@ai-sdk/google 4.0.0-beta.7 → 4.0.0-beta.82

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.
@@ -149,11 +149,9 @@ The following optional provider options are available for Google Generative AI m
 - **safetySettings** _Array\<\{ category: string; threshold: string \}\>_
 
   Optional. Safety settings for the model.
-
   - **category** _string_
 
     The category of the safety setting. Can be one of the following:
-
     - `HARM_CATEGORY_UNSPECIFIED`
     - `HARM_CATEGORY_HATE_SPEECH`
     - `HARM_CATEGORY_DANGEROUS_CONTENT`
@@ -164,7 +162,6 @@ The following optional provider options are available for Google Generative AI m
   - **threshold** _string_
 
     The threshold of the safety setting. Can be one of the following:
-
     - `HARM_BLOCK_THRESHOLD_UNSPECIFIED`
     - `BLOCK_LOW_AND_ABOVE`
     - `BLOCK_MEDIUM_AND_ABOVE`
@@ -177,8 +174,7 @@ 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'_
 
     Optional. Controls the thinking depth for Gemini 3 models. Gemini 3.1 Pro supports 'low', 'medium', and 'high', Gemini 3 Pro supports 'low' and 'high', while Gemini 3 Flash supports all four levels: 'minimal', 'low', 'medium', and 'high'. Only supported by Gemini 3 models.
@@ -186,7 +182,7 @@ 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
@@ -199,12 +195,10 @@ 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_
 
     Model defaults to generate 1:1 squares, or to matching the output image size to that of your input image. Can be one of the following:
-
     - 1:1
     - 2:3
     - 3:2
@@ -219,7 +213,6 @@ The following optional provider options are available for Google Generative AI m
   - **imageSize** _string_
 
     Controls the output image resolution. Defaults to 1K. Can be one of the following:
-
     - 1K
     - 2K
     - 4K
@@ -232,7 +225,6 @@ The following optional provider options are available for Google Generative AI m
 - **mediaResolution** _string_
 
   Optional. If specified, the media resolution specified will be used. Can be one of the following:
-
   - `MEDIA_RESOLUTION_UNSPECIFIED`
   - `MEDIA_RESOLUTION_LOW`
   - `MEDIA_RESOLUTION_MEDIUM`
@@ -245,6 +237,18 @@ The following optional provider options are available for Google Generative AI m
   Optional. Defines labels used in billing reports. Available on Vertex AI only.
   See [Google Cloud labels documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/add-labels-to-api-calls).
 
+- **serviceTier** _'standard' | 'flex' | 'priority'_
+
+  Optional. The service tier to use for the request.
+  Set to `'flex'` for 50% cheaper processing at the cost of increased latency.
+  Set to `'priority'` for ultra-low latency at a 75-100% price premium over `'standard'`.
+
+  Because Priority can be gracefully downgraded to Standard under load, the
+  tier the request actually ran on is surfaced on
+  `result.providerMetadata.google.serviceTier`. See
+  [Priority inference](https://ai.google.dev/gemini-api/docs/priority-inference)
+  and [Flex inference](https://ai.google.dev/gemini-api/docs/flex-inference).
+
 - **threshold** _string_
 
   Optional. Standalone threshold setting that can be used independently of `safetySettings`.
@@ -252,7 +256,7 @@ 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
 
@@ -312,7 +316,7 @@ 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';
@@ -378,7 +382,7 @@ 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
 
