IQ Routing sits in front of OpenAI-, Anthropic-, and other compatible LLM endpoints to select a lower-cost model for each request while preserving required quality. It supports chatbots, RAG pipelines, agent loops, and finance workloads, with caching and spend analytics for engineering teams.
In the Inference & model serving space, IQ Routing takes a focused approach. It focuses on reducing LLM spending and improving visibility by routing each request to the least expensive model that meets quality requirements. It is built as a B2B product for AI engineering and platform teams. There is a free tier. It ships for the web and API.
Among its 10 catalogued features are quality-based routing, cost optimization, and LLM caching. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match