@ai-sdk/google-vertex 5.0.59 → 5.0.60

package/docs/16-google-vertex.mdx

@@ -996,198 +996,10 @@ The following optional provider options are available for Google Vertex AI embed
 
 ### Image Models
 
-You can create image models using the `.image()` factory method. The Google Vertex provider supports both [Imagen](https://cloud.google.com/vertex-ai/generative-ai/docs/image/overview) and [Gemini image models](https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-flash-image). For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).
-
-#### Imagen Models
-
-[Imagen models](https://cloud.google.com/vertex-ai/generative-ai/docs/image/generate-images) generate images using the Imagen on Vertex AI API.
-
-```ts
-import { googleVertex } from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-
-const { image } = await generateImage({
-  model: googleVertex.image('imagen-4.0-generate-001'),
-  prompt: 'A futuristic cityscape at sunset',
-  aspectRatio: '16:9',
-});
-```
-
-Further configuration can be done using Google Vertex provider options. You can validate the provider options using the `GoogleVertexImageModelOptions` type.
-
-```ts
-import { googleVertex } from '@ai-sdk/google-vertex';
-import { GoogleVertexImageModelOptions } from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-
-const { image } = await generateImage({
-  model: googleVertex.image('imagen-4.0-generate-001'),
-  providerOptions: {
-    vertex: {
-      negativePrompt: 'pixelated, blurry, low-quality',
-    } satisfies GoogleVertexImageModelOptions,
-  },
-  // ...
-});
-```
-
-The following provider options are available:
-
-- **negativePrompt** _string_
-  A description of what to discourage in the generated images.
-
-- **personGeneration** `allow_adult` | `allow_all` | `dont_allow`
-  Whether to allow person generation. Defaults to `allow_adult`.
-
-- **safetySetting** `block_low_and_above` | `block_medium_and_above` | `block_only_high` | `block_none`
-  Whether to block unsafe content. Defaults to `block_medium_and_above`.
-
-- **addWatermark** _boolean_
-  Whether to add an invisible watermark to the generated images. Defaults to `true`.
-
-- **storageUri** _string_
-  Cloud Storage URI to store the generated images.
-
-<Note>
-  Imagen models do not support the `size` parameter. Use the `aspectRatio`
-  parameter instead.
-</Note>
-
-Additional information about the images can be retrieved using Google Vertex meta data.
-
-```ts
-import { googleVertex } from '@ai-sdk/google-vertex';
-import { GoogleVertexImageModelOptions } from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-
-const { image, providerMetadata } = await generateImage({
-  model: googleVertex.image('imagen-4.0-generate-001'),
-  prompt: 'A futuristic cityscape at sunset',
-  aspectRatio: '16:9',
-});
-
-console.log(
-  `Revised prompt: ${providerMetadata.vertex.images[0].revisedPrompt}`,
-);
-```
-
-##### Image Editing
-
-Google Vertex Imagen models support image editing through inpainting, outpainting, and other edit modes. Pass input images via `prompt.images` and optionally a mask via `prompt.mask`.
-
-<Note>
-  Image editing is supported by `imagen-3.0-capability-001`. The
-  `imagen-4.0-generate-001` model does not currently support editing operations.
