A lightning-fast ⚡ chat interface powered by Cerebras's API and built with Next.js
- 🧠 Access to powerful LLMs through Cerebras's API
- 🔄 Real-time chat with multiple model options
- ⏱️ Response time tracking for performance insights
- 📱 Fully responsive design for all devices
- 🌙 Dark mode support for comfortable viewing
- 🤔 "Thinking" states to see model reasoning
- 📋 Easy text copying functionality
- 🔌 Simple integration with Next.js applications
- ⚡ Llama 3.1 - 8B (
llama3.1-8b) - 🦙 Llama 3.3 - 70B (
llama-3.3-70b) - 🐦 Qwen 3 - 32B (
qwen-3-32b) - 🐦 Qwen 3 - 235B A22B Instruct 2507 (
qwen-3-235b-a22b-instruct-2507) - 🤖 GPT OSS - 120B (
gpt-oss-120b)
- Node.js 18.x or higher
- A Cerebras API key
- Clone the repository:
git clone https://github.com/xeven777/next-cerebras.git
cd next-cerebras- Install dependencies:
npm install
# or
yarn
# or
pnpm install- Create a
.env.localfile in the root directory:
CEREBRAS_API_KEY=your-api-key
- Start the development server:
npm run dev
# or
yarn dev
# or
pnpm dev- Open http://localhost:3000 in your browser.
- 🔤 Type your message in the input field
- 🔄 Select your preferred model from the dropdown
- 🚀 Hit "Send" or press Enter
- ⏱️ Watch as the AI responds with timing information
You can customize the application by:
- Adding new models to the
modelsarray inChatbox.tsx - Modifying the UI theme in your Tailwind configuration
- Adding new prompt suggestions for quick user interactions
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the project
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
- Cerebras for their powerful API
- Next.js for the React framework
- Vercel AI SDK for streaming capabilities