@@ -510,7 +514,7 @@ 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({
@@ -525,9 +529,7 @@ 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
-  | undefined;
+const metadata = providerMetadata?.google as GoogleProviderMetadata | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const safetyRatings = metadata?.safetyRatings;
 ```
@@ -537,14 +539,12 @@ The `googleSearch` tool accepts the following optional configuration options:
 - **searchTypes** _object_
 
   Enables specific search types. Both can be combined.
-
   - `webSearch`: Enable web search grounding (pass `{}` to enable). This is the default.
   - `imageSearch`: Enable [image search grounding](https://ai.google.dev/gemini-api/docs/image-generation#image-search) (pass `{}` to enable).
 
 - **timeRangeFilter** _object_
 
   Restricts search results to a specific time range. Both `startTime` and `endTime` are required.
-
   - `startTime`: Start time in ISO 8601 format (e.g. `'2025-01-01T00:00:00Z'`).
   - `endTime`: End time in ISO 8601 format (e.g. `'2025-12-31T23:59:59Z'`).
 
@@ -563,12 +563,10 @@ When Google Search grounding is enabled, the model will include sources in the r
 Additionally, the grounding metadata includes detailed information about how search results were used to ground the model's response. Here are the available fields:
 
 - **`webSearchQueries`** (`string[] | null`)
-
   - Array of search queries used to retrieve information
   - Example: `["What's the weather in Chicago this weekend?"]`
 
 - **`searchEntryPoint`** (`{ renderedContent: string } | null`)
-
   - Contains the main search result content used as an entry point
   - The `renderedContent` field contains the formatted content
 
@@ -619,10 +617,10 @@ the model has access to a compliance-focused web index designed for highly-regul
 </Note>
 
 ```ts
-import { createVertex } from '@ai-sdk/google-vertex';
+import { createGoogleVertex } from '@ai-sdk/google-vertex';
 import { generateText } from 'ai';
 
-const vertex = createVertex({
+const vertex = createGoogleVertex({
   project: 'my-project',
   location: 'us-central1',
 });
@@ -686,9 +684,7 @@ const { text, sources, providerMetadata } = await generateText({
   },
 });
 
-const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
-  | undefined;
+const metadata = providerMetadata?.google as GoogleProviderMetadata | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const urlContextMetadata = metadata?.urlContextMetadata;
 ```
@@ -696,7 +692,6 @@ const urlContextMetadata = metadata?.urlContextMetadata;
 The URL context metadata includes detailed information about how the model used the URL context to generate the response. Here are the available fields:
 
 - **`urlMetadata`** (`{ retrievedUrl: string; urlRetrievalStatus: string; }[] | null`)
-
   - Array of URL context metadata
   - Each object includes:
     - **`retrievedUrl`**: The URL of the context
@@ -708,7 +703,7 @@ 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"
     }
   ]
@@ -722,8 +717,8 @@ 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"
             }
         }
     ],
@@ -760,7 +755,7 @@ 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({}),
@@ -768,9 +763,7 @@ const { text, sources, providerMetadata } = await generateText({
   },
 });
 
-const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
-  | undefined;
+const metadata = providerMetadata?.google as GoogleProviderMetadata | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const urlContextMetadata = metadata?.urlContextMetadata;
 ```
@@ -782,7 +775,7 @@ 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({
@@ -801,9 +794,7 @@ const { text, sources, providerMetadata } = await generateText({
     'What are the best Italian restaurants within a 15-minute walk from here?',
 });
 
-const metadata = providerMetadata?.google as
-  | GoogleGenerativeAIProviderMetadata
-  | undefined;
+const metadata = providerMetadata?.google as GoogleProviderMetadata | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 ```
 
@@ -842,11 +833,11 @@ This enables the model to provide answers based on your specific data sources an
 </Note>
 
 ```ts highlight="8,17-20"
-import { createVertex } from '@ai-sdk/google-vertex';
-import { GoogleGenerativeAIProviderMetadata } from '@ai-sdk/google';
+import { createGoogleVertex } from '@ai-sdk/google-vertex';
+import { GoogleProviderMetadata } from '@ai-sdk/google';
 import { generateText } from 'ai';
 
-const vertex = createVertex({
+const vertex = createGoogleVertex({
   project: 'my-project',
   location: 'us-central1',
 });
@@ -866,9 +857,7 @@ 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
-  | undefined;
+const metadata = providerMetadata?.google as GoogleProviderMetadata | undefined;
 const groundingMetadata = metadata?.groundingMetadata;
 const safetyRatings = metadata?.safetyRatings;
 ```
@@ -878,7 +867,6 @@ When RAG Engine Grounding is enabled, the model will include sources from your R
 Additionally, the grounding metadata includes detailed information about how RAG results were used to ground the model's response. Here are the available fields:
 
 - **`groundingChunks`** (Array of chunk objects | null)
-
   - Contains the retrieved context chunks from your RAG corpus
   - Each chunk includes:
     - **`retrievedContext`**: Information about the retrieved context
@@ -887,7 +875,6 @@ Additionally, the grounding metadata includes detailed information about how RAG
       - `text`: The actual text content of the chunk
 
