Features
OpenAI-compatible endpoint
Real-time provider benchmarking (price, latency, load)
Automatic cheapest/fastest routing
Support for closed and open LLMs
Restrict routing to specific providers
Performance constraint configuration
List all available models & family models
MakeHub Tools Layer for custom tooling
Direct integration with Cline and Roo Code forks
Command generative model: agentic, multimodal, 49 languages
North Mini Code open-source agentic coding model
Transcribe speech-to-text in 14 languages
Embed multimodal text representations for RAG
Rerank relevance boosting for search quality
Model Vault dedicated secure inference per instance
Private deployment in VPC, on-premises, or Model Vault
North enterprise AI workplace platform with agents
Compass intelligent search and discovery system
LLM serving fairness to prevent noisy neighbor effects
Customization via fine-tuning on proprietary data
Multi-layered security and industry certifications
API access with trial and production keys
Agentic tool orchestration and reasoning
Integration with Wiz for security incident automation via MCP
