Architecture
Model Routing Guide
Routing strategies across LLM providers and model tiers — cost-aware selection, fallback chains, and capability-based dispatch.
Intermediate
Routing strategies across LLM providers and model tiers — cost-aware selection, fallback chains, and capability-based dispatch.
Full guide coming soon.
Learning Path
Continue Learning
architecture
Production
Related Guides
- AI Gateway
AI gateway architecture — unified API layer for model routing, auth, rate limiting, observability, and cost control.
- Cost Optimization
Reducing LLM spend — workload-based model routing, prompt compression, caching, batching, and token-aware context design.
- Latency Optimization
Making AI systems fast — TTFT, streaming, parallel retrieval, caching, and routing simple steps to faster model tiers.
Related Tools
| Tool | Category | Purpose | Website | Best For |
|---|---|---|---|---|
| LangChain PopularOpen SourceAPI | frameworks | Framework for building LLM-powered applications and workflows. | langchain.com | RAG systems |