> ## 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.

# Azure Foundry

> Use the Azure Foundry deployment adapters.

<Info>
  Looking for usage documentation? Check out [Classification](/capabilities/classification), [Regression](/capabilities/regression) and [KV cache](/capabilities/kv-cache).
</Info>

<div className="python-reference-heading">
  <h2 id="classifier">
    `foundry.TabPFNClassifier`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L427" aria-label="View source for foundry.TabPFNClassifier"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

TabPFN classifier backed by an Azure AI Foundry endpoint.

```python theme={null}
foundry.TabPFNClassifier(
    *args: Any,
    task: str = "classification",
    **kwargs: Any,
)
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="classifier-args" /><code className="python-reference-parameter">\*args</code> | <code className="python-reference-type">Any</code> | — | — |
  | <span id="classifier-task" /><code className="python-reference-parameter">task</code> | <code className="python-reference-type">str</code> | `"classification"` | — |
  | <span id="classifier-kwargs" /><code className="python-reference-parameter">\*\*kwargs</code> | <code className="python-reference-type">Any</code> | — | See the [accepted constructor options](#classifier-endpoint-url) in this table. |
  | <span id="classifier-endpoint-url" /><code className="python-reference-parameter">endpoint\_<wbr />url</code> | <code className="python-reference-type">str</code> | Required | Accepted through `**kwargs`. |
  | <span id="classifier-api-key" /><code className="python-reference-parameter">api\_<wbr />key</code> | <code className="python-reference-type">str</code> | Required | Accepted through `**kwargs`. |
  | <span id="classifier-n-estimators" /><code className="python-reference-parameter">n\_<wbr />estimators</code> | <code className="python-reference-type">int</code> | `8` | Accepted through `**kwargs`. |
  | <span id="classifier-softmax-temperature" /><code className="python-reference-parameter">softmax\_<wbr />temperature</code> | <code className="python-reference-type">float</code> | `0.9` | Accepted through `**kwargs`. |
  | <span id="classifier-balance-probabilities" /><code className="python-reference-parameter">balance\_<wbr />probabilities</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="classifier-average-before-softmax" /><code className="python-reference-parameter">average\_<wbr />before\_<wbr />softmax</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="classifier-ignore-pretraining-limits" /><code className="python-reference-parameter">ignore\_<wbr />pretraining\_<wbr />limits</code> | <code className="python-reference-type">bool</code> | `True` | Accepted through `**kwargs`. |
  | <span id="classifier-inference-precision" /><code className="python-reference-parameter">inference\_<wbr />precision</code> | <code className="python-reference-type">Literal\["autocast", "auto"]</code> | `"auto"` | Accepted through `**kwargs`. |
  | <span id="classifier-random-state" /><code className="python-reference-parameter">random\_<wbr />state</code> | <code className="python-reference-type">Optional\[int]</code> | `0` | Accepted through `**kwargs`. |
  | <span id="classifier-inference-config" /><code className="python-reference-parameter">inference\_<wbr />config</code> | <code className="python-reference-type">Optional\[Dict\[str, Any]]</code><br /><a href="/api-reference/python/tabpfn/inference-config#inferenceconfig"><code>InferenceConfig</code> options</a> | `None` | Accepted through `**kwargs`. |
  | <span id="classifier-paper-version" /><code className="python-reference-parameter">paper\_<wbr />version</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="classifier-thinking-mode" /><code className="python-reference-parameter">thinking\_<wbr />mode</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="classifier-thinking-effort" /><code className="python-reference-parameter">thinking\_<wbr />effort</code> | <code className="python-reference-type">Optional\[<a href="/api-reference/python/tabpfn-client/configuration#thinkingeffort">Thinking<wbr />Effort</a>]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="classifier-thinking-timeout-s" /><code className="python-reference-parameter">thinking\_<wbr />timeout\_<wbr />s</code> | <code className="python-reference-type">Optional\[float]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="classifier-thinking-metric" /><code className="python-reference-parameter">thinking\_<wbr />metric</code> | <code className="python-reference-type">Optional\[str]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="classifier-use-kv-cache" /><code className="python-reference-parameter">use\_<wbr />kv\_<wbr />cache</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="classifier-fit-mode" /><code className="python-reference-parameter">fit\_<wbr />mode</code> | <code className="python-reference-type">Optional\[<a href="/api-reference/python/tabpfn-client/configuration#fitmodeliteral">Fit<wbr />Mode<wbr />Literal</a>]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="classifier-timeout-s" /><code className="python-reference-parameter">timeout\_<wbr />s</code> | <code className="python-reference-type">float</code> | `300.0` | Accepted through `**kwargs`. |
</div>

**Example**