-</Note>
-
-###### Inpainting (Insert Objects)
-
-Insert or replace objects in specific areas using a mask:
-
-```ts
-import {
-  googleVertex,
-  GoogleVertexImageModelOptions,
-} from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-import fs from 'fs';
-
-const image = fs.readFileSync('./input-image.png');
-const mask = fs.readFileSync('./mask.png'); // White = edit area
-
-const { images } = await generateImage({
-  model: googleVertex.image('imagen-3.0-capability-001'),
-  prompt: {
-    text: 'A sunlit indoor lounge area with a pool containing a flamingo',
-    images: [image],
-    mask,
-  },
-  providerOptions: {
-    vertex: {
-      edit: {
-        baseSteps: 50,
-        mode: 'EDIT_MODE_INPAINT_INSERTION',
-        maskMode: 'MASK_MODE_USER_PROVIDED',
-        maskDilation: 0.01,
-      },
-    } satisfies GoogleVertexImageModelOptions,
-  },
-});
-```
-
-###### Outpainting (Extend Image)
-
-Extend an image beyond its original boundaries:
-
-```ts
-import {
-  googleVertex,
-  GoogleVertexImageModelOptions,
-} from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-import fs from 'fs';
-
-const image = fs.readFileSync('./input-image.png');
-const mask = fs.readFileSync('./outpaint-mask.png'); // White = extend area
-
-const { images } = await generateImage({
-  model: googleVertex.image('imagen-3.0-capability-001'),
-  prompt: {
-    text: 'Extend the scene with more of the forest background',
-    images: [image],
-    mask,
-  },
-  providerOptions: {
-    vertex: {
-      edit: {
-        baseSteps: 50,
-        mode: 'EDIT_MODE_OUTPAINT',
-        maskMode: 'MASK_MODE_USER_PROVIDED',
-      },
-    } satisfies GoogleVertexImageModelOptions,
-  },
-});
-```
-
-###### Edit Provider Options
-
-The following options are available under `providerOptions.vertex.edit`:
-
-- **mode** - The edit mode to use:
-  - `EDIT_MODE_INPAINT_INSERTION` - Insert objects into masked areas
-  - `EDIT_MODE_INPAINT_REMOVAL` - Remove objects from masked areas
-  - `EDIT_MODE_OUTPAINT` - Extend image beyond boundaries
-  - `EDIT_MODE_CONTROLLED_EDITING` - Controlled editing
-  - `EDIT_MODE_PRODUCT_IMAGE` - Product image editing
-  - `EDIT_MODE_BGSWAP` - Background swap
-
-- **baseSteps** _number_ - Number of sampling steps (35-75). Higher values = better quality but slower.
-
-- **maskMode** - How to interpret the mask:
-  - `MASK_MODE_USER_PROVIDED` - Use the provided mask directly
-  - `MASK_MODE_DEFAULT` - Default mask mode
-  - `MASK_MODE_DETECTION_BOX` - Mask from detected bounding boxes
-  - `MASK_MODE_CLOTHING_AREA` - Mask from clothing segmentation
-  - `MASK_MODE_PARSED_PERSON` - Mask from person parsing
-
-- **maskDilation** _number_ - Percentage (0-1) to grow the mask. Recommended: 0.01.
-
-<Note>
-  Input images must be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
-  base64-encoded strings. URL-based images are not supported for Google Vertex
-  image editing.
-</Note>
-
-##### Imagen Model Capabilities
-
-| Model                           | Aspect Ratios             |
-| ------------------------------- | ------------------------- |
-| `imagen-3.0-generate-001`       | 1:1, 3:4, 4:3, 9:16, 16:9 |
-| `imagen-3.0-generate-002`       | 1:1, 3:4, 4:3, 9:16, 16:9 |
-| `imagen-3.0-fast-generate-001`  | 1:1, 3:4, 4:3, 9:16, 16:9 |
-| `imagen-4.0-generate-001`       | 1:1, 3:4, 4:3, 9:16, 16:9 |
-| `imagen-4.0-fast-generate-001`  | 1:1, 3:4, 4:3, 9:16, 16:9 |
-| `imagen-4.0-ultra-generate-001` | 1:1, 3:4, 4:3, 9:16, 16:9 |
+You can create Gemini image models using the `.image()` factory method. These
+models provide image output through the language model `:generateContent` API.
+For more on image generation with the AI SDK see
+[generateImage()](/docs/reference/ai-sdk-core/generate-image).
