@ai-sdk/google 4.0.0-beta.43 → 4.0.0-beta.45

package/docs/{15-google-generative-ai.mdx → 15-google.mdx}

@@ -1,12 +1,12 @@
 ---
-title: Google Generative AI
-description: Learn how to use Google Generative AI Provider.
+title: Google
+description: Learn how to use Google Provider.
 ---
 
-# Google Generative AI Provider
+# Google Provider
 
-The [Google Generative AI](https://ai.google.dev) provider contains language and embedding model support for
-the [Google Generative AI](https://ai.google.dev/api/rest) APIs.
+The [Google](https://ai.google.dev) provider contains language and embedding model support for
+the [Google](https://ai.google.dev/api/rest) APIs.
 
 ## Setup
 
@@ -36,17 +36,17 @@ You can import the default provider instance `google` from `@ai-sdk/google`:
 import { google } from '@ai-sdk/google';
 ```
 
-If you need a customized setup, you can import `createGoogleGenerativeAI` from `@ai-sdk/google` and create a provider instance with your settings:
+If you need a customized setup, you can import `createGoogle` from `@ai-sdk/google` and create a provider instance with your settings:
 
 ```ts
-import { createGoogleGenerativeAI } from '@ai-sdk/google';
+import { createGoogle } from '@ai-sdk/google';
 
-const google = createGoogleGenerativeAI({
+const google = createGoogle({
   // custom settings
 });
 ```
 
-You can use the following optional settings to customize the Google Generative AI provider instance:
+You can use the following optional settings to customize the Google provider instance:
 
 - **baseURL** _string_
 
@@ -89,7 +89,7 @@ The models support tool calls and some have multi-modal capabilities.
 const model = google('gemini-2.5-flash');
 ```
 
-You can use Google Generative AI language models to generate text with the `generateText` function:
+You can use Google language models to generate text with the `generateText` function:
 
 ```ts
 import { google } from '@ai-sdk/google';
@@ -101,11 +101,11 @@ const { text } = await generateText({
 });
 ```
 
-Google Generative AI language models can also be used in the `streamText` function
+Google language models can also be used in the `streamText` function
 and support structured data generation with [`Output`](/docs/reference/ai-sdk-core/output)
 (see [AI SDK Core](/docs/ai-sdk-core)).
 
-Google Generative AI also supports some model specific settings that are not part of the [standard call settings](/docs/ai-sdk-core/settings).
+Google also supports some model specific settings that are not part of the [standard call settings](/docs/ai-sdk-core/settings).
 You can pass them as an options argument:
 
 ```ts
@@ -128,7 +128,7 @@ await generateText({
 });
 ```
 
-The following optional provider options are available for Google Generative AI models:
+The following optional provider options are available for Google models:
 
 - **cachedContent** _string_
 
@@ -141,7 +141,7 @@ The following optional provider options are available for Google Generative AI m
 
   This is useful when the JSON Schema contains elements that are
   not supported by the OpenAPI schema version that
-  Google Generative AI uses. You can use this to disable
+  Google uses. You can use this to disable
   structured outputs if you need to.
 
   See [Troubleshooting: Schema Limitations](#schema-limitations) for more details.
@@ -177,7 +177,7 @@ The following optional provider options are available for Google Generative AI m
 
 - **thinkingConfig** _\{ thinkingLevel?: 'minimal' | 'low' | 'medium' | 'high'; thinkingBudget?: number; includeThoughts?: boolean \}_
 
-  Optional. Configuration for the model's thinking process. Only supported by specific [Google Generative AI models](https://ai.google.dev/gemini-api/docs/thinking).
+  Optional. Configuration for the model's thinking process. Only supported by specific [Google models](https://ai.google.dev/gemini-api/docs/thinking).
 
   - **thinkingLevel** _'minimal' | 'low' | 'medium' | 'high'_
 
@@ -186,7 +186,7 @@ The following optional provider options are available for Google Generative AI m
   - **thinkingBudget** _number_
 
     Optional. Gives the model guidance on the number of thinking tokens it can use when generating a response. Setting it to 0 disables thinking, if the model supports it.
-    For more information about the possible value ranges for each model see [Google Generative AI thinking documentation](https://ai.google.dev/gemini-api/docs/thinking#set-budget).
+    For more information about the possible value ranges for each model see [Google thinking documentation](https://ai.google.dev/gemini-api/docs/thinking#set-budget).
 