 - **`groundingSupports`** (Array of support objects | null)
-
   - Contains details about how specific response parts are supported by RAG results
   - Each support object includes:
     - **`segment`**: Information about the grounded text segment
@@ -931,12 +918,10 @@ Example response:
 The `vertexRagStore` tool accepts the following configuration options:
 
 - **`ragCorpus`** (`string`, required)
-
   - The RagCorpus resource name in the format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
   - This identifies your specific RAG corpus to search against
 
 - **`topK`** (`number`, optional)
-
   - The number of top contexts to retrieve from your RAG corpus
   - Defaults to the corpus configuration if not specified
 
@@ -1051,7 +1036,7 @@ 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`
@@ -1060,6 +1045,7 @@ The following Zod features are known to not work with Google Generative AI:
 
 | Model                                 | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      | Google Search       | URL Context         |
 | ------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `gemini-3.5-flash`                    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.1-pro-preview`              | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.1-flash-image-preview`      | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.1-flash-lite-preview`       | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
@@ -1079,6 +1065,635 @@ The following Zod features are known to not work with Google Generative AI:
   available provider model ID as a string if needed.
 </Note>
 
+## Realtime Models
+
+<Note type="warning">Realtime is an experimental feature.</Note>
+
+You can create models that call the [Gemini Live API](https://ai.google.dev/gemini-api/docs/live)
+using the `.experimental_realtime()` factory method.
+
+```ts
+import { google } from '@ai-sdk/google';
+
+const model = google.experimental_realtime('gemini-3.1-flash-live-preview');
+```
+
+Realtime sessions run in the browser and require a short-lived token created on
+your server with `google.experimental_realtime.getToken()`:
+
+```ts
+const token = await google.experimental_realtime.getToken({
+  model: 'gemini-3.1-flash-live-preview',
+});
+```
+
+Google realtime models may require provider-specific audio formats, depending
+on the model and modality. See [Realtime](/docs/ai-sdk-core/realtime) for the
+complete setup and tool calling pattern.
+
+## Interactions API
+
+The [Gemini Interactions API](https://ai.google.dev/gemini-api/docs/interactions)
+(`POST /v1beta/interactions`) is a separate Google endpoint with server-side
+state, unified content blocks, first-class built-in tools, agent presets,
+managed agents that run in a sandboxed Linux environment, and native
+multimodal image output. It is reached via the `google.interactions(...)`
+factory:
+
+```ts
+import { google } from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  prompt: 'Hello, how are you?',
+});
+```
+
+`google.interactions(...)` accepts a model ID string (e.g.
+`'gemini-2.5-flash'`, `'gemini-3-pro-preview'`), `{ agent: <name> }` to use
+a Gemini [agent preset](#agent-presets), or `{ managedAgent: <name> }` to
+invoke a [managed agent](#managed-agents) you created on Google's side.
+The returned model can be passed to `generateText` and `streamText` like
+any other AI SDK language model.
+
+<Note>
+  Use `google(...)` for the standard `:generateContent` /
+  `:streamGenerateContent` endpoints, and `google.interactions(...)` for the new
+  Interactions endpoint. Pick one per model instance — they target different
+  request bodies and SSE event vocabularies.
+</Note>
+
+### Provider Options
+
+The Interactions model reads its options from the shared
+`providerOptions.google.*` namespace. Validate them with the
+`GoogleLanguageModelInteractionsOptions` type:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  prompt: 'What color is the sky in one word?',
+  providerOptions: {
+    google: {
+      serviceTier: 'priority',
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+The following optional provider options are available:
+
+- **previousInteractionId** _string_
+
+  Server-side interaction id from a prior turn. When set, the server pulls
+  prior context from its own state and only the new user message is sent on
+  the wire. Pair with the default `store: true` to chain stateful
+  conversations. See [Stateful chaining](#stateful-chaining).
+
+- **store** _boolean_
+
+  Whether the server should persist the interaction. Defaults to `true`.
+  Set to `false` for stateless multi-turn conversations where the full
+  message history is re-sent on every turn.
+
+- **agent** _string_
+
+  Name of a Gemini agent preset (e.g. `'deep-research-pro-preview-12-2025'`).
+
+      <Note>
+
+  Prefer the factory form `google.interactions({ agent: '...' })` over
+  setting `agent` in provider options — the factory is type-checked
+  against the supported agent names.
+
+  </Note>
+
+- **agentConfig** _object_
+
