Skip to main content

​
Installation

npm install @ai-billing/google @ai-billing/core @ai-sdk/google ai

​
Overview

The @ai-billing/google package provides middleware for tracking token usage and calculating costs when using Google models with the Vercel AI SDK. It captures Google-specific metrics, such as internalReasoningTokens, inputCacheReadTokens, and inputCacheWriteTokens, ensuring that Prompt Caching and reasoning costs are accurately reflected.

​
Usage

To use the middleware, wrap your Google model using wrapLanguageModel from the ai package and pass the createGoogleMiddleware.
1

Initialize the Google provider

First, set up the Google provider using your API key.
import { createGoogleGenerativeAI } from '@ai-sdk/google';

const google = createGoogleGenerativeAI({
  apiKey: process.env.GOOGLE_AI_STUDIO_KEY,
});
2

Define model pricing

Set up a price resolver to define the costs for the models you’ll be using. For Google, you can specify costs for standard prompt/completion tokens, cached tokens (inputCacheReadTokens and inputCacheWriteTokens), and internalReasoningTokens.
import { createObjectPriceResolver } from '@ai-billing/core';

const priceResolver = createObjectPriceResolver({
  'models/gemini-3.1-flash-lite-preview': {
    promptTokens: 0.00000025, // $0.25 per 1M tokens
    completionTokens: 0.0000015, // $1.50 per 1M tokens
    inputCacheReadTokens: 0.000000025, // $0.025 per 1M tokens
    inputCacheWriteTokens: 0.00000008333333, // ~$0.083 per 1M tokens
    internalReasoningTokens: 0.0000015, // $1.50 per 1M tokens
  },
});
3

Create the billing middleware

Initialize the Google billing middleware. You need to provide a destination (such as consoleDestination) where billing events will be sent, along with your priceResolver.
import { createGoogleMiddleware } from '@ai-billing/google';
import { consoleDestination } from '@ai-billing/core';

const billingMiddleware = createGoogleMiddleware({
  destinations: [consoleDestination()],
  priceResolver: priceResolver,
});
4

Wrap the model

Use wrapLanguageModel from the ai package to apply the billing middleware to your Google model.
import { wrapLanguageModel } from 'ai';

const wrappedModel = wrapLanguageModel({
  model: google('models/gemini-3.1-flash-lite-preview'),
  middleware: billingMiddleware,
});
5

Use the wrapped model

Finally, use the wrapped model with AI SDK functions like generateText or streamText. The billing middleware will automatically track tokens, handle caching and reasoning metrics, and calculate costs.
import { generateText } from 'ai';

const result = await generateText({
  model: wrappedModel,
  prompt: 'What is the capital of Sweden?',
});