Skip to main content

LLM Gateway Core

A production-grade infrastructure component that abstracts multiple Large Language Model providers behind a single, unified API

Why LLM Gateway Core?

LLM Gateway Core provides reliable, cost-effective access to multiple LLM providers with intelligent routing, distributed caching, atomic rate limiting, and comprehensive observability. Built on FastAPI with Redis and Prometheus integration.

Multi-Provider Support

Abstract Gemini, Ollama, and custom providers behind a single API

Intelligent Routing

Route requests based on model hints: online, local, fast, or secure

Distributed Caching

Redis-backed response caching to reduce latency and API costs

Rate Limiting

Token bucket algorithm with atomic Redis operations

Quick Start

Get started with LLM Gateway Core in minutes.

Quickstart

Deploy with Docker Compose and make your first request

Architecture

Understand the system design and core components

API Reference

Explore the REST API endpoints and schemas

Key Features

Provider Abstraction

Seamlessly integrate cloud and local model providers

Observability

Full metrics with Prometheus and Grafana dashboards

Docker Deployment

Production-ready Docker Compose configuration

Configuration

Flexible environment-based configuration

Build docs developers (and LLMs) love