+  Per-agent configuration. Currently supports `{ type: 'dynamic' }` and
+  `{ type: 'deep-research', thinkingSummaries?, visualization?, collaborativePlanning? }`.
+
+- **thinkingLevel** _'minimal' | 'low' | 'medium' | 'high'_
+
+  Controls reasoning depth for thinking-enabled models. Mapped onto the
+  Interactions request's `thinking_level`.
+
+- **thinkingSummaries** _'auto' | 'none'_
+
+  Whether the model returns synthesized thought summaries on reasoning
+  parts. Defaults to the API default.
+
+- **responseFormat** _Array\<\{ type: 'text' | 'image' | 'audio'; mimeType?: string; schema?: unknown; aspectRatio?: string; imageSize?: '1K' \| '2K' \| '4K' \| '512' \}\>_
+
+  Output-format entries that map directly to the API's `response_format`
+  array. Use this for fine-grained control over image, audio, or non-JSON
+  text outputs (e.g. `aspectRatio` and `imageSize` for image generation).
+  The AI SDK call-level `responseFormat: { type: 'json', schema }` still
+  drives JSON-mode automatically and prepends a matching text entry;
+  entries listed here are appended.
+
+  `aspectRatio` accepts `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`,
+  `9:16`, `16:9`, `21:9`, `1:8`, `8:1`, `1:4`, `4:1`.
+
+- **imageConfig** _\{ aspectRatio?: string; imageSize?: '1K' | '2K' | '4K' | '512' \}_ (deprecated)
+
+  Use **responseFormat** with a `{ type: 'image', ... }` entry instead.
+  Retained for backwards compatibility; the SDK translates `imageConfig`
+  into a matching `response_format` image entry and emits a warning when
+  set. Ignored when `responseFormat` already supplies an image entry.
+
+- **mediaResolution** _'low' | 'medium' | 'high' | 'ultra_high'_
+
+  Media resolution applied to image inputs / outputs.
+
+- **serviceTier** _'flex' | 'standard' | 'priority'_
+
+  Service tier for the request. Mirrored back on
+  `result.providerMetadata.google.serviceTier` for observability.
+
+- **systemInstruction** _string_
+
+  Alternative to the AI SDK `system` message. If both are set, the AI SDK
+  `system` message wins and a warning is emitted.
+
+- **background** _boolean_
+
+  Run the interaction in the background. Required for agents whose
+  server-side workflow cannot complete within a single request/response;
+  rejected by agents that only support synchronous calls. When `true`,
+  the POST returns a non-terminal status and the SDK polls
+  `GET /interactions/{id}` until the work completes.
+
+- **environment** _string \| object_
+
+  Sandbox environment configuration for [managed agents](#managed-agents).
+  Pass `'remote'` to provision a fresh sandbox, an `environment_id`
+  string to reuse an existing one, or an object of the form
+  `{ type: 'remote', sources?, network? }` to preload files and/or
+  constrain outbound traffic. Only applies to agent calls.
+
+- **pollingTimeoutMs** _number_
+
+  Maximum time, in milliseconds, to poll a background interaction before
+  giving up. Defaults to 30 minutes (1,800,000 ms). Long-running agents
+  may need longer.
+
+### Provider Metadata
+
+`result.providerMetadata.google` (typed via `GoogleInteractionsProviderMetadata`)
+exposes:
+
+- **interactionId** _string_
+
+  Server-side interaction id. Pass this back as `previousInteractionId` on
+  the next turn to chain.
+
+- **serviceTier** _string_
+
+  Service tier the request actually ran on.
+
+- **signature** _string_
+
+  Per-block signature hash, set by the SDK on output reasoning and
+  tool-call parts. Round-tripped automatically on the next turn.
+
+### Stateful chaining
+
+With the default `store: true`, the server retains the prior turn so the
+next request only needs to send the new user message and the
+`previousInteractionId`:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const turn1 = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  prompt: 'What are the three largest cities in Spain?',
+});
+
+const interactionId = turn1.providerMetadata?.google?.interactionId as
+  | string
+  | undefined;
+
+const turn2 = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  prompt: 'What is the most famous landmark in the second one?',
+  providerOptions: {
+    google: {
+      previousInteractionId: interactionId,
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+For stateless multi-turn conversations, set `store: false` and re-send the
+full message history on every turn (no `previousInteractionId`):
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText, type ModelMessage } from 'ai';
+
+const messages: Array<ModelMessage> = [
+  { role: 'user', content: 'What are the three largest cities in Spain?' },
+];
+
+const turn1 = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  messages,
+  providerOptions: {
+    google: { store: false } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+
+messages.push(...turn1.responseMessages);
+messages.push({
+  role: 'user',
+  content: 'What is the most famous landmark in the second one?',
+});
+
+const turn2 = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  messages,
+  providerOptions: {