     <Note>
       This option is for Gemini 2.5 models. Gemini 3 models should use
@@ -199,7 +199,7 @@ The following optional provider options are available for Google Generative AI m
 
 - **imageConfig** _\{ aspectRatio?: string, imageSize?: string \}_
 
-  Optional. Configuration for the models image generation. Only supported by specific [Google Generative AI models](https://ai.google.dev/gemini-api/docs/image-generation).
+  Optional. Configuration for the models image generation. Only supported by specific [Google models](https://ai.google.dev/gemini-api/docs/image-generation).
 
   - **aspectRatio** _string_
 
@@ -258,7 +258,7 @@ The following optional provider options are available for Google Generative AI m
 
 ### Thinking
 
-The Gemini 2.5 and Gemini 3 series models use an internal "thinking process" that significantly improves their reasoning and multi-step planning abilities, making them highly effective for complex tasks such as coding, advanced mathematics, and data analysis. For more information see [Google Generative AI thinking documentation](https://ai.google.dev/gemini-api/docs/thinking).
+The Gemini 2.5 and Gemini 3 series models use an internal "thinking process" that significantly improves their reasoning and multi-step planning abilities, making them highly effective for complex tasks such as coding, advanced mathematics, and data analysis. For more information see [Google thinking documentation](https://ai.google.dev/gemini-api/docs/thinking).
 
 #### Gemini 3 Models
 
@@ -318,7 +318,7 @@ console.log(reasoning); // Reasoning summary
 
 ### File Inputs
 
-The Google Generative AI provider supports file inputs, e.g. PDF files.
+The Google provider supports file inputs, e.g. PDF files.
 
 ```ts
 import { google } from '@ai-sdk/google';
@@ -384,7 +384,7 @@ See [File Parts](/docs/foundations/prompts#file-parts) for details on how to use
 
 ### Cached Content
 
-Google Generative AI supports both explicit and implicit caching to help reduce costs on repetitive content.
+Google supports both explicit and implicit caching to help reduce costs on repetitive content.
 
 #### Implicit Caching
 
@@ -516,7 +516,7 @@ the model has access to the latest information using Google Search.
 
 ```ts highlight="8,17-20"
 import { google } from '@ai-sdk/google';
-import { GoogleGenerativeAIProviderMetadata } from '@ai-sdk/google';
+import { GoogleProviderMetadata } from '@ai-sdk/google';
 import { generateText } from 'ai';
 
 const { text, sources, providerMetadata } = await generateText({
@@ -532,7 +532,7 @@ const { text, sources, providerMetadata } = await generateText({
 // access the grounding metadata. Casting to the provider metadata type
 // is optional but provides autocomplete and type safety.
 const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
+  | GoogleProviderMetadata
   | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const safetyRatings = metadata?.safetyRatings;
@@ -693,7 +693,7 @@ const { text, sources, providerMetadata } = await generateText({
 });
 
 const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
+  | GoogleProviderMetadata
   | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const urlContextMetadata = metadata?.urlContextMetadata;
@@ -714,7 +714,7 @@ Example response:
 {
   "urlMetadata": [
     {
-      "retrievedUrl": "https://ai-sdk.dev/providers/ai-sdk-providers/google-generative-ai",
+      "retrievedUrl": "https://ai-sdk.dev/providers/ai-sdk-providers/google",
       "urlRetrievalStatus": "URL_RETRIEVAL_STATUS_SUCCESS"
     }
   ]
@@ -728,8 +728,8 @@ With the URL context tool, you will also get the `groundingMetadata`.
     "groundingChunks": [
         {
             "web": {
-                "uri": "https://ai-sdk.dev/providers/ai-sdk-providers/google-generative-ai",
-                "title": "Google Generative AI - AI SDK Providers"
+                "uri": "https://ai-sdk.dev/providers/ai-sdk-providers/google",
+                "title": "Google - AI SDK Providers"
             }
         }
     ],
@@ -766,7 +766,7 @@ import { generateText } from 'ai';
 
