System Settings & AI Model Gateway
Configure model providers, API keys, RBAC roles, and S3 asset storage.
Active LLM Provider Gateway
Groq LPUEngine (Ultra-Fast Llama 3.3)
Lightning fast sub-100ms open-weights inference
Auto-Switching Gateway (Recommended)
Intelligently selects fastest available provider
OpenAI GPT-4o
High intelligence reasoning and function calling
Anthropic Claude 3.5 Sonnet
Superior complex coding & analytical depth
Google Gemini 1.5 Pro
Ultra-long context window RAG processing
Local Ollama (Llama 3 / Mistral)
100% On-Premise offline privacy model