Providers¶
LLM Client supports multiple LLM providers. Each provider has its own set of models and configuration options.
Supported Providers¶
- OpenAI - GPT-4o, GPT-4o-mini, GPT-3.5-turbo
- Groq - Llama 3.3, Mixtral (Ultra-fast inference)
- Gemini - Google's Gemini Pro and Flash models
- Ollama - Local LLMs (Llama 3, Phi-3, etc.)
- Ollama Cloud - Access powerful models without a local GPU
- KI Connect - AI infrastructure for universities in NRW
How to get API Keys¶
To use most providers, you need an API key. Please refer to the specific provider page for instructions on how to obtain one: