Mengseang.
← Software/llm-router
API / Infrastructure2025

LLM Router

Self-hosted OpenAI-compatible API that routes LLM requests across 14 providers with automatic failover. Production-grade infrastructure.

LLMROUTERREQUESTOPENAI-COMPATIBLE · 14 PROV
Tech Stack
Node.jsTypeScriptNestJS
Metrics
Providers14
FailoverAuto
Links
Tags
APIAISelf-hosted
Skills & Tools
Node.jsTypeScriptNestJSOpenAI APIFailoverSelf-hosted
Key Features
01

OpenAI-compatible API: existing OpenAI clients work without code changes

02

Routing strategies: weighted, latency-priority, cost-priority, and model-pinned

03

Circuit breaker per provider to prevent retry storms during outages

04

Per-request provider selection via headers for workload-specific routing

05

Observability dashboard with p50/p95 latency, error rate, and cost per million tokens