Grid-aware compute platform · Australia

Grid-aware compute for AI workloads.

FlexSys schedules training, image/video generation and inference onto whichever GPU capacity has the cheapest, greenest grid power right now — on our infrastructure, yours, or partner clouds.

Try the inference router live below — it's one of the platform's surfaces.

POST /api/gw/v1/chat/completionsmodel meta/llama-3.1-8b-instructstream true
01 · Architecture

How a request flows

From your SDK to a GPU and back. Five replaceable layers — scroll to walk through them.

02 · Grid awareness

Routes follow the grid

The cheapest electron right now wins. We watch the wholesale market and steer inference toward the region paying the least for power.

03 · Pricing

Published rates

Live from our control plane, refreshed every 30 seconds. We pick the cheapest backend; you pay the same regardless of where the request lands.

04 · Bring your own cluster

Run the data plane in your DC

Same operator, your hardware, our control plane. Outbound-only agent — no firewall changes.

Control planeSaaS · oursAgentoutbound only · TLSYour clusterdata planeOperatorkube CRsAudit + pricingmetadata onlyGPUsprompts stay hereBYOC · SHAPE 3
  • Your data plane stays in your DC
    Tokens, prompts and responses never leave your network. We see usage counts and routing metadata, nothing more.
  • Same operator runs at Flipped + at you
    One open-source kube operator. Identical FlexSysJob CRs. What we run in our cluster is what runs in yours.
  • Outbound-only agent — no firewall changes
    The agent dials out to our control plane over TLS. No inbound NAT, no exposed ingress, no shared VPC.
Talk to us about your DC
opens email to sales@flipped.energy
Get started

Stop paying frontier prices for non-frontier work.

Get a demo key in 30 seconds. Or book a 30-minute architecture call to talk about running FlexSys in your own DC.

Get a demo API key Book a 30-min architecture call
today the playground above is your demo · production handover Q3 2026