> ## 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.

# Model versions

> Version of the model.

<div className="python-reference-heading">
  <h2 id="modelversion">
    `ModelVersion`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/constants.py#L31" aria-label="View source for ModelVersion"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Version of the model.

**Fields**

<div className="python-reference-table">
  | Name | Type | Default | Description |
  | - | - | - | - |
  | <span id="modelversion--v2" /><code className="python-reference-parameter">V2</code> | — | `"v2"` | — |
  | <span id="modelversion--v2-5" /><code className="python-reference-parameter">V2\_<wbr />5</code> | — | `"v2.5"` | — |
  | <span id="modelversion--v2-6" /><code className="python-reference-parameter">V2\_<wbr />6</code> | — | `"v2.6"` | — |
  | <span id="modelversion--v3" /><code className="python-reference-parameter">V3</code> | — | `"v3"` | — |
  | <span id="modelversion--v3-5" /><code className="python-reference-parameter">V3\_<wbr />5</code> | — | `"v3.5"` | — |
  | <span id="modelversion--v3-5-fast" /><code className="python-reference-parameter">V3\_<wbr />5\_<wbr />FAST</code> | — | `"v3.5-fast"` | — |
</div>


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