Skip to content

Inference API (HLD Inference Gateway)

HLD Inference Gateway is the high-performance intelligence broker for the High Limit Designs ecosystem. It provides a unified OpenAI-compatible REST API that abstracts multiple model backends.

Features

  • OpenAI Compatibility: Seamlessly integrate with any tool that supports the /v1 protocol.
  • Model Routing: Dynamically route requests between local GGUF models and high-tier providers.
  • Dark Mesh Integration: Direct connectivity to Fleet agents.

Endpoint

https://api.highlimitdesigns.com/v1