> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# tabpfn

> Install TabPFN and browse the local Python package reference.

<Info>
  Looking for usage documentation? Check out [Quickstart](/quickstart), [Classification](/capabilities/classification), and [Regression](/capabilities/regression).
</Info>

## Installation

```bash theme={null}
pip install tabpfn
```

## Reference topics

<CardGroup cols={2}>
  <Card title="TabPFNClassifier" href="/api-reference/python/tabpfn/classifier/configuration">
    Constructor options, fitting, prediction, embeddings, and persistence.
  </Card>

  <Card title="TabPFNRegressor" href="/api-reference/python/tabpfn/regressor/configuration">
    Constructor options, fitting, prediction, and predictive distributions.
  </Card>

  <Card title="Inference configuration" href="/api-reference/python/tabpfn/inference-config">
    Settings accepted by the estimators through inference\_config.
  </Card>

  <Card title="Inference tuning" href="/api-reference/python/tabpfn/inference-tuning">
    Tuning configuration and performance metrics.
  </Card>

  <Card title="Fine-tuning" href="/api-reference/python/tabpfn/finetuning/base">
    Fine-tuning estimators, batch types, and experiment logging.
  </Card>

  <Card title="Preprocessing" href="/api-reference/python/tabpfn/preprocessing/configuration">
    Preprocessing configuration, pipelines, and presets.
  </Card>

  <Card title="Model versions" href="/api-reference/python/tabpfn/model-versions">
    Model version identifiers.
  </Card>

  <Card title="Model persistence" href="/api-reference/python/tabpfn/model-persistence">
    Save and load fitted models and model specifications.
  </Card>

  <Card title="Diagnostics" href="/api-reference/python/tabpfn/diagnostics">
    Environment diagnostics and error types.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.