600 * MillisecondsPerSecond });
Step 3: Set the in-app parameter value
You should set in-app default parameter values in the Remote Config object. This ensures that your app behaves as expected even if it cannot fetch values from the Remote Config service.
Swift
-
In the Firebase console, open Remote Config .
-
In the Parameters tab, open the Menu, and select Download default values.
-
When prompted, enable .plist for iOS, then click Download file.
-
Save the file in the your application directory.
-
In Xcode, right-click on your app and select Add Files
-
Select remote_config_defaults.plist, then click Add.
-
Update your app code to reference the defaults file:
// Set default values for Remote Config parameters. remoteConfig . setDefaults ( fromPlist : "remote_config_defaults" )
Kotlin
-
From the Firebase console, open Remote Config .
-
In the Parameters tab, open the Menu, and select Download default values.
-
When prompted, enable .xml for Android, then click Download file.
-
Save the file in your app's XML resources directory.
-
Update your main activity file to add the defaults after the
configSettingsyou added previously:// Set default values for Remote Config parameters. remoteConfig . setDefaultsAsync ( R . xml . remote_config_defaults )
Java
-
In the Firebase console, open Remote Config .
-
In the Parameters tab, open the Menu, and select Download default values.
-
When prompted, enable .xml for Android, then click Download file.
-
Save the file in your app's XML resources directory.
-
Update your main activity file to add the defaults after the
configSettingsyou added previously:// Set default values for Remote Config parameters. mFirebaseRemoteConfig . setDefaultsAsync ( R . xml . remote_config_defaults );
Web
You can set the default value for the model name directly in your code:
// Set default values for Remote Config parameters.
remoteConfig
.
defaultConfig
=
{
model_name
:
'gemini-2.5-flash'
,
};
Dart
You can set the default value for the model name directly in your code:
// Set default values for Remote Config parameters.
remoteConfig
.
setDefaults
(
const
{
"model_name"
:
"gemini-2.5-flash"
});
Unity
You can set the default value for the model name directly in your code:
// Set default values for Remote Config parameters.
await
remoteConfig
.
SetDefaultsAsync
(
new
System
.
Collections
.
Generic
.
Dictionary<string
,
object
> ()
{
{
"model_name"
,
"gemini-2.5-flash"
}
}
);
Step 4: Fetch and activate the value
After setting the default value for the model name, add the following to fetch and activate values.
Swift
// Fetch and activate Remote Config
values
remoteConfig
.
fetchAndActivate
{
status
,
error
in
if
let
error
=
error
{
print
(
"Error fetching Remote Config
:
\(
error
.
localizedDescription
)
"
)
}
}
This should update the Remote Config object whenever a new Remote Config template is published.
Kotlin
// Fetch and activate Remote Config
values
remoteConfig
.
fetchAndActivate
()
.
addOnCompleteListener
(
this
)
{
task
-
>
if
(
task
.
isSuccessful
)
{
val
updated
=
task
.
result
Log
.
d
(
TAG
,
" Remote Config
values fetched and activated:
$
updated
"
)
}
else
{
Log
.
e
(
TAG
,
"Error fetching Remote Config
"
,
task
.
exception
)
}
}
Java
// Fetch and activate Remote Config
values
mFirebaseRemoteConfig
.
fetchAndActivate
()
.
addOnCompleteListener
(
this
,
new
OnCompleteListener<Boolean>
()
{
@Override
public
void
onComplete
(
@NonNull
Task<Boolean>
task
)
{
if
(
task
.
isSuccessful
())
{
boolean
updated
=
task
.
getResult
();
Log
.
d
(
TAG
,
"Config params updated: "
+
updated
);
}
else
{
Log
.
e
(
TAG
,
"Error fetching Remote Config
"
,
task
.
exception
)
}
}
});
Web
-
Add
getValueandfetchAndActivateto your imports:import { getValue , fetchAndActivate } from 'firebase/remote-config' ; -
Locate the code where you specify the default value for the model name. Directly after that code block, add the following code to fetch and activate the config and assign the fetched value to the
modelNameconstant.// Fetch and activate Remote Config . try { await fetchAndActivate ( remoteConfig ); } catch ( err ) { console . error ( ' Remote Config fetch failed' , err ); } console . log ( ' Remote Config fetched.' ); // Assign Remote Config values. const modelName = getValue ( remoteConfig , 'model_name' ). asString ();
Dart
// Fetch and activate Remote Config.
remoteConfig
.
fetchAndActivate
();
// Assign Remote Config values.
String
?
_modelName
=
remoteConfig
.
getString
(
"model_name"
);
Unity
// Fetch and activate Remote Config
values.
await
remoteConfig
.
FetchAndActivateAsync
();
Step 5: Add a real-time Remote Config listener
Add a real-time Remote Config listener to your app to ensure that changes you make to the Remote Config template are propagated to the client as soon as they're updated.
The following code updates the Remote Config object whenever a parameter value changes.
Swift
// Add real-time Remote Config
remoteConfig
.
addOnConfigUpdateListener
{
configUpdate
,
error
in
guard
let
configUpdate
=
configUpdate
,
error
==
nil
else
{
print
(
"Error listening for config updates:
\(
error
?.
localizedDescription
??
