Skip to main content
POST
/
tabpfn
/
predict
Predict (TabPFN JSON API)
curl --request POST \
  --url https://api.priorlabs.ai/tabpfn/predict \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "test_set_upload_id": "223e4567-e89b-12d3-a456-426614174000",
  "fitted_train_set_id": "323e4567-e89b-12d3-a456-426614174000",
  "task_config": {
    "task": "classification",
    "tabpfn_config": {
      "model_path": "auto"
    }
  }
}
'
{
  "prediction": [
    "<unknown>"
  ],
  "metadata": {
    "test_set_num_rows": 123,
    "test_set_num_cols": 123,
    "package_version": "<string>",
    "tabpfn_config": {
      "n_estimators": 4,
      "categorical_features_indices": [
        123
      ],
      "softmax_temperature": 123,
      "average_before_softmax": true,
      "random_state": 123,
      "inference_config": {},
      "ignore_pretraining_limits": true,
      "n_preprocessing_jobs": 4,
      "inference_precision": "auto",
      "fit_mode": "fit_preprocessors",
      "device": [
        "<string>"
      ],
      "memory_saving_mode": true,
      "model_path": "<string>",
      "balance_probabilities": true
    },
    "task": "classification"
  }
}

Authorizations

​
Authorization
string
header
required

Bearer token for authentication, obtained after signing up and generating an API key.

Body

application/json
​
test_set_upload_id
string<uuid>
required
​
fitted_train_set_id
string<uuid>
required
​
task_config
ClassifierConfig · object
required
​
force_refit
boolean
default:false

Whether to force the fitting of the test set even if a fittedtest set and transform states already exist.

Response

Prediction payload + metadata.

​
prediction
required
​
metadata
ClassifierMetadata · object
required