```python theme={null}
from tabpfn_client.foundry import TabPFNClassifier
clf = TabPFNClassifier(
    endpoint_url="https://<your-endpoint>.<region>.inference.ml.azure.com/predict",
    api_key="<your-foundry-bearer-token>",
)
clf.fit(X_train, y_train)
clf.predict(X_test)
clf.predict_proba(X_test)
```

***

<div className="python-reference-heading">
  <h2 id="classifier-fit">
    `foundry.TabPFNClassifier.fit`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L360" aria-label="View source for foundry.TabPFNClassifier.fit"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Store the training data; the endpoint fits on the next `predict*` call.

```python theme={null}
foundry.TabPFNClassifier.fit(
    X: Any,
    y: Any,
) -> "_FoundryBase"
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="classifier-fit-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">Any</code> | Required | Training features. |
  | <span id="classifier-fit-y" /><code className="python-reference-parameter">y</code> | <code className="python-reference-type">Any</code> | Required | Training targets. |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type">\_Foundry<wbr />Base</code> | The estimator itself. |
</div>

**Raises**

`ValueError`

If `X` and `y` have different numbers of samples.

***

<div className="python-reference-heading">
  <h2 id="classifier-predict">
    `foundry.TabPFNClassifier.predict`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L444" aria-label="View source for foundry.TabPFNClassifier.predict"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Predict class labels for `X`.

```python theme={null}
foundry.TabPFNClassifier.predict(
    X: Any,
) -> np.ndarray
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="classifier-predict-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">Any</code> | Required | — |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type"><a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a></code> | — |
</div>

***

<div className="python-reference-heading">
  <h2 id="classifier-predict-proba">
    `foundry.TabPFNClassifier.predict_proba`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L449" aria-label="View source for foundry.TabPFNClassifier.predict_proba"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Predict class probabilities for `X`.

```python theme={null}
foundry.TabPFNClassifier.predict_proba(
    X: Any,
) -> np.ndarray
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="classifier-predict-proba-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">Any</code> | Required | — |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type"><a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a></code> | — |
</div>

***

<div className="python-reference-heading">
  <h2 id="regressor">
    `foundry.TabPFNRegressor`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L455" aria-label="View source for foundry.TabPFNRegressor"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