+    google: { store: false } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+### Built-in Tools
+
+The Interactions API ships a built-in tool catalog. The provider-defined
+tools under `google.tools.*` map onto Interactions tool descriptors:
+
+| AI SDK tool                           | Interactions tool type | Notes                                     |
+| ------------------------------------- | ---------------------- | ----------------------------------------- |
+| `google.tools.googleSearch`           | `google_search`        | Web / image search grounding.             |
+| `google.tools.codeExecution`          | `code_execution`       | Server-side Python execution.             |
+| `google.tools.urlContext`             | `url_context`          | Fetch URLs referenced in the prompt.      |
+| `google.tools.fileSearch`             | `file_search`          | Retrieval from File Search stores.        |
+| `google.tools.googleMaps`             | `google_maps`          | Maps grounding for nearby-places queries. |
+| _provider tool_ `google.computer_use` | `computer_use`         | Computer use (browser environment).       |
+| _provider tool_ `google.mcp_server`   | `mcp_server`           | Remote MCP server passthrough.            |
+| _provider tool_ `google.retrieval`    | `retrieval`            | Vertex AI Search retrieval.               |
+
+Function tools (`type: 'function'`) defined with the AI SDK `tool(...)`
+helper are translated to Interactions `function` tool descriptors. Other
+tool kinds emit a warning and are dropped.
+
+```ts
+import { google } from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const { text, sources } = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  tools: {
+    google_search: google.tools.googleSearch({}),
+  },
+  prompt:
+    "What's a notable AI development from this past week? " +
+    'Include the date for each item you mention.',
+});
+```
+
+Function tools work the same way as on the standard provider:
+
+```ts
+import { google } from '@ai-sdk/google';
+import { generateText, stepCountIs, tool } from 'ai';
+import { z } from 'zod';
+
+const weatherTool = tool({
+  description: 'Get the weather for a city.',
+  inputSchema: z.object({ city: z.string() }),
+  execute: async ({ city }) => `It is sunny in ${city}.`,
+});
+
+const { text, toolCalls } = await generateText({
+  model: google.interactions('gemini-2.5-flash'),
+  tools: { getWeather: weatherTool },
+  stopWhen: stepCountIs(5),
+  prompt: 'What is the weather in San Francisco right now?',
+});
+```
+
+### Image output via Interactions
+
+Add a `{ type: 'image' }` entry to `responseFormat` on a Gemini
+image-capable model to get images as `LanguageModelV4FilePart` files in
+the response. No tool wrapping is required, and the entry doubles as the
+place to set `aspectRatio`, `imageSize`, and `mimeType`.
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions('gemini-3-pro-image-preview'),
+  prompt: 'Generate an image of a comic cat in a spaceship.',
+  providerOptions: {
+    google: {
+      responseFormat: [{ type: 'image' }],
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+
+for (const file of result.files) {
+  if (file.mediaType.startsWith('image/')) {
+    // file.uint8Array | file.base64 | file.mediaType
+  }
+}
+```
+
+To control aspect ratio, image size, or output mime type, add those
+fields to the same image entry:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions('gemini-3-pro-image-preview'),
+  prompt: 'Generate a high-quality landscape photo of mountains at sunset.',
+  providerOptions: {
+    google: {
+      responseFormat: [
+        {
+          type: 'image',
+          aspectRatio: '16:9',
+          imageSize: '4K',
+        },
+      ],
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+For multimodal output, list one entry per modality. The model returns
+text in `result.text` and the accompanying image(s) in `result.files`:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions('gemini-2.5-flash-image'),
+  prompt:
+    'Tell me a three sentence bedtime story about a unicorn, accompanied by a suitable illustration.',
+  providerOptions: {
+    google: {
+      responseFormat: [
+        { type: 'text' },
+        { type: 'image', aspectRatio: '16:9' },
+      ],
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+
+console.log(result.text);
+
+const images = result.files.filter(file => file.mediaType.startsWith('image/'));
+// images[0].uint8Array | images[0].base64 | images[0].mediaType
+```
+
+Iterative image editing pairs naturally with stateful chaining — keep
+`previousInteractionId` set across turns and the model edits its prior
+output:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const model = google.interactions('gemini-3-pro-image-preview');
+
+const turn1 = await generateText({
+  model,
+  prompt: 'Generate an image of a comic cat in a spaceship.',
+  providerOptions: {
+    google: {
+      responseFormat: [{ type: 'image' }],
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+
