# Blog

> Benchmarks, engineering notes, and product updates from the team building Fabric Gateway.

Fabric Gateway, from Postman. This is the Markdown version of https://fabricgateway.ai/blog/.

## [Adaptive Model Routing in Fabric Gateway: Cutting LLM Costs 50–80% on Most Workloads](https://fabricgateway.ai/blog/adaptive-model-routing-in-fabric-gateway/)

How adaptive model routing in Fabric Gateway classifies each request once and routes it to a cheap, medium or strong model tier, cutting LLM costs 50–80% for a 1–3 point quality drop, with benchmark results for OpenAI and Anthropic.

By [Arpit Kumar](https://www.linkedin.com/in/arpitsr/) and [Anand Keshavan](https://www.linkedin.com/in/anand-kumar-keshavan-18829a1/) · October 13, 2026 · 7 min read

---

- [Homepage](https://fabricgateway.ai/)
- [Pricing](https://fabricgateway.ai/pricing/)
- [Book a demo](https://fabricgateway.ai/book-demo/)
- [Documentation](https://docs.fabricgateway.ai)
- [Sign up and log in](https://app.fabricgateway.ai)
- [Site summary for AI assistants](https://fabricgateway.ai/llms.txt)