 
 #### Gemini Image Models
 
@@ -1222,20 +1034,11 @@ const { image } = await generateImage({
 });
 ```
 
-You can also use URLs (including `gs://` Cloud Storage URIs) for input images:
-
-```ts
-import { googleVertex } from '@ai-sdk/google-vertex';
-import { generateImage } from 'ai';
-
-const { image } = await generateImage({
-  model: googleVertex.image('gemini-2.5-flash-image'),
-  prompt: {
-    text: 'Add a small wizard hat to this cat',
-    images: ['https://example.com/cat.png'],
-  },
-});
-```
+<Note>
+  Input images must be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
+  base64-encoded strings. URL inputs, including HTTP and `gs://` URLs, are not
+  supported by `generateImage()` with Google Vertex image models.
+</Note>
 
 <Note>
   Gemini image models do not support the `size` or `n` parameters. Use
@@ -1260,8 +1063,8 @@ const { image } = await generateImage({
 <Note>
   `gemini-3-pro-image-preview` supports additional features including up to 14
   reference images for editing (6 objects, 5 humans), resolution options (1K,
-  2K, 4K via `providerOptions.vertex.imageConfig.imageSize`), and Google Search
-  grounding.
+  2K, 4K via `providerOptions.vertex.imageConfig.imageSize`). Use the
+  `GoogleVertexImageModelOptions` type to validate Gemini provider options.
 </Note>
 
 ### Video Models

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/google-vertex",
-  "version": "5.0.59",
+  "version": "5.0.60",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -73,8 +73,8 @@
   "dependencies": {
     "google-auth-library": "^10.6.2",
     "@ai-sdk/anthropic": "4.0.40",
-    "@ai-sdk/google": "4.0.48",
-    "@ai-sdk/openai-compatible": "3.0.33",
+    "@ai-sdk/google": "4.0.49",
+    "@ai-sdk/openai-compatible": "3.0.34",
     "@ai-sdk/provider": "4.0.7",
     "@ai-sdk/provider-utils": "5.0.28"
   },

package/src/google-vertex-image-model-options.ts

@@ -1,74 +1,6 @@
-import { z } from 'zod/v4';
+import type { GoogleLanguageModelOptions } from '@ai-sdk/google';
 
-export const googleVertexImageModelOptionsSchema = z.object({
-  negativePrompt: z.string().nullish(),
-  personGeneration: z
-    .enum(['dont_allow', 'allow_adult', 'allow_all'])
-    .nullish(),
-  safetySetting: z
-    .enum([
-      'block_low_and_above',
-      'block_medium_and_above',
-      'block_only_high',
-      'block_none',
-    ])
-    .nullish(),
-  addWatermark: z.boolean().nullish(),
-  storageUri: z.string().nullish(),
-  sampleImageSize: z.enum(['1K', '2K']).nullish(),
-  /**
-   * Configuration for image editing operations
-   */
-  edit: z
-    .object({
-      /**
-       * An integer that represents the number of sampling steps.
-       * A higher value offers better image quality, a lower value offers better latency.
-       * Try 35 steps to start. If the quality doesn't meet your requirements,
-       * increase the value towards an upper limit of 75.
-       */
-      baseSteps: z.number().nullish(),
-
-      // Edit mode options
-      // https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects
-      mode: z
-        .enum([
-          'EDIT_MODE_INPAINT_INSERTION',
-          'EDIT_MODE_INPAINT_REMOVAL',
-          'EDIT_MODE_OUTPAINT',
-          'EDIT_MODE_CONTROLLED_EDITING',
-          'EDIT_MODE_PRODUCT_IMAGE',
-          'EDIT_MODE_BGSWAP',
-        ])
-        .nullish(),
-
-      /**
-       * The mask mode to use.
-       * - `MASK_MODE_DEFAULT` - Default value for mask mode.
-       * - `MASK_MODE_USER_PROVIDED` - User provided mask. No segmentation needed.
-       * - `MASK_MODE_DETECTION_BOX` - Mask from detected bounding boxes.
-       * - `MASK_MODE_CLOTHING_AREA` - Masks from segmenting the clothing area with open-vocab segmentation.
-       * - `MASK_MODE_PARSED_PERSON` - Masks from segmenting the person body and clothing using the person-parsing model.
