Deploy Model
General
Deploy Model
Deploy an aligned model for inference use.
This endpoint deploys a domain-aligned model, making it available for inference.
Path Parameters:
model_id: Unique identifier of the aligned model to deploy
Returns:
String containing the model ID for tracking deployment status
Raises:
400: If model is already deployed or deployment provider is invalid404: If model or alignment task not found
Example Request:
POST /api/v3/models/deploy-model/alignment-xyz789
Headers: {"Authorization": "Bearer <api_key>"}
Example Response:
"alignment-xyz789"
Notes:
- Deployment is asynchronous and may take 5-15 minutes to complete
- Use
/models/alignedto check deployment status (DEPLOYING,DEPLOYED) - Once deployed, the model will be available at its inference endpoint
- Model must be in
UNDEPLOYEDstate before deployment
POST
Deploy Model
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Query Parameters
Deploy the newest checkpoint of a run that is still training. The GPU serves the latest checkpoint it has written and refreshes on its own, so answers change as training continues. Evaluation is unaffected and still runs on the finished model.
Response
Successful Response