 const { text, sources, providerMetadata } = await generateText({
   model: google('gemini-2.5-flash'),
-  prompt: `Based on this context: https://ai-sdk.dev/providers/ai-sdk-providers/google-generative-ai, tell me how to use Gemini with AI SDK.
+  prompt: `Based on this context: https://ai-sdk.dev/providers/ai-sdk-providers/google, tell me how to use Gemini with AI SDK.
     Also, provide the latest news about AI SDK V5.`,
   tools: {
     google_search: google.tools.googleSearch({}),
@@ -775,7 +775,7 @@ const { text, sources, providerMetadata } = await generateText({
 });
 
 const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
+  | GoogleProviderMetadata
   | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const urlContextMetadata = metadata?.urlContextMetadata;
@@ -788,7 +788,7 @@ the model has access to Google Maps data for location-aware responses. This enab
 
 ```ts highlight="7-16"
 import { google, type GoogleLanguageModelOptions } from '@ai-sdk/google';
-import { GoogleGenerativeAIProviderMetadata } from '@ai-sdk/google';
+import { GoogleProviderMetadata } from '@ai-sdk/google';
 import { generateText } from 'ai';
 
 const { text, sources, providerMetadata } = await generateText({
@@ -808,7 +808,7 @@ const { text, sources, providerMetadata } = await generateText({
 });
 
 const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
+  | GoogleProviderMetadata
   | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 ```
@@ -849,7 +849,7 @@ This enables the model to provide answers based on your specific data sources an
 
 ```ts highlight="8,17-20"
 import { createVertex } from '@ai-sdk/google-vertex';
-import { GoogleGenerativeAIProviderMetadata } from '@ai-sdk/google';
+import { GoogleProviderMetadata } from '@ai-sdk/google';
 import { generateText } from 'ai';
 
 const vertex = createVertex({
@@ -873,7 +873,7 @@ const { text, sources, providerMetadata } = await generateText({
 // access the grounding metadata. Casting to the provider metadata type
 // is optional but provides autocomplete and type safety.
 const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
+  | GoogleProviderMetadata
   | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const safetyRatings = metadata?.safetyRatings;
@@ -1057,7 +1057,7 @@ const { output } = await generateText({
 });
 ```
 
-The following Zod features are known to not work with Google Generative AI:
+The following Zod features are known to not work with Google:
 
 - `z.union`
 - `z.record`
@@ -1117,12 +1117,12 @@ using the `.embedding()` factory method.
 const model = google.embedding('gemini-embedding-001');
 ```
 
-The Google Generative AI provider sends API calls to the right endpoint based on the type of embedding:
+The Google provider sends API calls to the right endpoint based on the type of embedding:
 
 - **Single embeddings**: When embedding a single value with `embed()`, the provider uses the single `:embedContent` endpoint, which typically has higher rate limits compared to the batch endpoint.
 - **Batch embeddings**: When embedding multiple values with `embedMany()` or multiple values in `embed()`, the provider uses the `:batchEmbedContents` endpoint.
 
-Google Generative AI embedding models support additional settings. You can pass them as an options argument:
+Google embedding models support additional settings. You can pass them as an options argument:
 
 ```ts
 import { google, type GoogleEmbeddingModelOptions } from '@ai-sdk/google';
@@ -1164,7 +1164,7 @@ const { embeddings } = await embedMany({
 });
 ```
 
-The following optional provider options are available for Google Generative AI embedding models:
+The following optional provider options are available for Google embedding models:
 
 - **outputDimensionality**: _number_
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/google",
-  "version": "4.0.0-beta.43",
+  "version": "4.0.0-beta.45",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -36,7 +36,7 @@
   },
   "dependencies": {
     "@ai-sdk/provider": "4.0.0-beta.12",
-    "@ai-sdk/provider-utils": "5.0.0-beta.24"
+    "@ai-sdk/provider-utils": "5.0.0-beta.26"
   },
   "devDependencies": {
     "@types/node": "20.17.24",

package/src/{convert-google-generative-ai-usage.ts → convert-google-usage.ts}

@@ -1,23 +1,23 @@
 import { LanguageModelV4Usage } from '@ai-sdk/provider';
 
-export type GoogleGenerativeAITokenDetail = {
+export type GoogleTokenDetail = {
   modality: string;
   tokenCount: number;
 };
 