+const interactionId = turn1.providerMetadata?.google?.interactionId as
+  | string
+  | undefined;
+
+const turn2 = await generateText({
+  model,
+  prompt: 'now make the cat red',
+  providerOptions: {
+    google: {
+      responseFormat: [{ type: 'image' }],
+      previousInteractionId: interactionId,
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+### Agent presets
+
+Pass `{ agent: <name> }` to target a Gemini agent preset. The factory
+type-checks the agent name against the supported set:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions({
+    agent: 'deep-research-pro-preview-12-2025',
+  }),
+  prompt:
+    'Briefly summarize the most-cited papers on retrieval-augmented generation since 2024 (2-3 sentences).',
+  providerOptions: {
+    google: {
+      background: true,
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+Whether an agent runs synchronously or in the background depends on the
+agent. Long-running presets (such as the `deep-research-*` family)
+require `background: true` — the POST returns a non-terminal status and
+the SDK polls `GET /interactions/{id}` internally until the interaction
+completes. Other agents accept synchronous calls only and will reject
+`background: true`. Set the flag explicitly via
+`providerOptions.google.background`.
+
+The default polling timeout is 30 minutes; raise it via
+`pollingTimeoutMs` for slower agents:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+await generateText({
+  model: google.interactions({ agent: 'deep-research-max-preview-04-2026' }),
+  prompt: 'Produce a long-form research brief on ...',
+  providerOptions: {
+    google: {
+      background: true,
+      pollingTimeoutMs: 60 * 60 * 1000, // 1 hour
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+Agents also chain through `previousInteractionId` like model-id calls.
+
+### Managed Agents
+
+[Managed agents](https://ai.google.dev/gemini-api/docs/agents) run inside a
+sandboxed Linux environment provisioned per interaction. Pass the `environment`
+provider option to control how the sandbox is set up; the option is only
+accepted on agent calls.
+
+The simplest form provisions a fresh sandbox:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions({ agent: 'antigravity-preview-05-2026' }),
+  prompt: 'What is 2 + 2?',
+  providerOptions: {
+    google: {
+      environment: 'remote',
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+`environment` accepts three shapes:
+
+- `'remote'` — provision a fresh sandbox for this call.
+- any other string — an `environment_id` to reuse, forking the previous
+  sandbox so its filesystem and installed packages persist.
+- an object — provision a fresh sandbox and optionally preload `sources`
+  and/or constrain outbound traffic via `network`:
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+await generateText({
+  model: google.interactions({ agent: 'antigravity-preview-05-2026' }),
+  prompt:
+    'Read the file at /data/note.txt and tell me exactly what it contains.',
+  providerOptions: {
+    google: {
+      environment: {
+        type: 'remote',
+        sources: [
+          {
+            type: 'inline',
+            content: 'hello from the AI SDK example\n',
+            target: '/data/note.txt',
+          },
+        ],
+      },
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+Three source types are supported: `inline` (write a string into the
+sandbox at `target`), `repository` (clone a git repository — pass the
+URL as `source`), and `gcs` (mount a Google Cloud Storage prefix).
+
+The `network` field accepts the string `'disabled'` to block all
+outbound traffic, or an object with an `allowlist` array whose entries
+each carry a `domain` plus an optional `transform` array of header
+objects to inject into matching requests.
+
+#### Custom managed agents
+
+For user-defined agents that you created on Google's side via the
+Gemini API's `/v1beta/agents` endpoint, pass the agent's name through the dedicated
+`managedAgent` factory shape instead of `agent` (which only accepts
+known preset names):
+
+```ts
+import {
+  google,
+  type GoogleLanguageModelInteractionsOptions,
+} from '@ai-sdk/google';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: google.interactions({ managedAgent: 'my-custom-agent' }),
+  prompt: 'Hello!',
+  providerOptions: {
+    google: {
+      environment: 'remote',
+    } satisfies GoogleLanguageModelInteractionsOptions,
+  },
+});
+```
+
+### Streaming
+
+`streamText` is supported. The stream's `finish` part exposes
+`interactionId` on `providerMetadata.google` so callers can chain.
+
+```ts
+import { google } from '@ai-sdk/google';
+import { streamText } from 'ai';
+
+const result = streamText({
+  model: google.interactions('gemini-2.5-flash'),
+  prompt: 'Hello, how are you?',
+});
+
+for await (const textPart of result.textStream) {
+  process.stdout.write(textPart);
+}
+
+const googleMetadata = (await result.providerMetadata)?.google;
+console.log('Interaction id:', googleMetadata?.interactionId);
+```
+
 ## Gemma Models
 
