Pinned Tweet
Launch Day! Launch Day! Launch Day!
AI teams overpay for inference twice: once for models bigger than they need, and again for idle capacity they don’t use. @useRouterPlus is the extended inference team for fast-growing AI companies. We test models and providers on your traffic and get providers to compete for your work.
Make your inference better. Go to routerplus.com
Replying to @alpha_dot_sh
@alpha_dot_sh is now live on routerplus.
Image and video models are now live on RouterPlus!
Veo 3.1, Kling, Seedance, Nano Banana, GPT Image, Flux, Grok Imagine, Hailuo and more, all behind one API key.
Replying to @p0
@p0 is now live on RouterPlus, and Parallel Search and Decisions are free.
Decisions gives your agents structured answers about the live web with citations, 13× faster at 1/16 the cost of GPT Luna with native web search.
Search gives any model live web results with excerpts.
Turn both on with one header, x-tm-tools: parallel:search, parallel:decisions, on any chat model with your RouterPlus key.
Free for a limited period of time!
check it out at routerplus.com/providers/par…
1
52
check it out at routerplus.com/providers/par…
1
29
Replying to @BoundlessHQ
@BoundlessHQ now live on routerplus
Replying to @PhalaNetwork
@PhalaNetwork is now live on routerplus
RouterPlus (YC F26) retweeted
been putting together a slack group of engineers and folks handling inference at their companies. calling it The Inference Club.
getting the first few folks together. if this is your world, would love to have you.
comment or dm to get in
K3.1 Pro by @Kimi_Moonshot is live on routerplus!
try it out yourself! routerplus.com/models/moonsh…
2
305
Check us out for inference tailored to your workload, at the best price ever!
The cheapest inference quote can miss your busiest hour.
@alokbishoyi97 and @XLN1999 built @useRouterPlus to test customer workloads, source inference capacity and maintain a backup provider.
Providers compete to serve the traffic an application actually needs.
fondo.ai/48ynbtW
4
510
Replying to @paperinstr
@paperinstr is now live on RouterPlus.
Ultramarine 1 Flash, their open model for knowledge work, is available today.
Try it out here! routerplus.com/models/paper-…
1
58
RouterPlus (YC F26) retweeted
AI teams overpay for inference twice: once for models bigger than they need, and again for idle capacity they don’t use. @useRouterPlus is the extended inference team for fast-growing AI companies. We test models and providers on your traffic and get providers to compete for your work.
Make your inference better. Go to routerplus.com
Replying to @Doubleword_
@Doubleword_ is live on routerplus
RouterPlus (YC F26) retweeted
call for startups : corgi for ai inference.
anyone know of a fast way to underwrite insurance for inference contracts ? we are seeing many mid six to seven figure contracts where we need this desperately.
ideally it should be from someone who truly understants the inference markets, variance in providers and can run their own evals if need be. also better if the cost of insurance can be baked in the token price itself somehow












