LLM Runner Router - Documentation

🧠 LLM Runner Router

v2.1.0

Home GitHub NPM

Getting Started

Overview Architecture Quick Examples

API Providers

Overview Quick Start OpenAI Anthropic OpenRouter Groq Hugging Face Local Inference Azure OpenAI Amazon Bedrock Google Vertex AI Mistral AI Together AI Fireworks AI DeepInfra Cohere Perplexity AI REST API Streaming Cost Optimization Rate Limiting Response Caching APILoader Reference

Provider Integration

Authentication Patterns Adapter Architecture Integration Plan Integration Checklist Integration Summary

Adapter Reference

OpenAI Adapter Anthropic Adapter Groq Adapter OpenRouter Adapter Custom Adapters

API Tutorials

Best Practices Chatbot with Fallback Cost-Effective RAG Streaming UI Integration Function Calling Migrate from OpenAI Migrate from LangChain Migrate from LlamaIndex

Advanced Topics

Custom Adapters Enterprise Features Advanced Routing

Core Documentation

API Reference Configuration Routing Strategies Model Formats Performance

Examples & Tutorials

Basic Usage Streaming Building APIs Docker & Deployment Monitoring

Operations

Deployment Security Troubleshooting

Development

Plugin Development FAQ Glossary

Home > Documentation

Loading documentation...

🧠 LLM Runner Router

Universal Model Orchestration System - Intelligently route between any AI model, anywhere, with blazing fast performance.

GitHub NPM Package Support Echo AI Systems

Built with 💚 by Echo AI Systems

Open source • MIT Licensed • Production Ready • Last updated: