Skip to content
HyperInfer

HyperInfer Documentation

Welcome to the HyperInfer documentation! HyperInfer is a modular, high-performance LLM gateway built in Rust.

Overview

HyperInfer combines a data plane (thick client for zero-latency LLM calls with local routing, caching, and rate limiting) with a control plane (centralized server for configuration management, authentication, MCP hosting, and an OpenAI-compatible proxy).

  • ⚡ Get Started — Install HyperInfer and make your first LLM call in minutes

    Get Started

  • Architecture — Understand the data plane / control plane architecture

    Architecture

  • Guides — Deep dives into routing, providers, monitoring, and more

    Guides

  • Docker Deployment — Docker, Kubernetes, and configuration reference

    Deployment

  • API Reference — Auto-generated docs for Rust and Python APIs

    API Reference

  • Contributing — How to get involved

    Contributing