Ramp, the expense management company, just opened its internal LLM gateway to everyone. Router is an API product: one OpenAI-compatible endpoint that routes each request to the cheapest model clearing its quality bar. Early users cut inference costs 40% on average. This isn’t a v1 — Ramp has run it internally for three years, currently pushing 2.75T+ tokens a month.
One endpoint, automatic cost routing
Integration is a base URL swap: keep your OpenAI SDK, point it at Router, and requests get routed across OpenAI, Anthropic, DeepSeek, Moonshot, xAI and other models — with automatic fallbacks when a provider degrades. A dashboard tracks token spend, latency, and fallback events per use case. Free through 2026 (you still pay inference), $26 starting credit, US-only for now.
Why a fintech is giving this away
Stripe bought OpenRouter for $7B+ on August 16. Ramp answered on August 20 with a free competitor. LLM routing is now a giants’ game, and both fintechs see the same thing: whoever routes your tokens sees your AI spend. Ramp already sells AI expense management — the gateway is the wedge, the spend data is the prize.
You Might Also Like
- Cursor Composer 2 Takes on Anthropic and Openai With a 0 50 m Token Coding Model and the Benchmarks Back it up
- Meta Model api Muse Spark 1 1 Undercuts Openai and Anthropic at 1 25 4 25 per Million Tokens
- 13b Into Openai yet Microsoft Copilot Cowork Runs on Anthropic Claude
- Stripe Coinbase and Ramp Built Internal Coding Agents Langchain Open swe Gives you the Same Architecture for Free
- Openrouter is Raising 120m at a 1 3b Valuation and its Processing More Tokens Than Most ai Companies Make

Leave a comment