-       */
-      maskMode: z
-        .enum([
-          'MASK_MODE_DEFAULT',
-          'MASK_MODE_USER_PROVIDED',
-          'MASK_MODE_DETECTION_BOX',
-          'MASK_MODE_CLOTHING_AREA',
-          'MASK_MODE_PARSED_PERSON',
-        ])
-        .nullish(),
-
-      /**
-       * Optional. A float value between 0 and 1, inclusive, that represents the
-       * percentage of the image width to grow the mask by. Using dilation helps
-       * compensate for imprecise masks. We recommend a value of 0.01.
-       */
-      maskDilation: z.number().nullish(),
-    })
-    .nullish(),
-});
-export type GoogleVertexImageModelOptions = z.infer<
-  typeof googleVertexImageModelOptionsSchema
+export type GoogleVertexImageModelOptions = Omit<
+  GoogleLanguageModelOptions,
+  'responseModalities'
 >;

package/src/google-vertex-image-model.ts

@@ -2,27 +2,17 @@ import type { GoogleLanguageModelOptions } from '@ai-sdk/google';
 import { GoogleLanguageModel } from '@ai-sdk/google/internal';
 import type {
   ImageModelV4,
-  ImageModelV4File,
   LanguageModelV4Prompt,
   SharedV4Warning,
 } from '@ai-sdk/provider';
 import {
-  combineHeaders,
   convertToBase64,
-  convertUint8ArrayToBase64,
-  createJsonResponseHandler,
   generateId as defaultGenerateId,
-  parseProviderOptions,
-  postJsonToApi,
-  resolve,
   serializeModelOptions,
   WORKFLOW_SERIALIZE,
   WORKFLOW_DESERIALIZE,
   type Resolvable,
 } from '@ai-sdk/provider-utils';
-import { z } from 'zod/v4';
-import { googleVertexFailedResponseHandler } from './google-vertex-error';
-import { googleVertexImageModelOptionsSchema } from './google-vertex-image-model-options';
 import type { GoogleVertexImageModelId } from './google-vertex-image-settings';
 
 interface GoogleVertexImageModelConfig {
@@ -36,7 +26,6 @@ interface GoogleVertexImageModelConfig {
   };
 }
 
-// https://cloud.google.com/vertex-ai/generative-ai/docs/image/generate-images
 export class GoogleVertexImageModel implements ImageModelV4 {
   readonly specificationVersion = 'v4';
 
@@ -54,12 +43,7 @@ export class GoogleVertexImageModel implements ImageModelV4 {
     return new GoogleVertexImageModel(options.modelId, options.config);
   }
 
-  get maxImagesPerCall(): number {
-    if (isGeminiModel(this.modelId)) {
-      return 10;
-    }
-    return 4;
-  }
+  readonly maxImagesPerCall = 10;
 
   get provider(): string {
     return this.config.provider;
@@ -73,176 +57,24 @@ export class GoogleVertexImageModel implements ImageModelV4 {
   async doGenerate(
     options: Parameters<ImageModelV4['doGenerate']>[0],
   ): Promise<Awaited<ReturnType<ImageModelV4['doGenerate']>>> {
-    if (isGeminiModel(this.modelId)) {
-      return this.doGenerateGemini(options);
-    }
-    return this.doGenerateImagen(options);
-  }
-
-  private async doGenerateImagen({
-    prompt,
-    n,
-    size,
-    aspectRatio,
-    seed,
-    providerOptions,
-    headers,
-    abortSignal,
-    files,
-    mask,
-  }: Parameters<ImageModelV4['doGenerate']>[0]): Promise<
-    Awaited<ReturnType<ImageModelV4['doGenerate']>>
-  > {
-    const warnings: Array<SharedV4Warning> = [];
-
-    if (size != null) {
-      warnings.push({
-        type: 'unsupported',
-        feature: 'size',
-        details:
-          'This model does not support the `size` option. Use `aspectRatio` instead.',
-      });
-    }
-
-    const googleVertexImageOptions =
-      (await parseProviderOptions({
-        provider: 'googleVertex',
-        providerOptions,
-        schema: googleVertexImageModelOptionsSchema,
-      })) ??
