Ramp Launches AI Model Routing Service Router
· Technology · TechCrunch
Ramp, a corporate expense‑management platform, unveiled Router, an AI model routing service that lets users switch between large language models from providers such as OpenAI, Anthropic, DeepSeek, Moonshot, Minimax, Nvidia, xAI and Z.ai through a single API. The service is free through the end of 2026, although users still pay for inference costs, and includes a $26 credit on launch. Router offers dashboards that display token spend, cost, latency and fallback attempts, and it records inputs and outputs for one year unless users opt out. The platform currently operates only in the United States and the company has not announced a pricing model beyond 2026. Ramp plans to use Router to enter the AI inference market and provide a tightly integrated routing tool for its existing expense‑management clients. The service is positioned similarly to OpenRouter but with fewer model options available to customers.
Why it matters
Corporate users in the United States using Ramp gain a cost‑control tool that lets them compare and schedule calls to multiple large language models without changing APIs. The availability of a free router until 2026 could encourage firms to test different models before committing to expensive inference contracts.
Read the original report — TechCrunch
Join us on Telegram
Breaking news the moment it lands. At 10,000 members we ship the Android app.