v1

latestOpenAPI 3.1.02026-07-2673250.3 KB

Training

Fit (TabPFN JSON API)

Recommended: Use tabpfn-client (TabPFNClassifier / TabPFNRegressor). It calls these routes for you.

JSON body after you upload train files via POST /tabpfn/prepare_train_set_upload and PUT the returned signed URLs. Returns fitted_train_set_id. Long fits may stream JSON with leading keepalive whitespace; see the TabPFN-3 changelog.

Key fields: train_set_upload_id (UUID), task (classification | regression), tabpfn_systems, optional tabpfn_config, thinking_effort (medium | high or omit), thinking_timeout_s, thinking_effort_metric, force_refit.

post/tabpfn/fit

Request body

train_set_upload_idstring uuid required

task'classification' | 'regression' required

Specifies the type of task to perform — either classification or regression.

tabpfn_systemsstring[]

tabpfn_configobject nullable

thinking_effort'medium' | 'high' nullable

thinking_timeout_snumber nullable

thinking_effort_metricstring nullable

force_refitboolean

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

Response

Fitted train set id (JSON; may be streamed with leading whitespace on long fits).

fitted_train_set_idstring uuid required