Production base URLs
Environments
Every evaluation targets anenv_id:
The control plane is shared; task banks, apps, and verifiers are environment-specific.
Which API should I use?
Conventions
- JSON request/response unless noted (export returns
application/zip) - Evaluation start returns 202 with
run_id; poll status untilCOMPLETED/FAILED/CANCELLED - Terminal rewards:
+1/0/-1(see Verifiers