Corporate expense management platform Ramp launched its AI model routing service, Router, on Wednesday evening. The service enables users and companies to utilise and switch between various large language models (LLMs) via an API.
Ramp stated it has been using this router internally for its own AI needs over the past three years. Router is currently available only in the United States and is free to use for the rest of 2026, though users must still cover AI model inference costs. A $26 credit launch offer is also included.
The service provides access to models from providers such as OpenAI, Anthropic, DeepSeek, Moonshot, Minimax, Nvidia, xAI, and Z.ai. Router also includes several strategies for customers to route AI requests based on preferences, such as setting preferences for model providers' flex usage tiers or routing difficult problems to more expensive models.
Users receive a dashboard to monitor details like token spend, cost, latency, and fallback attempts. Router has an opt-out data retention policy, recording model inputs, outputs, and tool calls for one year by default, with personally identifiable information removed before product improvement use.