"No error available"
)
"
)
return
}
print
(
"Updated keys:
\(
configUpdate
.
updatedKeys
)
"
)
remoteConfig
.
activate
{
changed
,
error
in
guard
error
==
nil
else
{
print
(
"Error activating config:
\(
error
?.
localizedDescription
??
"No error available"
)
"
)
return
}
print
(
"Activated config successfully"
)
}
}
Kotlin
Optionally, you can also configure an action inside the addOnCompleteListener
activation:
// Add a real-time Remote Config
listener
remoteConfig
.
addOnConfigUpdateListener
(
object
:
ConfigUpdateListener
{
override
fun
onUpdate
(
configUpdate
:
ConfigUpdate
)
{
Log
.
d
(
ContentValues
.
TAG
,
"Updated keys: "
+
configUpdate
.
updatedKeys
);
remoteConfig
.
activate
().
addOnCompleteListener
{
// Optionally, add an action to perform on update here.
}
}
override
fun
onError
(
error
:
FirebaseRemoteConfigException
)
{
Log
.
w
(
ContentValues
.
TAG
,
"Config update error with code: "
+
error
.
code
,
error
)
}
}
Java
Optionally, you can also configure an action inside the addOnCompleteListener
activation:
// Add a real-time Remote Config
listener
remoteConfig
.
addOnConfigUpdateListener
(
new
ConfigUpdateListener
()
{
@Override
public
void
onUpdate
(
ConfigUpdate
configUpdate
)
{
Log
.
d
(
ContentValues
.
TAG
,
"Updated keys: "
+
configUpdate
.
getUpdatedKeys
());
remoteConfig
.
activate
().
addOnCompleteListener
(
new
OnCompleteListener<Boolean>
()
{
@Override
public
void
onComplete
(
@NonNull
Task<Boolean>
task
)
{
// Optionally, add an action to perform on update here.
}
});
}
@Override
public
void
onError
(
FirebaseRemoteConfigException
error
)
{
Log
.
w
(
ContentValues
.
TAG
,
"Config update error with code: "
+
error
.
getCode
(),
error
);
}
});
Web
Real-time Remote Config listeners aren't supported for Web apps.
Dart
// Add a real-time Remote Config
listener
remoteConfig
.
onConfigUpdated
.
listen
((
event
)
async
{
await
remoteConfig
.
activate
();
});
Unity
// Add a real-time Remote Config
listener to automatically update whenever
// a new template is published.
// Note: the parameters can be anonymous as they are unused.
remoteConfig
.
OnConfigUpdateListener
+=
(
_
,
_
)
=
>
{
remoteConfig
.
ActivateAsync
();
};
Step 6: Update the Gemini API requests to use the Remote Config value
Click your Gemini API provider to view provider-specific content and code on this page.
Now that Remote Config is fully configured, update your code to replace hard-coded values with values sourced from Remote Config .
Swift
import
FirebaseAI
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
let
modelName
=
remoteConfig
.
configValue
(
forKey
:
"model_name"
).
stringValue
let
model
=
FirebaseAI
.
firebaseAI
(
backend
:
.
googleAI
()).
generativeModel
(
modelName
:
modelName
)
// ...
Kotlin
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
val
model
=
Firebase
.
ai
(
backend
=
GenerativeBackend
.
googleAI
()).
generativeModel
(
modelName
=
remoteConfig
.
getString
(
"model_name"
)
)
// ...
Java
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
GenerativeModel
ai
=
FirebaseAI
.
getInstance
(
GenerativeBackend
.
googleAI
())
.
generativeModel
(
/* modelName */
remoteConfig
.
getString
(
"model_name"
),
/* generationConfig (optional) */
null
,
/* safetySettings (optional) */
null
,
/* requestOptions (optional) */
new
RequestOptions
(),
/* tools (optional) */
null
,
/* toolsConfig (optional) */
null
,
/* systemInstruction (optional) */
null
,
);
GenerativeModelFutures
model
=
GenerativeModelFutures
.
from
(
ai
);
// ...
Web
// ...
const
ai
=
getAI
(
firebaseApp
,
{
backend
:
new
GoogleAIBackend
()
});
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
const
model
=
getGenerativeModel
(
ai
,
{
model
:
modelName
});
// ...
Dart
// ...
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
final
model
=
FirebaseAI
.
googleAI
().
generativeModel
(
model:
_modelName
,
);
// ...
Unity
// ...
var
ai
=
FirebaseAI
.
GetInstance
(
FirebaseAI
.
Backend
.
GoogleAI
());
// When creating a `GenerativeModel` instance, source the model name value from Remote Config
var
modelName
=
remoteConfig
.
GetValue
(
"model_name"
).
StringValue
;
var
model
=
ai
.
GetGenerativeModel
(
modelName
:
modelName
);
// ...
Step 7: Run the app
Build and run the app and verify that it works. Make changes to your configuration from the Remote Config page in the Firebase console, publish the changes, and verify the result.
Next steps
-
Learn more about implementing other use cases for Remote Config and Firebase AI Logic .
-
For mobile apps and games:
-
Test different model settings with Remote Config and A/B Testing .
-
Gradually release model parameter changes using Remote Config rollouts (iOS+ and Android only).
-
Use Remote Config personalization to use machine learning to determine the best settings for individual users (iOS+, Android, and Unity only).
-