-export type GoogleGenerativeAIUsageMetadata = {
+export type GoogleUsageMetadata = {
   promptTokenCount?: number | null;
   candidatesTokenCount?: number | null;
   totalTokenCount?: number | null;
   cachedContentTokenCount?: number | null;
   thoughtsTokenCount?: number | null;
   trafficType?: string | null;
-  promptTokensDetails?: GoogleGenerativeAITokenDetail[] | null;
-  candidatesTokensDetails?: GoogleGenerativeAITokenDetail[] | null;
+  promptTokensDetails?: GoogleTokenDetail[] | null;
+  candidatesTokensDetails?: GoogleTokenDetail[] | null;
 };
 
-export function convertGoogleGenerativeAIUsage(
-  usage: GoogleGenerativeAIUsageMetadata | undefined | null,
+export function convertGoogleUsage(
+  usage: GoogleUsageMetadata | undefined | null,
 ): LanguageModelV4Usage {
   if (usage == null) {
     return {

package/src/{convert-to-google-generative-ai-messages.ts → convert-to-google-messages.ts}

@@ -8,11 +8,11 @@ import {
   resolveProviderReference,
 } from '@ai-sdk/provider-utils';
 import {
-  GoogleGenerativeAIContent,
-  GoogleGenerativeAIContentPart,
-  GoogleGenerativeAIFunctionResponsePart,
-  GoogleGenerativeAIPrompt,
-} from './google-generative-ai-prompt';
+  GoogleContent,
+  GoogleContentPart,
+  GoogleFunctionResponsePart,
+  GooglePrompt,
+} from './google-prompt';
 
 const dataUrlRegex = /^data:([^;,]+);base64,(.+)$/s;
 
@@ -32,7 +32,7 @@ function parseBase64DataUrl(
 
 function convertUrlToolResultPart(
   url: string,
-): GoogleGenerativeAIFunctionResponsePart | undefined {
+): GoogleFunctionResponsePart | undefined {
   // Per https://ai.google.dev/api/caching#FunctionResponsePart, only inline data is supported.
   // https://docs.cloud.google.com/vertex-ai/generative-ai/docs/model-reference/function-calling#functionresponsepart suggests that this
   // may be different for Vertex, but this needs to be confirmed and further tested for both APIs.
@@ -55,14 +55,14 @@ function convertUrlToolResultPart(
  * text). This format is supported by Gemini 3+ models.
  */
 function appendToolResultParts(
-  parts: GoogleGenerativeAIContentPart[],
+  parts: GoogleContentPart[],
   toolName: string,
   outputValue: Array<{
     type: string;
     [key: string]: unknown;
   }>,
 ): void {
-  const functionResponseParts: GoogleGenerativeAIFunctionResponsePart[] = [];
+  const functionResponseParts: GoogleFunctionResponsePart[] = [];
   const responseTextParts: string[] = [];
 
   for (const contentPart of outputValue) {
@@ -122,7 +122,7 @@ function appendToolResultParts(
  * non-text content like images is sent as separate top-level inlineData parts.
  */
 function appendLegacyToolResultParts(
-  parts: GoogleGenerativeAIContentPart[],
+  parts: GoogleContentPart[],
   toolName: string,
   outputValue: Array<{
     type: string;
@@ -166,16 +166,16 @@ function appendLegacyToolResultParts(
   }
 }
 
-export function convertToGoogleGenerativeAIMessages(
+export function convertToGoogleMessages(
   prompt: LanguageModelV4Prompt,
   options?: {
     isGemmaModel?: boolean;
     providerOptionsName?: string;
     supportsFunctionResponseParts?: boolean;
   },
-): GoogleGenerativeAIPrompt {
+): GooglePrompt {
   const systemInstructionParts: Array<{ text: string }> = [];
-  const contents: Array<GoogleGenerativeAIContent> = [];
+  const contents: Array<GoogleContent> = [];
   let systemMessagesAllowed = true;
   const isGemmaModel = options?.isGemmaModel ?? false;
   const providerOptionsName = options?.providerOptionsName ?? 'google';
@@ -199,7 +199,7 @@ export function convertToGoogleGenerativeAIMessages(
       case 'user': {
         systemMessagesAllowed = false;
 
-        const parts: GoogleGenerativeAIContentPart[] = [];
+        const parts: GoogleContentPart[] = [];
 
         for (const part of content) {
           switch (part.type) {
@@ -418,7 +418,7 @@ export function convertToGoogleGenerativeAIMessages(
       case 'tool': {
         systemMessagesAllowed = false;
 
