diff --git a/common/api-review/vertexai.api.md b/common/api-review/vertexai.api.md
index d8c189a0059..2286824d45c 100644
--- a/common/api-review/vertexai.api.md
+++ b/common/api-review/vertexai.api.md
@@ -510,11 +510,7 @@ export interface ImagenSafetySettings {
 }
 
 // @public
-export enum InferenceMode {
-    ONLY_IN_CLOUD = "ONLY_IN_CLOUD",
-    ONLY_ON_DEVICE = "ONLY_ON_DEVICE",
-    PREFER_ON_DEVICE = "PREFER_ON_DEVICE"
-}
+export type InferenceMode = 'prefer_on_device' | 'only_on_device' | 'only_in_cloud';
 
 // @public
 export interface InlineDataPart {
diff --git a/docs-devsite/vertexai.md b/docs-devsite/vertexai.md
index 734a21fa3dc..3ad906c6e47 100644
--- a/docs-devsite/vertexai.md
+++ b/docs-devsite/vertexai.md
@@ -55,7 +55,6 @@ The Vertex AI in Firebase Web SDK.
 |  [ImagenAspectRatio](./vertexai.md#imagenaspectratio) | <b><i>(Public Preview)</i></b> Aspect ratios for Imagen images.<!-- -->To specify an aspect ratio for generated images, set the <code>aspectRatio</code> property in your [ImagenGenerationConfig](./vertexai.imagengenerationconfig.md#imagengenerationconfig_interface)<!-- -->.<!-- -->See the the [documentation](http://firebase.google.com/docs/vertex-ai/generate-images) for more details and examples of the supported aspect ratios. |
 |  [ImagenPersonFilterLevel](./vertexai.md#imagenpersonfilterlevel) | <b><i>(Public Preview)</i></b> A filter level controlling whether generation of images containing people or faces is allowed.<!-- -->See the <a href="http://firebase.google.com/docs/vertex-ai/generate-images">personGeneration</a> documentation for more details. |
 |  [ImagenSafetyFilterLevel](./vertexai.md#imagensafetyfilterlevel) | <b><i>(Public Preview)</i></b> A filter level controlling how aggressively to filter sensitive content.<!-- -->Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include 'harmful categories' (for example, <code>violence</code>, <code>sexual</code>, <code>derogatory</code>, and <code>toxic</code>). This filter level controls how aggressively to filter out potentially harmful content from responses. See the [documentation](http://firebase.google.com/docs/vertex-ai/generate-images) and the [Responsible AI and usage guidelines](https://cloud.google.com/vertex-ai/generative-ai/docs/image/responsible-ai-imagen#safety-filters) for more details. |
-|  [InferenceMode](./vertexai.md#inferencemode) | Determines whether inference happens on-device or in-cloud. |
 |  [Modality](./vertexai.md#modality) | Content part modality. |
 |  [SchemaType](./vertexai.md#schematype) | Contains the list of OpenAPI data types as defined by the [OpenAPI specification](https://swagger.io/docs/specification/data-models/data-types/) |
 |  [VertexAIErrorCode](./vertexai.md#vertexaierrorcode) | Standardized error codes that [VertexAIError](./vertexai.vertexaierror.md#vertexaierror_class) can have. |
@@ -132,6 +131,7 @@ The Vertex AI in Firebase Web SDK.
 
