Ramp Launches Router: LLM Gateway Cuts Inference Costs by 40%

SethGRosenberg · x · 2026-08-28

Ramp released 'Router', an LLM gateway designed to reduce inference costs by 40% on average by routing every request to the lowest-cost model that meets performance requirements. It consolidates access to multiple models (closed and open-source) behind a single API endpoint, supports automatic routing, and continuously rolls out new cost-saving strategies. Customer Delphi reported a 92% reduction in model costs after routing billions of tokens. The tool includes a CLI and offers free routing through 2026.

Original post →

More from Infra

Infra channel →