AI Model Tokenization with Real-time Token Counting

Features · Deploy your own · Running locally

• Next.js
  • App Router with file-based routing and server components
  • Built-in API routes for token counting
• Shadcn/ui
  • Beautiful, accessible UI components built with Radix UI
  • Custom components for consistent design and developer experience
• Multiple AI Models
  • Support for various language models from SST's Models.dev database
  • Comprehensive model specifications, pricing, and capabilities data

You can deploy your own version of Tokenizer to Vercel with one click:

Deploy with Vercel

You will need to use the environment variables defined in .env.example to run Tokenizer. It's recommended you use Vercel Environment Variables for this, but a .env file is all that is necessary.

Note: You should not commit your .env file or it will expose secrets that will allow others to control access to your various accounts.

1. Clone the repository: git clone https://github.com/muradpm/tokenizer.git
2. Install Vercel CLI: bun i -g vercel
3. Link local instance with Vercel and GitHub accounts (creates .vercel directory): vercel link
4. Download your environment variables: vercel env pull

bun install
bun dev

Your app should now be running on localhost:3000