IQ Routing

IQ Routing is a gateway that sits between your application and LLM providers like OpenAI, Anthropic, and Google. Instead of sending every request to your most expensive model, it evaluates each call and routes it to the cheapest model that still meets your quality standards. The company reports spend reductions of 40 to 80 percent on their own traffic. You can start using it in about thirty seconds by pointing your existing OpenAI or Anthropic SDK at a single base URL.

The core of the service is a classifier that reads each request for true difficulty, then weighs cost and latency across providers before picking a model. It also includes a semantic cache that catches repeated queries and similar ones, returning answers without charging you again. For teams using tools like Claude Code or Cursor that lock you into one model family, IQ Routing stays within that family while still routing to the right tier for each step. The dashboard shows live request feeds, per-team budgets, audit logs, and a breakdown of costs by model.

This tool is built for engineering teams running production chatbots, RAG pipelines, or agent loops who want to control rising LLM costs without sacrificing quality. It also helps finance and operations teams track exactly where money goes, with per-team budgets and detailed cost splits. The free tier supports up to 240 requests per minute with bring-your-own-keys, and paid plans add alerting, custom routing bands, and on-prem deployment options.