Ramp Router
ramp.comI love that 3 years in we're still (Even more so) at the "you have to pick the right model for the job" stage, requiring these sorts of hacks.
If the AI companies were clever they'd offer this themselves.
I find the "We put a model in front of your models so you can pick the right model while you model" mindset to be very strange.
It feels wasteful, but I do it too. Could definitely be an ignorance problem where I don't really know what the alternative is.
Is model routing going to become the next "look at this memory system I made" but for enterprise?
Looks like it will be a paid offering? Seems strange coming from a Fintech, unless they're looking to pivot.
It is not strange at all given their business is spend management and likely a significant portion of their customers spend on inference and would like that spend to be... managed.
Except as the corporate spending card company they see just how much their customers are spending on inference and have made it a cornerstone of their marketing for the last two years.
Their positioning is: You already have all your teams spending routing through us so that through greater transparency to finance you get better spending controls. We now apply the same to inference, which is spread out across all parts of your company in a similar way.
All summed up really well with their tagline “Tokens are money. Save both.”
Don’t think I’ll be using model routing / shared gateway from Ramp any time soon, but the value of this kind of capability is definitely there. And there’s no shortage of vendors aiming to offer this kind of gateway/router functionality. But most of those come from the technology side of the organization. This gets to come from the office of the CFO.
Pretty sure it won't be. What makes you think it will be paid?
> free to use at launch
How does this help me control spend if I don't understand how much it will cost me a year after I bake it into my infrastructure?
Honestly it kinda makes sense, Ramp's whole shtick is controlling spend, and this would prolly help people control their AI spend.