-      (await parseProviderOptions({
-        provider: 'vertex',
-        providerOptions,
-        schema: googleVertexImageModelOptionsSchema,
-      }));
-
-    // Extract edit-specific options from provider options
-    const { edit, ...otherOptions } = googleVertexImageOptions ?? {};
-    const { mode: editMode, baseSteps, maskMode, maskDilation } = edit ?? {};
-
-    // Build the request body based on whether we're editing or generating
-    const isEditMode = files != null && files.length > 0;
-
-    let body: Record<string, unknown>;
-
-    if (isEditMode) {
-      // Build reference images for editing
-      const referenceImages: Array<Record<string, unknown>> = [];
-
-      // Add the source image(s)
-      for (let i = 0; i < files.length; i++) {
-        const file = files[i];
-        referenceImages.push({
-          referenceType: 'REFERENCE_TYPE_RAW',
-          referenceId: i + 1,
-          referenceImage: {
-            bytesBase64Encoded: getBase64Data(file),
-          },
-        });
-      }
-
-      // Add mask if provided
-      if (mask != null) {
-        referenceImages.push({
-          referenceType: 'REFERENCE_TYPE_MASK',
-          referenceId: files.length + 1,
-          referenceImage: {
-            bytesBase64Encoded: getBase64Data(mask),
-          },
-          maskImageConfig: {
-            maskMode: maskMode ?? 'MASK_MODE_USER_PROVIDED',
-            ...(maskDilation != null ? { dilation: maskDilation } : {}),
-          },
-        });
-      }
-
-      body = {
-        instances: [
-          {
-            prompt,
-            referenceImages,
-          },
-        ],
-        parameters: {
-          sampleCount: n,
-          ...(aspectRatio != null ? { aspectRatio } : {}),
-          ...(seed != null ? { seed } : {}),
-          editMode: editMode ?? 'EDIT_MODE_INPAINT_INSERTION',
-          ...(baseSteps != null ? { editConfig: { baseSteps } } : {}),
-          ...otherOptions,
-        },
-      };
-    } else {
-      // Standard image generation
-      body = {
-        instances: [{ prompt }],
-        parameters: {
-          sampleCount: n,
-          ...(aspectRatio != null ? { aspectRatio } : {}),
-          ...(seed != null ? { seed } : {}),
-          ...otherOptions,
-        },
-      };
+    if (!this.modelId.startsWith('gemini-')) {
+      throw new Error(
+        'Google image models other than Gemini are no longer supported. Use a model ID that starts with `gemini-`.',
+      );
     }
 
-    const currentDate = this.config._internal?.currentDate?.() ?? new Date();
-    const { value: response, responseHeaders } = await postJsonToApi({
-      url: `${this.config.baseURL}/models/${this.modelId}:predict`,
-      headers: combineHeaders(
-        this.config.headers ? await resolve(this.config.headers) : undefined,
-        headers,
-      ),
-      body,
-      failedResponseHandler: googleVertexFailedResponseHandler,
-      successfulResponseHandler: createJsonResponseHandler(
-        googleVertexImageResponseSchema,
-      ),
+    const {
+      prompt,
+      n,
+      size,
+      aspectRatio,
+      seed,
+      providerOptions,
+      headers,
       abortSignal,
-      fetch: this.config.fetch,
-    });
-
-    return {
-      images:
-        response.predictions?.map(
-          ({ bytesBase64Encoded }) => bytesBase64Encoded,
-        ) ?? [],
-      warnings,
-      response: {
-        timestamp: currentDate,
-        modelId: this.modelId,
-        headers: responseHeaders,
-      },
-      providerMetadata: (() => {
-        const payload = {
-          images:
-            response.predictions?.map(prediction => {
-              const {
-                // normalize revised prompt property
-                prompt: revisedPrompt,
-              } = prediction;
-
-              return { ...(revisedPrompt != null && { revisedPrompt }) };
-            }) ?? [],
-        };
-        return { googleVertex: payload, vertex: payload };
-      })(),
-    };
-  }
-
-  private async doGenerateGemini({
-    prompt,
-    n,
-    size,
-    aspectRatio,
-    seed,
-    providerOptions,
-    headers,
-    abortSignal,
-    files,
-    mask,
-  }: Parameters<ImageModelV4['doGenerate']>[0]): Promise<
-    Awaited<ReturnType<ImageModelV4['doGenerate']>>
-  > {
+      files,
+      mask,
+    } = options;
     const warnings: Array<SharedV4Warning> = [];
 
     if (mask != null) {
@@ -320,20 +152,29 @@ export class GoogleVertexImageModel implements ImageModelV4 {
       }),
     });
 
-    const userVertexOptions = (providerOptions?.googleVertex ??
