Available Models

This document provides a comprehensive list of all available AI models in our system. Each model has a unique identifier that can be used when making API requests or configuring your applications.

Model IDs

Below is the complete list of model IDs that you can use:

• gpt-4o-mini: A lightweight version of GPT-4 optimized for faster responses and lower resource usage
• gpt-4o: The standard GPT-4 model offering high-quality responses and advanced reasoning capabilities
• gpt-3.5-turbo: Fast and efficient model suitable for general-purpose tasks with good performance
• claude-3.5-sonnet: Anthropic's Claude 3.5 Sonnet model known for its balanced performance and reliability
• gemini-1.5-flash: Google's Gemini model optimized for quick responses and efficient processing
• llama-3.1-70b-instruct: Meta's 70B parameter Llama model fine-tuned for instruction following
• llama-3.1-405b-instruct: Meta's largest 405B parameter Llama model with advanced capabilities
• deepseek-chat: DeepSeek's chat-optimized model offering strong conversational abilities
• mistral-large-latest: Mistral's latest large model providing high-quality responses and reasoning

Usage

When making API requests or configuring your application, you can use any of these model IDs to specify which AI model you want to use. The default model is gpt-4o-mini.

For detailed information about each model's capabilities and best use cases, please refer to our API documentation.