 You can use [Gemma models](https://deepmind.google/models/gemma/) with the Google Generative AI API.
@@ -1111,12 +1726,12 @@ 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';
@@ -1158,7 +1773,7 @@ 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_
 
@@ -1167,7 +1782,6 @@ The following optional provider options are available for Google Generative AI e
 - **taskType**: _string_
 
   Optional. Specifies the task type for generating embeddings. Supported task types include:
-
   - `SEMANTIC_SIMILARITY`: Optimized for text similarity.
   - `CLASSIFICATION`: Optimized for text classification.
   - `CLUSTERING`: Optimized for clustering texts based on similarity.
@@ -1179,13 +1793,14 @@ The following optional provider options are available for Google Generative AI e
 
 - **content**: _array_
 
-  Optional. Per-value multimodal content parts for embedding non-text content (images, video, PDF, audio). Each entry corresponds to the embedding value at the same index — its parts are merged with the text value in the request. Use `null` for entries that are text-only. The array length must match the number of values being embedded. Each non-null entry is an array of parts, where each part can be either `{ text: string }` or `{ inlineData: { mimeType: string, data: string } }`. Supported by `gemini-embedding-2-preview`.
+  Optional. Per-value multimodal content parts for embedding non-text content (images, video, PDF, audio). Each entry corresponds to the embedding value at the same index — its parts are merged with the text value in the request. Use `null` for entries that are text-only. The array length must match the number of values being embedded. Each non-null entry is an array of parts, where each part can be `{ text: string }`, `{ inlineData: { mimeType: string, data: string } }` for inline base64 data, or `{ fileData: { fileUri: string, mimeType: string } }` to reference remote content via HTTP URL or Google Cloud Storage URI (`gs://...`). Supported by `gemini-embedding-2-preview`.
 
 ### Model Capabilities
 
 | Model                        | Default Dimensions | Custom Dimensions   | Multimodal          |
 | ---------------------------- | ------------------ | ------------------- | ------------------- |
 | `gemini-embedding-001`       | 3072               | <Check size={18} /> | <Cross size={18} /> |
+| `gemini-embedding-2`         | 3072               | <Check size={18} /> | <Check size={18} /> |
 | `gemini-embedding-2-preview` | 3072               | <Check size={18} /> | <Check size={18} /> |
 
