Key facts
- Ramp has launched an AI model routing service named Router.
- The service allows users to access and switch between multiple large language models via an API.
- Router provides access to models from OpenAI, Anthropic, Nvidia, xAI, and others.
- It offers customizable routing strategies based on user preferences and performance benchmarks.
- Ramp will retain model inputs and outputs for one year by default, with PII removed.
Ramp, a corporate expense management platform, has launched its own AI model routing service called Router. The service allows users and companies to access and switch between various large language models (LLMs) through a single API. Ramp has reportedly been using this internal tool for its own AI needs for the past three years.
Router is currently available only in the United States and will be free to use through the end of 2026, though users will still incur costs for AI model inference. The company also offered a $26 credit as a launch promotion, but has not disclosed pricing for 2027.
The service provides access to a range of LLMs, including those from OpenAI, Anthropic, DeepSeek, Moonshot, Minimax, Nvidia, xAI, and Z.ai. It features several routing strategies designed to help customers direct AI requests to specific models based on preferences, such as prioritizing flexible usage tiers, optimizing for cost and latency using user-defined benchmarks, or routing complex problems to more powerful models.
Users will have access to a dashboard that tracks token spend, costs, latency, and fallback attempts. Ramp has implemented an opt-out data retention policy, recording model inputs, outputs, and tool calls for one year by default, with personally identifiable information to be removed before use for product improvement.
For Ramp, this move into AI model routing presents a dual opportunity: to capitalize on the growing AI inference market and to offer its existing client base a service that complements its current expense management and AI token usage monitoring products. The company also aims to build relationships with AI labs and inference providers, potentially attracting new customers and driving sales of its core expense management solutions.