ai-billing

• Middleware for the Vercel AI SDK
• Sends billing events directly to billing platforms (Stripe, Polar, and Lago)
• Ships with components to make usage-based billing easy

UI Components

Storybook: Explore the @ai-billing/nextjs components

<CreditTopUpPolar>

<CreditUsagePolar>

Full-stack examples

Name	Demo Link	Repo	Deploy
Chatbot (OpenRouter + Polar)	View Demo	GitHub
Chatbot (OpenAI + Polar)	View Demo	GitHub
Chatbot (Stripe)	View Demo	GitHub

Billing Architecture

Supported Providers

Provider	Package	Size
OpenRouter	@ai-billing/openrouter
OpenAI	@ai-billing/openai
Vercel AI Gateway	@ai-billing/gateway
OpenAI Compatible	@ai-billing/openai-compatible
Groq	@ai-billing/groq
Google Generative AI	@ai-billing/google
Anthropic	@ai-billing/anthropic
xAI Grok	@ai-billing/xai
MiniMax	@ai-billing/minimax
DeepSeek	@ai-billing/deepseek
Chutes	@ai-billing/chutes

Supported Destinations

Destination	Package	Size
Polar.sh	@ai-billing/polar
Stripe	@ai-billing/stripe
OpenMeter (Kong)	@ai-billing/openmeter
Lago	@ai-billing/lago

UI & SDKs

Package	Description	Size
@ai-billing/nextjs	Next.js UI components for displaying billing usage and managing top-ups.
@ai-billing/ui	Internal headless UI components shared across @ai-billing/* packages.
@ai-billing/narev	TypeScript SDK for the Narev billing API.

---

Installation

npm install @ai-billing/core @ai-billing/openrouter # Example for OpenRouter

Basic Usage

Wrap your model provider with the billing middleware and define your destinations.

import { streamText, wrapLanguageModel } from 'ai';
import { createOpenRouter } from '@openrouter/ai-sdk-provider';
import { createOpenRouterV3Middleware } from '@ai-billing/openrouter';

const billingMiddleware = createOpenRouterV3Middleware({});

const model = wrapLanguageModel({
  model: createOpenRouter({ apiKey: process.env.OPENROUTER_API_KEY })('google/gemini-2.0-flash-001'),
  middleware: billingMiddleware,
});

---

Send usage to Polar.sh

Wrap your model provider with the billing middleware and define your destinations.

import { streamText, wrapLanguageModel } from 'ai';
import { createOpenRouter } from '@openrouter/ai-sdk-provider';
import { createOpenRouterV3Middleware } from '@ai-billing/openrouter';
import { createPolarDestination } from '@ai-billing/polar';

const billingMiddleware = createOpenRouterV3Middleware({
  destinations: [
    createPolarDestination({
      accessToken: process.env.POLAR_ACCESS_TOKEN,
      eventName: 'llm_usage',
    })
  ],
});

const model = wrapLanguageModel({
  model: createOpenRouter({ apiKey: process.env.OPENROUTER_API_KEY })('google/gemini-2.0-flash-001'),
  middleware: billingMiddleware,
});

const { textStream } = await streamText({
  model,
  messages: [{ role: 'user', content: 'Quantify the value of metadata.' }],
  providerOptions: { 
    'ai-billing-tags': { userId: 'usr_123', org: 'Acme' } 
  },
});

Status and Roadmap

Note: We are prioritizing support for TEXT models.

Active Development

• Requesty
• Cloudflare AI Gateway

Full list of providers can be found here: https://ai-sdk.dev/providers/ The following providers are planned for future implementation. To prioritize a specific provider, please open a GitHub issue.

Architecture

The package consists of two primary components:

1. Provider Middleware

• specialized for @ai-sdk/* that understand the specific providerMetadata shapes of different LLM usage
• provider-specific cost calculation logic that that turn usage into cost
• PriceResolver allowing to pass custom prices at time of request

2. Destinations

• functions that receive a normalized BillingEvent and handle the API calls to external services
• allow charging in credits using standardized meters