Skip to main content

Production base URLs

Environments

Every evaluation targets an env_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 until COMPLETED / FAILED / CANCELLED
  • Terminal rewards: +1 / 0 / -1 (see Verifiers

Health