NUnugen
Models

Get Model

Get one aligned model by ID.

Returns:

  • model_id, model_name, base_model_id, base_model_name, alignment_id
  • deployment_status (UNDEPLOYED, DEPLOYING, DEPLOYED, UNDEPLOYING), derived from the live deployment
  • error: why the last deploy or undeploy failed, null when it succeeded
  • progress, eta_seconds: not wired up yet, always null
  • performance_metrics, evaluation_data: from the model's latest evaluation, if any
  • usage_count, downloadable: not wired up yet, always 0 and false
  • inference_capture_enabled
  • created_at, updated_at
get/api/v3/models/{model_id}

Request

  • Base URL
    https://api.nugen.in
  • Auth
    HTTP bearer

Path parameters

model_idstring required

ID of the model, as listed by GET /models/aligned or GET /models/base

Response

Returns one aligned model: its model_id, model_name, base model, derived deployment status and timestamps.

model_idstring required

Unique identifier of the aligned model.

model_namestring required

Display name of the aligned model.

base_model_idstring required

Base model this model was aligned from.

base_model_namestring required

Display name of the base model this model was aligned from.

alignment_idstring nullable

Alignment project that produced this model.

deployment_status'UNDEPLOYED' | 'DEPLOYING' | 'DEPLOYED' | 'UNDEPLOYING' required

Where a model rests, and what it passes through in between. Only DEPLOYED serves inference. A failed attempt settles back to the state it came from and puts the reason in error.

errorstring nullable

Why the last deploy or undeploy failed, null when it succeeded.

progressnumber nullable

Completion progress, 0.0 to 100.0. Not wired up yet, always null.

eta_secondsinteger nullable

Estimated time remaining in seconds. Not wired up yet, always null.

evaluation_dataobject nullable

Benchmark evaluation results if the model has been evaluated (includes evaluation_id, status, metrics, and comparison data)

usage_countinteger

Number of times this model has been used for inference

downloadableboolean

Whether the model can be downloaded for local deployment

inference_capture_enabledboolean

Whether instructions and responses for this model are kept, so they can feed train-time alignment. Set with PATCH /api/v3/inference/capture.

created_atstring nullable

Creation timestamp.

updated_atstring nullable

Last update timestamp.

Example response

{
  "performance_metrics": {
    "accuracy": 0.92,
    "average_response_time": 1.2,
    "domain_violations": 2,
    "uncertainty": 0.15
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.