> ## 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.

# API reference

> Python methods and functions for TabPFN, its API client, and extensions, alongside the REST API contract.

Use the reference for signatures, parameters, and return values. Each page links to the source, with related capability guides where available.

<CardGroup cols={2}>
  <Card title="tabpfn" icon="python" href="/api-reference/python/tabpfn/overview">
    Useful if you want to run base TabPFN models locally, on your GPUs.
  </Card>

  <Card title="tabpfn-client" icon="cloud" href="/api-reference/python/tabpfn-client/overview">
    Useful if you want to run Plus or Thinking models. Our API, or Azure, AWS or on-prem containers are supported.
  </Card>

  <Card title="tabpfn-extensions" icon="puzzle-piece" href="/api-reference/python/tabpfn-extensions/overview">
    Add capabilities such as interpretability. Browse each extension by topic, with related functions and result types together.
  </Card>

  <Card title="REST API" icon="code" href="/api-reference/training/prepare-train-set-upload">
    Useful if you want to run Plus or Thinking models and do not use Python as your main programming language. Covers our REST API.
  </Card>
</CardGroup>


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