-      providerOptions?.vertex) as
-      | Omit<GoogleLanguageModelOptions, 'responseModalities' | 'imageConfig'>
-      | undefined;
+    const {
+      responseModalities: _strippedResponseModalities,
+      imageConfig: userImageConfig,
+      ...userVertexOptions
+    } = ((providerOptions?.googleVertex ?? providerOptions?.vertex) as
+      | GoogleLanguageModelOptions
+      | undefined) ?? {};
     const innerVertexOptions: GoogleLanguageModelOptions = {
+      ...userVertexOptions,
       responseModalities: ['IMAGE'],
-      imageConfig: aspectRatio
-        ? {
-            aspectRatio: aspectRatio as NonNullable<
-              GoogleLanguageModelOptions['imageConfig']
-            >['aspectRatio'],
-          }
-        : undefined,
-      ...(userVertexOptions ?? {}),
+      imageConfig:
+        aspectRatio != null || userImageConfig != null
+          ? {
+              ...userImageConfig,
+              ...(aspectRatio != null
+                ? {
+                    aspectRatio: aspectRatio as NonNullable<
+                      GoogleLanguageModelOptions['imageConfig']
+                    >['aspectRatio'],
+                  }
+                : {}),
+            }
+          : undefined,
     };
     const result = await languageModel.doGenerate({
       prompt: languageModelPrompt,
@@ -386,39 +227,3 @@ export class GoogleVertexImageModel implements ImageModelV4 {
     };
   }
 }
-
-function isGeminiModel(modelId: string): boolean {
-  return modelId.startsWith('gemini-');
-}
-
-// minimal version of the schema, focussed on what is needed for the implementation
-// this approach limits breakages when the API changes and increases efficiency
-const googleVertexImageResponseSchema = z.object({
-  predictions: z
-    .array(
-      z.object({
-        bytesBase64Encoded: z.string(),
-        mimeType: z.string(),
-        prompt: z.string().nullish(),
-      }),
-    )
-    .nullish(),
-});
-
-/**
- * Helper to convert ImageModelV4File data to base64 string
- */
-function getBase64Data(file: ImageModelV4File): string {
-  if (file.type === 'url') {
-    throw new Error(
-      'URL-based images are not supported for Google Vertex image editing. Please provide the image data directly.',
-    );
-  }
-
-  if (typeof file.data === 'string') {
-    return file.data;
-  }
-
-  // Convert Uint8Array to base64
-  return convertUint8ArrayToBase64(file.data);
-}

package/src/google-vertex-image-settings.ts

@@ -1,10 +1,4 @@
 export type GoogleVertexImageModelId =
-  | 'imagen-3.0-generate-001'
-  | 'imagen-3.0-generate-002'
-  | 'imagen-3.0-fast-generate-001'
-  | 'imagen-4.0-generate-001'
-  | 'imagen-4.0-ultra-generate-001'
-  | 'imagen-4.0-fast-generate-001'
   | 'gemini-2.5-flash-image'
   | 'gemini-3-pro-image-preview'
   | 'gemini-3.1-flash-image-preview'