tutorials · 1 min read
Tutorial: Route Requests Through the LLM Gateway
Configure cost-aware routing across OpenAI, Anthropic and a self-hosted model - with fallback, caching and budgets - in 10 minutes.
BABhogar AI TeamProduct & Engineering
The LLM gateway is the easiest place to cut AI cost without losing quality. This tutorial sets up cost-aware routing across three providers.
Why it matters
You will configure routes that send easy queries to a small model, hard queries to a flagship, and fall back gracefully on outage.
How Bhogar AI approaches it
Open Gateway settings, add provider keys (or BYOK), define route policy, set budgets and fallback chains, point your app at the gateway endpoint.
- Add provider credentials (or BYOK)
- Define route policy on cost + capability
- Set per-tenant budgets
- Configure fallback chain
- Point your app at the gateway endpoint
What you get
Ten minutes to active cost-aware routing with fallback, budgets and observability.