ExplainAI.dev is a centralized platform for tracking and comparing AI models. It provides up-to-date information on AI model benchmarks, pricing, capabilities, and real-world performance, helping developers, researchers, and businesses choose the best AI model for their needs.
- Catalog of AI models (GPT-4, Grok, Claude, DeepSeek, Mistral, Gemini, Llama, etc.).
- Each model includes:
- Performance Benchmarks
- Pricing (
$/1M tokens, $ /hour, etc.) - Speed & Latency (API response times)
- Training Data & Special Features
- Best Use Cases (chatbots, coding, research, etc.)
- Side-by-side comparisons of model performance.
- Filtering by:
- Best for Chatbots
- Best for Code Generation
- Best for Cost Efficiency
- Best for Low Latency
- Tracks API pricing for AI providers (OpenAI, Anthropic, DeepSeek, Mistral, etc.).
- Real-time updates on pricing changes.
- Sorting Options: Lowest Cost, Highest Accuracy, Best Performance.
| Category | Technology |
|---|---|
| Frontend | Next.js |
| UI Styling | Tailwind CSS |
| Data Storage | Static JSON/YAML files |
| Data Sources | LMSYS, OpenAI, Anthropic, DeepSeek, etc. |
| Deployment | Vercel |
| Content Management | MDX (Markdown + React |
- Automated AI model data scraping (?)
- Advanced filtering & sorting for AI model comparison
- User accounts & history tracking
I welcome contributions! Please follow these steps:
- Fork the repository.
- Create a new branch (
feature-branch-name). - Commit changes and push to your fork.
- Submit a pull request for review.
MIT License
For inquiries, reach out via email at contact@explainai.dev or open an issue on GitHub. Email isn't active yet!