AI Gateway + App Hosting + Databases + Model Inference.
Everything your team needs to build and run AI.

Run your applications close to users in Australia, on infrastructure in Sydney.
Deploy and run production applications on infrastructure in Sydney.
Connect your app to a database you already run, with its own connection string.
Your apps reach 200+ models through our gateway in Singapore, the nearest region.
Reach 200+ frontier and open-source models through a single connection, and switch between them without changing your code.
Frontier and open source, all reached through one integration.
The gateway sits close to home, so responses come back fast for local users.
If a provider drops, requests move to a healthy route for the same model, instantly.
Text, image, speech, transcription and embeddings, all through one connection.
Deploy the apps you build on those models, with the database, email, and backups provisioned for you.
Push from Git or upload your files, with scaling and TLS handled.
A Postgres database created and connected the moment you deploy.
Transactional email set up and reaching the inbox from the very first ship.
Automated backups and recovery run quietly, with nothing to set up.
Deploy apps, check spend and read logs just by asking your AI assistant. Sign in once, no key to copy.
Govern usage, spend, and access across your whole organisation, from one place.
Set the rules for what each model and app can do on every request.
Budget caps per key, team, or company, with alerts before you hit them.
Add people, set roles, and control who reaches which models and apps.
Keep apps internal to your team or open them up, on your terms.
Support, billing and hosting built for Australia, in ways a global provider cannot match.
Talk to the people who run the platform, not a ticket queue.
Every service, every model and every app on one bill.
We run in Sydney: your apps, close to your users.
Your apps run in Sydney. AI calls go through our gateway in Singapore, the nearest region that runs it, and Colombo and Bangalore are there if your users are.
Most are served by the companies that build them and their cloud partners: Claude, GPT and Gemini weights are not released, so nobody outside those companies can run them. A few open-source models also run on hardware we own in Colombo.
Apps run in Sydney and can connect to a database you already have. Managed databases are in Singapore, Colombo and Bangalore, not yet in Sydney.
Yes, on request. We configure your account for in-region processing and storage, so calls stay on models we host ourselves. It is agreed in writing rather than switched on by default — ask us and we will set it up.
Twice a day. Every dump is verified, encrypted and moved off the machine that made it, and we keep the off-site copy for ninety days. Worst case a restore costs you the work since the last one — up to twelve hours.
Only the base URL and the key. The gateway speaks the OpenAI API, so anything already written against an OpenAI SDK works as it is — and that one key reaches every model on the platform.
Pay as you go, on one monthly invoice in your local currency. No seats to buy, no plan to pick, and no minimum to clear before you start.
Our engineers — the same people who run the platform.
Get a key, call any model, ship your app. Pay in your local currency.