Skip to main content

​
Installation

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

​
Overview

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

​
Usage

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

Initialize the xAI provider

First, set up the xAI provider using your API key.
import { createXai } from '@ai-sdk/xai';

const xai = createXai({
  apiKey: process.env.XAI_API_KEY,
});
2

Define model pricing

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

const priceResolver = createObjectPriceResolver({
  'grok-3-mini': {
    promptTokens: 0.000003,
    completionTokens: 0.000015,
    inputCacheReadTokens: 0.0000003,
    inputCacheWriteTokens: 0.00000375,
  },
});
3

Create the billing middleware

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

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

Wrap the model

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

const wrappedModel = wrapLanguageModel({
  model: xai('grok-3-mini'),
  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 metrics, and calculate costs.
import { generateText } from 'ai';

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