> ## Documentation Index
> Fetch the complete documentation index at: https://narev.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# CreateGoogleVertexV4Middleware

[**@ai-billing/google-vertex**](../index)

***

[@ai-billing/google-vertex](/docs/sdk/ai-billing/reference/google-vertex/typedoc/index) / createGoogleVertexV4Middleware

# Function: createGoogleVertexV4Middleware()

> **createGoogleVertexV4Middleware**\<`TTags`>(`options`): `LanguageModelV4Middleware`

Defined in: [google-vertex/src/ai-sdk/language-model-middleware/v4/language-model-v4-google-vertex-billing-middleware.ts:112](https://github.com/narevai/ai-billing/blob/main/packages/google-vertex/src/ai-sdk/language-model-middleware/v4/language-model-v4-google-vertex-billing-middleware.ts#L112)

Creates a V4 billing middleware for the Google Vertex AI provider (`@ai-sdk/google-vertex`).
Maps Vertex's Gemini-native usage into billing fields (adding `thoughtsTokenCount` back into the billed
completion count) and resolves cost from pricing plus usage.

Vertex's `trafficType` (`ON_DEMAND` vs `PROVISIONED`) is surfaced on the emitted event's
`usage.subProvider`, but is **not** used to change the billed rate — provisioned-throughput calls are
billed at the same resolved rate as on-demand calls. See calculateGoogleVertexCost.

## Type Parameters

### TTags

`TTags` *extends* `JSONObject`

The shape of the tags object, extending DefaultTags.

## Parameters

### options

[`GoogleVertexV4MiddlewareOptions`](/docs/sdk/ai-billing/reference/google-vertex/typedoc/interfaces/GoogleVertexV4MiddlewareOptions)\<`TTags`>

Billing options; see [GoogleVertexV4MiddlewareOptions](/docs/sdk/ai-billing/reference/google-vertex/typedoc/interfaces/GoogleVertexV4MiddlewareOptions).

## Returns

`LanguageModelV4Middleware`

A V4 billing middleware instance for Google Vertex AI.

## Example

```ts theme={null}
import { createVertex } from '@ai-sdk/google-vertex';
import { wrapLanguageModel } from 'ai';
import { createGoogleVertexV4Middleware } from '@ai-billing/google-vertex';
import {
  consoleDestination,
  createObjectPriceResolver,
  type ModelPricing,
} from '@ai-billing/core';

const vertex = createVertex({
  project: process.env.GOOGLE_VERTEX_PROJECT,
  location: process.env.GOOGLE_VERTEX_LOCATION,
});

const customPricingMap: Record<string, ModelPricing> = {
  'gemini-2.5-flash': {
    promptTokens: 0.3 / 1_000_000, // $0.30 per 1M tokens
    completionTokens: 2.5 / 1_000_000, // $2.50 per 1M tokens
    internalReasoningTokens: 2.5 / 1_000_000, // $2.50 per 1M tokens
  },
};

const priceResolver = createObjectPriceResolver(customPricingMap);

const billingMiddleware = createGoogleVertexV4Middleware({
  destinations: [consoleDestination()],
  priceResolver,
});

const wrappedModel = wrapLanguageModel({
  model: vertex('gemini-2.5-flash'),
  middleware: billingMiddleware,
});
```