Skip to content

README.md

Latest commit

 

History

History
62 lines (45 loc) · 1.84 KB

README.md

File metadata and controls

62 lines (45 loc) · 1.84 KB
Raw

LLMeter

LLMeter is a tool designed to help you test and evaluate prompts for various language models. It provides insights into performance and cost, allowing you to optimize your usage effectively.

Image

Features

  • Multi-Model Support: Test prompts across GPT-3.5-turbo, Gemini-2.0-flash, and more
  • Cost Intelligence: Real-time token cost estimation with currency conversion
  • Performance Metrics: Response time tracking and quality comparisons
  • Prompt Versioning: Save and compare different prompt variations
  • API Agnostic: Works with multiple LLM providers simultaneously
  • Security First: API keys stored locally in browser storage

Quick Start

Live Demo

Access the production deployment directly:
👉 llmeter.vercel.app

Local Development

  1. Clone the repository:

    git clone https://github.com/IremOztimur/llmeter.git

  2. Install dependencies:

    cd llmeter && npm install

  3. Start the development server:

    npm run dev

  4. Access at http://localhost:3000

Configuration

Model Setup

  1. Click Config in the navigation bar
  2. Select your target model from the dropdown
  3. Add your API keys:
    • Get OpenAI API Key
    • Get Gemini API Key
  4. Save configuration

Configuration Screenshot

Image

Contributing 🤝

Contributions are welcome! Please follow these steps:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit changes (git commit -m 'Add amazing feature')
  4. Push to branch (git push origin feature/amazing-feature)
  5. Open a Pull Request