Ramp launches Router to cut AI inference costs by 40%
Ramp Launches a Model Router
Ramp introduces Router, a model routing service that sends each request to the lowest-cost model meeting performance needs, cutting inference costs by 40% on average. With one endpoint and one bill, it supports models from OpenAI, Anthropic, and others, and is free through 2026. Ramp's internal use cut AI costs by over 25%, and integration with NVIDIA NeMo Switchyard reduced costs by 59%.
At Ramp, Router cut our overall LLM cost by 30% while making our features smarter and faster.
- aizk
I just want to know how much the domain cost.
- embedding-shape
The fact that they put "every model" repeatedly, then don't actually support even close to "most mainstream models", makes me highly doubtful their service will be more honest and forthcoming once I'm signed up.
- gonzalohm
I guess this is the world we live in now. All companies no matter which sector they belong to must buy AI crap.
A few years ago, companies buying random companies from a completely different sector was frowned upon by stakeholders
- copperx
Routing requests to the ideal model? that's some big talk right there.
- zelias
It can't be a coincidence that this dropped today, the same day news dropped about the Stripe acquisition of OpenRouter