-        const parts: GoogleGenerativeAIContentPart[] = [];
+        const parts: GoogleContentPart[] = [];
 
         for (const part of content) {
           if (part.type === 'tool-approval-response') {

package/src/{google-generative-ai-embedding-model.ts → google-embedding-model.ts}

@@ -18,26 +18,26 @@ import {
 import { z } from 'zod/v4';
 import { googleFailedResponseHandler } from './google-error';
 import {
-  GoogleGenerativeAIEmbeddingModelId,
+  GoogleEmbeddingModelId,
   googleEmbeddingModelOptions,
-} from './google-generative-ai-embedding-options';
+} from './google-embedding-options';
 
-type GoogleGenerativeAIEmbeddingConfig = {
+type GoogleEmbeddingConfig = {
   provider: string;
   baseURL: string;
   headers?: () => Record<string, string | undefined>;
   fetch?: FetchFunction;
 };
 
-export class GoogleGenerativeAIEmbeddingModel implements EmbeddingModelV4 {
+export class GoogleEmbeddingModel implements EmbeddingModelV4 {
   readonly specificationVersion = 'v4';
-  readonly modelId: GoogleGenerativeAIEmbeddingModelId;
+  readonly modelId: GoogleEmbeddingModelId;
   readonly maxEmbeddingsPerCall = 2048;
   readonly supportsParallelCalls = true;
 
-  private readonly config: GoogleGenerativeAIEmbeddingConfig;
+  private readonly config: GoogleEmbeddingConfig;
 
-  static [WORKFLOW_SERIALIZE](model: GoogleGenerativeAIEmbeddingModel) {
+  static [WORKFLOW_SERIALIZE](model: GoogleEmbeddingModel) {
     return serializeModelOptions({
       modelId: model.modelId,
       config: model.config,
@@ -46,21 +46,15 @@ export class GoogleGenerativeAIEmbeddingModel implements EmbeddingModelV4 {
 
   static [WORKFLOW_DESERIALIZE](options: {
     modelId: string;
-    config: GoogleGenerativeAIEmbeddingConfig;
+    config: GoogleEmbeddingConfig;
   }) {
-    return new GoogleGenerativeAIEmbeddingModel(
-      options.modelId,
-      options.config,
-    );
+    return new GoogleEmbeddingModel(options.modelId, options.config);
   }
 
   get provider(): string {
     return this.config.provider;
   }
-  constructor(
-    modelId: GoogleGenerativeAIEmbeddingModelId,
-    config: GoogleGenerativeAIEmbeddingConfig,
-  ) {
+  constructor(modelId: GoogleEmbeddingModelId, config: GoogleEmbeddingConfig) {
     this.modelId = modelId;
     this.config = config;
   }

package/src/{google-generative-ai-embedding-options.ts → google-embedding-options.ts}

@@ -5,7 +5,7 @@ import {
 } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
-export type GoogleGenerativeAIEmbeddingModelId =
+export type GoogleEmbeddingModelId =
   | 'gemini-embedding-001'
   | 'gemini-embedding-2-preview'
   | (string & {});

package/src/{google-generative-ai-files.ts → google-files.ts}

@@ -26,21 +26,21 @@ export type GoogleFilesUploadOptions = {
   [key: string]: unknown;
 };
 
-interface GoogleGenerativeAIFilesConfig {
+interface GoogleFilesConfig {
   provider: string;
   baseURL: string;
   headers: () => Record<string, string | undefined>;
   fetch?: FetchFunction;
 }
 
-export class GoogleGenerativeAIFiles implements FilesV4 {
+export class GoogleFiles implements FilesV4 {
   readonly specificationVersion = 'v4';
 
   get provider(): string {
     return this.config.provider;
   }
 
-  constructor(private readonly config: GoogleGenerativeAIFilesConfig) {}
+  constructor(private readonly config: GoogleFilesConfig) {}
 
   async uploadFile(
     options: FilesV4UploadFileCallOptions,

package/src/{google-generative-ai-image-model.ts → google-image-model.ts}

@@ -23,13 +23,13 @@ import {
 import { z } from 'zod/v4';
 import { googleFailedResponseHandler } from './google-error';
 import {
-  GoogleGenerativeAIImageModelId,
-  GoogleGenerativeAIImageSettings,
-} from './google-generative-ai-image-settings';
-import { GoogleGenerativeAILanguageModel } from './google-generative-ai-language-model';
-import type { GoogleLanguageModelOptions } from './google-generative-ai-options';
+  GoogleImageModelId,
+  GoogleImageSettings,
+} from './google-image-settings';
+import { GoogleLanguageModel } from './google-language-model';
+import type { GoogleLanguageModelOptions } from './google-options';
 
