Introducing: OpenRouter for everything. One prepaid balance for every API your agents and products need. It’s the billing and metering layer every AI team needed from day one. An OpenRouter for everything. Every model call, search, scrape, or data request - one key, one balance, charged as it happens... at the price you set. The markup is yours. Failed calls cost nothing. Full ledger down to the individual user. 286+ providers. 2,404+ endpoints. And now it fuels our consumer product, Locus Founder. No more juggling provider accounts, month-end invoices, or building your own usage billing system. Teams building agentic products can finally treat their API spend like any other line item: priced, capped, and billed through to their users. Comment “LOCUS” for priority early access. Book a call atshow more

@techbyved This is cool, how did you make the video? Remotion? Looks good. You should try Replit Animation sometime.

@techbyved Actually video was made with Fable 5, took some iteration of course. I'll give it a try! Shot you a dm as well :-)

I’ve been wanting to use this track for a launch for awhile, glad I finally could :-) Also docs here:

this is gonna make agent billing so much simpler

Indeed!

Can’t wait to see adoption go up and up

Indeed, we’ll keep pushing

Agents got a budget. Now give them a mandate.

You'll only ever need one api endpoint again

Model routing❌ API routing✅

This is actually a really clean idea. One balance for the whole AI stack would save so much billing pain.

congrats!! this is so cool🚀

billing consolidation across 2,400+ endpoints is genuinely hard to pull off. failed calls costing nothing is the detail that'll matter most to agent builders running at scale.

i've built enough agent infra to hate provider billing. one key and one ledger sounds boring in exactly the right way

🫡

this product makes a ton of sense for all the vibecoding solutions out there

The interesting part isn’t consolidating API keys, it’s turning fragmented AI infrastructure into a predictable cost layer. Once teams can meter, cap, and pass through every model and data call, AI usage starts looking like a normal infrastructure expense instead of a billing nightmare.

one leaked key can drain every service, are spend caps enforced per agent

Yup

great idea

🫡

Great stuff!

Agents are gig workers

This is sick!!

locus team is cooking

Thank you sir!

LOCUS

LOCUS

@ycombinator This is smart

LOCUS. 🫡

Congrats on the launch!

super cool

There should be a feature to sell unused AI credits. For example, If i have $200 in deepseek credits, since deepseek is on locus I can sell those credits to Locus, then get $200 Locus credits or $180 cash etc.

LOCUS

the agent handles the mess, you just pay one bill

Exactly 🫡

@ycombinator Portfolio: GitHub: SDE @CRED. Built an AI portfolio backend with Orchestrator/Worker logic and a custom MCP tool-calling layer. I know the infra cost of running agents. DMing.

Congrats! @zincdotcom would love to be a provider!

This is awesome, congrats Cole!

Thank you thank you sir

finally, a way to stop chasing 20 different developer API keys.

COOL! LFG Cole & Locus team🔥

Epic

E🅿️ic

wow