Coming soon
The Matilda API, on our GPUs
Call Matilda from your own code, served onshore from Melbourne. Reference docs and a self-serve dashboard are in build. Tell us what you need from it and we will point the beta at you first.
Endpoints, auth, and streaming
An OpenAI-compatible surface with the request and response shapes your client already speaks. Reference for every parameter, plus the streaming and tool-calling paths.
Keys, usage, and billing
Create and rotate API keys, watch token spend by model and by day, and manage workspace billing without filing a ticket.
Typed clients, or plain curl
Official TypeScript and Python clients with types generated from the spec, for when you would rather not hand-roll a fetch. The HTTP surface stays plain enough to curl.