# Chat Models

Welcome to the comprehensive guide for chat models available with Apexify.js. This README covers all the chat models you can use, categorized by provider and type.

• v3: Versatile and high-performance model for general-purpose chat.
• v3-32k: Extended context model for handling larger conversations.
• turbo: Optimized for faster responses and efficiency.
• turbo-16k: Extended context version of the turbo model.
• gemini: Advanced model with improved understanding and responses.
• llama3-70b: Large model with extensive capabilities.
• llama3-8b: Smaller variant for more specific applications.
• mixtral-8x7b: Special model for mixed-task handling.
• gemma-7b: High-performance model for diverse interactions.
• gemma2-9b: Enhanced version of the Gemma model.

• gemma-7b-it: Italian variant of the Gemma model.
• gemma2-9b-it: Italian variant of the Gemma2 model.
• llama3-groq-70b-8192-tool-use-preview: Tool-usage preview model with extensive capabilities.
• llama3-groq-8b-8192-tool-use-preview: Smaller tool-usage preview model.
• llama-3.1-70b-versatile: Versatile model with extensive features.
• llama-3.1-8b-instant: Instant response model with a focus on speed.
• llama-guard-3-8b: Model with enhanced safety features.
• llama3-70b-8192: Large model for deep and comprehensive conversations.
• llama3-8b-8192: Smaller variant for focused interactions.
• mixtral-8x7b-32768: Extended context model for mixed tasks.

• bard: General-purpose chat model with creative capabilities.
• bing: Search-focused model with integrated web results.
• codellama: Model specialized for coding-related queries.
• gemini: Similar to the Hercules version with unique features.
• llama: General-purpose model with balanced performance.
• mixtral: Versatile model for various applications.
• openchat: Model focused on open-domain conversations.
• v4: Latest generation model with advanced features.

• o1-mini: Lightweight model optimized for basic interactions.
• o1-preview: Preview model for early-stage testing of advanced features.
• claude-3.5-sonnet-200k: High-capacity model with extended context support.
• claude-3-sonnet-200k: Similar to Claude-3.5, but with optimizations for speed.
• gpt-4-turbo: Optimized version of GPT-4 with enhanced performance.
• command-r-plus: Enhanced model for command-based tasks.
• command-r: Standard command-response model for task handling.
• gpt-4: Standard GPT-4 model with full capabilities.
• chatgpt-4o-latest: Latest optimized version of GPT-4o for improved speed and accuracy.

-# Note: There is a default apiKey but limited. To get your own apikey join:

• apexai: Custom model for specialized applications.
• facebook_ai: Model developed by Facebook for diverse interactions.
• yi_34b: Model with a focus on advanced conversational capabilities.
• starChat: Model for engaging and dynamic conversations.

• gpt-4o: Specialized version of GPT-4 for optimized performance.

-# Note: There is a default apiKey but limited. To get your own apikey join:

• gemini-pro: Enhanced version of the Gemini model with advanced features.
• gemini-flash: High-speed variant of the Gemini model optimized for fast responses.

To use any of these chat models, you need to install Apexify.js. Follow the installation instructions below:

npm install apexify.js

pnpm add apexify.js

yarn add apexify.js

bun add apexify.js

Feel free to explore the models and integrate them into your applications. For further assistance or if you have any questions, reach out via Discord!