Ramp Launches Router.com to Cut Companies' Rising AI Bills
Article excerpt
Highlighted: the sentence this signal was extracted from
Router the right model for every request based on performance and cost; customers save 40% on average NEW YORK, Aug. 19, 2026 /PRNewswire/ -- Ramp today launched Router.com , a single endpoint to every major AI model. Each request is routed to the lowest-cost model that meets the required performance level. Unlike a routing layer alone, Router connects model selection decisions to Ramp's broader AI spend visibility and controls, giving companies a clearer view of what AI work costs, who owns it, and where to optimize. Customers already using Router have reduced their inference costs by 40% on average. It is live now at router.com and free through 2026. AI has become one of the fastest-growing business expenses; AI spend has grown 20.7x since June 2025, according to the Ramp AI Index. Different tasks call for different models. The best model for a job should get that job, and today it usually doesn't. "AI is the fastest-growing line item at most companies, and the one they can least measure," said Rahul Sengottuvelu, Chief Technology Officer at Ramp. "Router puts every token in one place and sends each request to the model that delivers the right performance at the right cost." How Router works Developers connect through one API and reach models from OpenAI, Anthropic, and SpaceXAI, with Gemini coming soon, alongside leading open models including Nvidia, Kimi, DeepSeek, GLM...
Keep reading with a free account
The rest of this article, and every signal for Ramp, is in your free account.
