Skip to main content

​
Installation

npm install @ai-billing/minimax @ai-billing/core @ai-sdk/anthropic ai

​
Overview

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

​
Usage

To use the middleware, wrap your Minimax model (which is accessed via the Anthropic provider) using wrapLanguageModel from the ai package and pass the createMinimaxMiddleware.
1

Initialize the Minimax provider

First, set up the provider using the Anthropic SDK with the Minimax base URL and your API key.
import { createAnthropic } from '@ai-sdk/anthropic';

const minimax = createAnthropic({
  apiKey: process.env.MINIMAX_API_KEY,
  baseURL: 'https://api.minimax.io/anthropic/v1',
});
2

Define model pricing

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

const priceResolver = createObjectPriceResolver({
  'minimax-m1': {
    promptTokens: 0.0000004, // 0.4 per 1M tokens
    completionTokens: 0.0000016, // 1.6 per 1M tokens
    internalReasoningTokens: 0.0000016, // 1.6 per 1M tokens
  },
});
3

Create the billing middleware

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

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

Wrap the model

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

const wrappedModel = wrapLanguageModel({
  model: minimax('minimax-m1'),
  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 reasoning metrics, and calculate costs.
import { generateText } from 'ai';

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