 ## Image Models
@@ -1309,6 +1924,29 @@ const { image } = await generateImage({
   details.
 </Note>
 
+#### Google Search Grounding
+
+Gemini image models support [Google Search grounding](#google-search) through `providerOptions.google.googleSearch`. The value matches the args of `google.tools.googleSearch(...)`; pass `{}` to enable with defaults, or `{ searchTypes: { imageSearch: {} } }` to ground on reference photos.
+
+```ts
+import { google } from '@ai-sdk/google';
+import { generateImage } from 'ai';
+
+const result = await generateImage({
+  model: google.image('gemini-3.1-flash-image-preview'),
+  prompt:
+    'Search for live footage of the 2026 Super Bowl halftime show artist, then generate a close-up in space.',
+  providerOptions: {
+    google: {
+      googleSearch: { searchTypes: { imageSearch: {} } },
+    },
+  },
+});
+
+// Grounding metadata is forwarded onto the image result:
+console.log(result.providerMetadata?.google?.groundingMetadata);
+```
+
 #### Gemini Image Model Capabilities
 
 | Model                            | Image Generation    | Image Editing       | Aspect Ratios                                       |
@@ -1323,3 +1961,80 @@ const { image } = await generateImage({
   2K, 4K via `providerOptions.google.imageConfig.imageSize`), and Google Search
   grounding.
 </Note>
+
+## Speech Models
+
+You can create models that call the [Gemini text-to-speech API](https://ai.google.dev/gemini-api/docs/speech-generation)
+using the `.speech()` factory method.
+
+The first argument is the model id e.g. `gemini-2.5-flash-preview-tts`.
+
+```ts
+const model = google.speech('gemini-2.5-flash-preview-tts');
+```
+
+The `voice` argument can be set to one of Gemini's [30 prebuilt voices](https://ai.google.dev/gemini-api/docs/speech-generation#voices)
+e.g. `Kore`, `Puck`, `Zephyr`, or `Charon`. Voice names are case-sensitive. It defaults to `Kore`.
+
+```ts highlight="6"
+import { generateSpeech } from 'ai';
+import { google } from '@ai-sdk/google';
+
+const result = await generateSpeech({
+  model: google.speech('gemini-2.5-flash-preview-tts'),
+  text: 'Hello, world!',
+  voice: 'Kore', // Gemini voice name
+});
+```
+
+By default the generated audio is returned as a playable WAV file (`result.audio.mediaType` is
+`audio/wav`). Set `outputFormat: 'pcm'` to receive the raw signed 16-bit little-endian mono PCM
+bytes instead; the sample rate is reported in `result.providerMetadata.google.sampleRate`.
+
+Gemini honors natural-language style direction. The `instructions` argument is prepended to the
+spoken text, so `instructions: 'Say cheerfully'` with `text: 'Hello'` speaks `Say cheerfully: Hello`.
+
+### Multi-speaker audio
+
+For multi-speaker dialogue, pass a `multiSpeakerVoiceConfig` through `providerOptions`. Each speaker
+name must match a name used in the input text. When set, it overrides the top-level `voice`.
+
+```ts highlight="8-23"
+import { generateSpeech } from 'ai';
+import { google, type GoogleSpeechModelOptions } from '@ai-sdk/google';
+
+const result = await generateSpeech({
+  model: google.speech('gemini-2.5-flash-preview-tts'),
+  text: 'Joe: How are you? Jane: Doing great, thanks!',
+  providerOptions: {
+    google: {
+      multiSpeakerVoiceConfig: {
+        speakerVoiceConfigs: [
+          {
+            speaker: 'Joe',
+            voiceConfig: { prebuiltVoiceConfig: { voiceName: 'Kore' } },
+          },
+          {
+            speaker: 'Jane',
+            voiceConfig: { prebuiltVoiceConfig: { voiceName: 'Puck' } },
+          },
+        ],
+      },
+    } satisfies GoogleSpeechModelOptions,
+  },
+});
+```
+
+<Note>
+  Gemini TTS models do not support the `speed` or `language` options; passing
+  them adds a warning to `result.warnings`. Language is detected automatically
+  from the input text.
+</Note>
+
+### Model Capabilities
+
+| Model                          | Multi-speaker       | Style via instructions |
+| ------------------------------ | ------------------- | ---------------------- |
+| `gemini-2.5-flash-preview-tts` | <Check size={18} /> | <Check size={18} />    |
+| `gemini-2.5-pro-preview-tts`   | <Check size={18} /> | <Check size={18} />    |
+| `gemini-3.1-flash-tts-preview` | <Check size={18} /> | <Check size={18} />    |