-interface GoogleGenerativeAIImageModelConfig {
+interface GoogleImageModelConfig {
   provider: string;
   baseURL: string;
   headers?: Resolvable<Record<string, string | undefined>>;
@@ -40,10 +40,10 @@ interface GoogleGenerativeAIImageModelConfig {
   };
 }
 
-export class GoogleGenerativeAIImageModel implements ImageModelV4 {
+export class GoogleImageModel implements ImageModelV4 {
   readonly specificationVersion = 'v4';
 
-  static [WORKFLOW_SERIALIZE](model: GoogleGenerativeAIImageModel) {
+  static [WORKFLOW_SERIALIZE](model: GoogleImageModel) {
     return serializeModelOptions({
       modelId: model.modelId,
       config: model.config,
@@ -52,13 +52,9 @@ export class GoogleGenerativeAIImageModel implements ImageModelV4 {
 
   static [WORKFLOW_DESERIALIZE](options: {
     modelId: string;
-    config: GoogleGenerativeAIImageModelConfig;
+    config: GoogleImageModelConfig;
   }) {
-    return new GoogleGenerativeAIImageModel(
-      options.modelId,
-      {},
-      options.config,
-    );
+    return new GoogleImageModel(options.modelId, {}, options.config);
   }
 
   get maxImagesPerCall(): number {
@@ -78,9 +74,9 @@ export class GoogleGenerativeAIImageModel implements ImageModelV4 {
   }
 
   constructor(
-    readonly modelId: GoogleGenerativeAIImageModelId,
-    private readonly settings: GoogleGenerativeAIImageSettings,
-    private readonly config: GoogleGenerativeAIImageModelConfig,
+    readonly modelId: GoogleImageModelId,
+    private readonly settings: GoogleImageSettings,
+    private readonly config: GoogleImageModelConfig,
   ) {}
 
   async doGenerate(
@@ -113,14 +109,14 @@ export class GoogleGenerativeAIImageModel implements ImageModelV4 {
     // Imagen API endpoints do not support image editing
     if (files != null && files.length > 0) {
       throw new Error(
-        'Google Generative AI does not support image editing with Imagen models. ' +
+        'Google Gemini API does not support image editing with Imagen models. ' +
           'Use Google Vertex AI (@ai-sdk/google-vertex) for image editing capabilities.',
       );
     }
 
     if (mask != null) {
       throw new Error(
-        'Google Generative AI does not support image editing with masks. ' +
+        'Google Gemini API does not support image editing with masks. ' +
           'Use Google Vertex AI (@ai-sdk/google-vertex) for image editing capabilities.',
       );
     }
@@ -282,7 +278,7 @@ export class GoogleGenerativeAIImageModel implements ImageModelV4 {
     ];
 
     // Instantiate language model
-    const languageModel = new GoogleGenerativeAILanguageModel(this.modelId, {
+    const languageModel = new GoogleLanguageModel(this.modelId, {
       provider: this.config.provider,
       baseURL: this.config.baseURL,
       headers: this.config.headers ?? {},

package/src/{google-generative-ai-image-settings.ts → google-image-settings.ts}

@@ -1,4 +1,4 @@
-export type GoogleGenerativeAIImageModelId =
+export type GoogleImageModelId =
   // Imagen models (use :predict API)
   | 'imagen-4.0-generate-001'
   | 'imagen-4.0-ultra-generate-001'
@@ -9,7 +9,7 @@ export type GoogleGenerativeAIImageModelId =
   | 'gemini-3.1-flash-image-preview'
   | (string & {});
 
-export interface GoogleGenerativeAIImageSettings {
+export interface GoogleImageSettings {
   /**
    * Override the maximum number of images per call (default 4)
    */