 |  Type Alias | Description |
 |  --- | --- |
+|  [InferenceMode](./vertexai.md#inferencemode) | Determines whether inference happens on-device or in-cloud. |
 |  [Part](./vertexai.md#part) | Content part - includes text, image/video, or function call/response part types. |
 |  [Role](./vertexai.md#role) | Role is the producer of the content. |
 |  [Tool](./vertexai.md#tool) | Defines a tool that model can call to access external knowledge. |
@@ -225,6 +225,16 @@ Possible roles.
 POSSIBLE_ROLES: readonly ["user", "model", "function", "system"]
 ```
 
+## InferenceMode
+
+Determines whether inference happens on-device or in-cloud.
+
+<b>Signature:</b>
+
+```typescript
+export type InferenceMode = 'prefer_on_device' | 'only_on_device' | 'only_in_cloud';
+```
+
 ## Part
 
 Content part - includes text, image/video, or function call/response part types.
@@ -491,24 +501,6 @@ export declare enum ImagenSafetyFilterLevel
 |  BLOCK\_NONE | <code>&quot;block_none&quot;</code> | <b><i>(Public Preview)</i></b> The least aggressive filtering level; blocks very few sensitive prompts and responses.<!-- -->Access to this feature is restricted and may require your case to be reviewed and approved by Cloud support. |
 |  BLOCK\_ONLY\_HIGH | <code>&quot;block_only_high&quot;</code> | <b><i>(Public Preview)</i></b> Blocks few sensitive prompts and responses. |
 
-## InferenceMode
-
-Determines whether inference happens on-device or in-cloud.
-
-<b>Signature:</b>
-
-```typescript
-export declare enum InferenceMode 
-```
-
-## Enumeration Members
-
-|  Member | Value | Description |
-|  --- | --- | --- |
-|  ONLY\_IN\_CLOUD | <code>&quot;ONLY_IN_CLOUD&quot;</code> | Exclusively uses the in-cloud model. |
-|  ONLY\_ON\_DEVICE | <code>&quot;ONLY_ON_DEVICE&quot;</code> | Exclusively uses the on-device model. Throws if one is not available. |
-|  PREFER\_ON\_DEVICE | <code>&quot;PREFER_ON_DEVICE&quot;</code> | Uses the on-device model if available, or falls back to the in-cloud model. |
-
 ## Modality
 
 Content part modality.
diff --git a/packages/vertexai/src/api.test.ts b/packages/vertexai/src/api.test.ts
index aeb090e24c5..7b25dbdf9e9 100644
--- a/packages/vertexai/src/api.test.ts
+++ b/packages/vertexai/src/api.test.ts
@@ -14,12 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-import {
-  ImagenModelParams,
-  InferenceMode,
-  ModelParams,
-  VertexAIErrorCode
-} from './types';
+import { ImagenModelParams, ModelParams, VertexAIErrorCode } from './types';
 import { VertexAIError } from './errors';
 import { ImagenModel, getGenerativeModel, getImagenModel } from './api';
 import { expect } from 'chai';
@@ -108,7 +103,7 @@ describe('Top level API', () => {
   });
   it('getGenerativeModel with HybridParams sets a default model', () => {
     const genModel = getGenerativeModel(fakeVertexAI, {
-      mode: InferenceMode.ONLY_ON_DEVICE
+      mode: 'only_on_device'
     });
     expect(genModel.model).to.equal(
       `publishers/google/models/${GenerativeModel.DEFAULT_HYBRID_IN_CLOUD_MODEL}`
@@ -116,7 +111,7 @@ describe('Top level API', () => {
   });
   it('getGenerativeModel with HybridParams honors a model override', () => {
     const genModel = getGenerativeModel(fakeVertexAI, {
-      mode: InferenceMode.ONLY_IN_CLOUD,
+      mode: 'prefer_on_device',
       inCloudParams: { model: 'my-model' }
     });
     expect(genModel.model).to.equal('publishers/google/models/my-model');
diff --git a/packages/vertexai/src/types/enums.ts b/packages/vertexai/src/types/enums.ts
index 57629e5c9f5..a9481d40f5f 100644
--- a/packages/vertexai/src/types/enums.ts
+++ b/packages/vertexai/src/types/enums.ts
@@ -240,23 +240,3 @@ export enum Modality {
    */
   DOCUMENT = 'DOCUMENT'
 }
-
-/**
- * Determines whether inference happens on-device or in-cloud.
- */
-export enum InferenceMode {
-  /**
-   * Uses the on-device model if available, or falls back to the in-cloud model.
-   */
-  PREFER_ON_DEVICE = 'PREFER_ON_DEVICE',
-
-  /**
-   * Exclusively uses the on-device model. Throws if one is not available.
-   */
-  ONLY_ON_DEVICE = 'ONLY_ON_DEVICE',
-
-  /**
-   * Exclusively uses the in-cloud model.
-   */
-  ONLY_IN_CLOUD = 'ONLY_IN_CLOUD'
-}
diff --git a/packages/vertexai/src/types/requests.ts b/packages/vertexai/src/types/requests.ts
index 345f98ca163..35a3c428d73 100644
--- a/packages/vertexai/src/types/requests.ts
+++ b/packages/vertexai/src/types/requests.ts
@@ -22,8 +22,7 @@ import {
   FunctionCallingMode,
   HarmBlockMethod,
   HarmBlockThreshold,
-  HarmCategory,
-  InferenceMode
+  HarmCategory
 } from './enums';
 import { ObjectSchemaInterface, SchemaRequest } from './schema';
 
@@ -233,3 +232,11 @@ export interface HybridParams {
    */
   inCloudParams?: ModelParams;
 }
+
+/**
+ * Determines whether inference happens on-device or in-cloud.
+ */
+export type InferenceMode =
+  | 'prefer_on_device'
+  | 'only_on_device'
+  | 'only_in_cloud';