You don’t need an SDK to use Pradra Studio — the Studio UI covers the whole lifecycle. Reach for these clients when you integrate predictions into your own application: every deployed capability is reachable over the REST API. Authenticate, then POST inputs to the capability’s stable endpoint. See the API Reference for the full surface.
# Exchange credentials for an access token
curl -X POST https://your-host/api/v1/auth/login \
-H 'Content-Type: application/json' \
-d '{"email":"you@example.com","password":"••••••••"}'
# -> { "access_token": "eyJ…", "refresh_token": "…", "user": { … } }
# inputs are keyed by the capability's input-contract field names
curl -X POST https://your-host/api/v1/predict/CAPABILITY_KEY \
-H 'Authorization: Bearer ACCESS_TOKEN' \
-H 'Content-Type: application/json' \
-d '{"inputs":{"age":30,"income":50000}}'
# -> { "data": { "capability_id": "…", "outputs": { "prediction": "yes" } } }
You can also authenticate with a long-lived API token
(aif_<8hex>.<32hex>) in the same Authorization: Bearer header — create one
under API Tokens in the account menu.