IMPORTANT: In July 2025, we stopped releasing new versions of KTX modules, and we removed the KTX libraries from the Firebase Android BoM (v34.0.0). If you use KTX APIs from the previously released KTX modules, we recommend that you migrate your app to use KTX APIs from the main modules instead. For details, see the FAQ about this initiative.

GenerativeModel

class GenerativeModel

Represents a multimodal model (like Gemini), capable of generating content based on various input types.

Summary

Public functions
`suspend CountTokensResponse`	`countTokens(prompt: Bitmap)` Counts the number of tokens in an image prompt using the model's tokenizer.
`suspend CountTokensResponse`	`countTokens(vararg prompt: Content)` Counts the number of tokens in a prompt using the model's tokenizer.
`suspend CountTokensResponse`	`countTokens(prompt: String)` Counts the number of tokens in a text prompt using the model's tokenizer.
`suspend GenerateContentResponse`	`generateContent(prompt: Bitmap)` Generates new content from the image input given to the model as a prompt.
`suspend GenerateContentResponse`	`generateContent(vararg prompt: Content)` Generates new content from the input `Content` given to the model as a prompt.
`suspend GenerateContentResponse`	`generateContent(prompt: String)` Generates new content from the text input given to the model as a prompt.
`Flow<GenerateContentResponse>`	`generateContentStream(prompt: Bitmap)` Generates new content as a stream from the image input given to the model as a prompt.
`Flow<GenerateContentResponse>`	`generateContentStream(vararg prompt: Content)` Generates new content as a stream from the input `Content` given to the model as a prompt.
`Flow<GenerateContentResponse>`	`generateContentStream(prompt: String)` Generates new content as a stream from the text input given to the model as a prompt.
`Chat`	`startChat(history: List<Content>)` Creates a `Chat` instance using this model with the optionally provided history.

Public functions

countTokens

suspend fun countTokens(prompt: Bitmap): CountTokensResponse

Counts the number of tokens in an image prompt using the model's tokenizer.

Parameters
`prompt: Bitmap`	The image given to the model as a prompt.

Returns
`CountTokensResponse`	The `CountTokensResponse` of running the model's tokenizer on the input.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

countTokens

suspend fun countTokens(vararg prompt: Content): CountTokensResponse

Counts the number of tokens in a prompt using the model's tokenizer.

Parameters
`vararg prompt: Content`	The input(s) given to the model as a prompt.

Returns
`CountTokensResponse`	The `CountTokensResponse` of running the model's tokenizer on the input.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

countTokens

suspend fun countTokens(prompt: String): CountTokensResponse

Counts the number of tokens in a text prompt using the model's tokenizer.

Parameters
`prompt: String`	The text given to the model as a prompt.

Returns
`CountTokensResponse`	The `CountTokensResponse` of running the model's tokenizer on the input.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContent

suspend fun generateContent(prompt: Bitmap): GenerateContentResponse

Generates new content from the image input given to the model as a prompt.

Parameters
`prompt: Bitmap`	The image to be converted into a single piece of `Content` to send to the model.

Returns
`GenerateContentResponse`	A `GenerateContentResponse` after some delay.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContent

suspend fun generateContent(vararg prompt: Content): GenerateContentResponse

Generates new content from the input Content given to the model as a prompt.

Parameters
`vararg prompt: Content`	The input(s) given to the model as a prompt.

Returns
`GenerateContentResponse`	The content generated by the model.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContent

suspend fun generateContent(prompt: String): GenerateContentResponse

Generates new content from the text input given to the model as a prompt.

Parameters
`prompt: String`	The text to be send to the model as a prompt.

Returns
`GenerateContentResponse`	The content generated by the model.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContentStream

fun generateContentStream(prompt: Bitmap): Flow<GenerateContentResponse>

Generates new content as a stream from the image input given to the model as a prompt.

Parameters
`prompt: Bitmap`	The image to be converted into a single piece of `Content` to send to the model.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned by the model.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContentStream

fun generateContentStream(vararg prompt: Content): Flow<GenerateContentResponse>

Generates new content as a stream from the input Content given to the model as a prompt.

Parameters
`vararg prompt: Content`	The input(s) given to the model as a prompt.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned by the model.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

generateContentStream

fun generateContentStream(prompt: String): Flow<GenerateContentResponse>

Generates new content as a stream from the text input given to the model as a prompt.

Parameters
`prompt: String`	The text to be send to the model as a prompt.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned by the model.

Throws
`com.google.firebase.vertexai.type.FirebaseVertexAIException: com.google.firebase.vertexai.type.FirebaseVertexAIException`	if the request failed.

See also
`FirebaseVertexAIException`	for types of errors.

startChat

fun startChat(history: List<Content> = emptyList()): Chat

Creates a Chat instance using this model with the optionally provided history.