TabPFN regressor backed by an Azure AI Foundry endpoint.

```python theme={null}
foundry.TabPFNRegressor(
    *args: Any,
    task: str = "regression",
    **kwargs: Any,
)
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="regressor-args" /><code className="python-reference-parameter">\*args</code> | <code className="python-reference-type">Any</code> | — | — |
  | <span id="regressor-task" /><code className="python-reference-parameter">task</code> | <code className="python-reference-type">str</code> | `"regression"` | — |
  | <span id="regressor-kwargs" /><code className="python-reference-parameter">\*\*kwargs</code> | <code className="python-reference-type">Any</code> | — | See the [accepted constructor options](#regressor-endpoint-url) in this table. |
  | <span id="regressor-endpoint-url" /><code className="python-reference-parameter">endpoint\_<wbr />url</code> | <code className="python-reference-type">str</code> | Required | Accepted through `**kwargs`. |
  | <span id="regressor-api-key" /><code className="python-reference-parameter">api\_<wbr />key</code> | <code className="python-reference-type">str</code> | Required | Accepted through `**kwargs`. |
  | <span id="regressor-n-estimators" /><code className="python-reference-parameter">n\_<wbr />estimators</code> | <code className="python-reference-type">int</code> | `8` | Accepted through `**kwargs`. |
  | <span id="regressor-softmax-temperature" /><code className="python-reference-parameter">softmax\_<wbr />temperature</code> | <code className="python-reference-type">float</code> | `0.9` | Accepted through `**kwargs`. |
  | <span id="regressor-balance-probabilities" /><code className="python-reference-parameter">balance\_<wbr />probabilities</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="regressor-average-before-softmax" /><code className="python-reference-parameter">average\_<wbr />before\_<wbr />softmax</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="regressor-ignore-pretraining-limits" /><code className="python-reference-parameter">ignore\_<wbr />pretraining\_<wbr />limits</code> | <code className="python-reference-type">bool</code> | `True` | Accepted through `**kwargs`. |
  | <span id="regressor-inference-precision" /><code className="python-reference-parameter">inference\_<wbr />precision</code> | <code className="python-reference-type">Literal\["autocast", "auto"]</code> | `"auto"` | Accepted through `**kwargs`. |
  | <span id="regressor-random-state" /><code className="python-reference-parameter">random\_<wbr />state</code> | <code className="python-reference-type">Optional\[int]</code> | `0` | Accepted through `**kwargs`. |
  | <span id="regressor-inference-config" /><code className="python-reference-parameter">inference\_<wbr />config</code> | <code className="python-reference-type">Optional\[Dict\[str, Any]]</code><br /><a href="/api-reference/python/tabpfn/inference-config#inferenceconfig"><code>InferenceConfig</code> options</a> | `None` | Accepted through `**kwargs`. |
  | <span id="regressor-paper-version" /><code className="python-reference-parameter">paper\_<wbr />version</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="regressor-thinking-mode" /><code className="python-reference-parameter">thinking\_<wbr />mode</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="regressor-thinking-effort" /><code className="python-reference-parameter">thinking\_<wbr />effort</code> | <code className="python-reference-type">Optional\[<a href="/api-reference/python/tabpfn-client/configuration#thinkingeffort">Thinking<wbr />Effort</a>]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="regressor-thinking-timeout-s" /><code className="python-reference-parameter">thinking\_<wbr />timeout\_<wbr />s</code> | <code className="python-reference-type">Optional\[float]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="regressor-thinking-metric" /><code className="python-reference-parameter">thinking\_<wbr />metric</code> | <code className="python-reference-type">Optional\[str]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="regressor-use-kv-cache" /><code className="python-reference-parameter">use\_<wbr />kv\_<wbr />cache</code> | <code className="python-reference-type">bool</code> | `False` | Accepted through `**kwargs`. |
  | <span id="regressor-fit-mode" /><code className="python-reference-parameter">fit\_<wbr />mode</code> | <code className="python-reference-type">Optional\[<a href="/api-reference/python/tabpfn-client/configuration#fitmodeliteral">Fit<wbr />Mode<wbr />Literal</a>]</code> | `None` | Accepted through `**kwargs`. |
  | <span id="regressor-timeout-s" /><code className="python-reference-parameter">timeout\_<wbr />s</code> | <code className="python-reference-type">float</code> | `300.0` | Accepted through `**kwargs`. |
</div>

**Example**

```python theme={null}
from tabpfn_client.foundry import TabPFNRegressor
reg = TabPFNRegressor(
    endpoint_url="https://<your-endpoint>.<region>.inference.ml.azure.com/predict",
    api_key="<your-foundry-bearer-token>",
)
reg.fit(X_train, y_train)
reg.predict(X_test)
reg.predict(X_test, output_type="quantiles", quantiles=[0.1, 0.5, 0.9])
```

***

<div className="python-reference-heading">
  <h2 id="regressor-fit">
    `foundry.TabPFNRegressor.fit`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L360" aria-label="View source for foundry.TabPFNRegressor.fit"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Store the training data; the endpoint fits on the next `predict*` call.

```python theme={null}
foundry.TabPFNRegressor.fit(
    X: Any,
    y: Any,
) -> "_FoundryBase"
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="regressor-fit-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">Any</code> | Required | Training features. |
  | <span id="regressor-fit-y" /><code className="python-reference-parameter">y</code> | <code className="python-reference-type">Any</code> | Required | Training targets. |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type">\_Foundry<wbr />Base</code> | The estimator itself. |
</div>

**Raises**

`ValueError`

If `X` and `y` have different numbers of samples.

***

<div className="python-reference-heading">
  <h2 id="regressor-predict">
    `foundry.TabPFNRegressor.predict`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-client/blob/5f8aee56ad2a788458704c342347e9bc282cebe9/src/tabpfn_client/foundry/estimator.py#L472" aria-label="View source for foundry.TabPFNRegressor.predict"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Predict regression targets for `X`.

```python theme={null}
foundry.TabPFNRegressor.predict(
    X: Any,
    output_type: Literal["mean", "median", "mode", "quantiles", "full", "main"] = "mean",
    quantiles: Optional[list] = None,
) -> Union[np.ndarray, list, Dict[str, np.ndarray]]
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="regressor-predict-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">Any</code> | Required | Test features. |
  | <span id="regressor-predict-output-type" /><code className="python-reference-parameter">output\_<wbr />type</code> | <code className="python-reference-type">Literal\["mean", "median", "mode", "quantiles", "full", "main"]</code> | `"mean"` | Which prediction to return. |
  | <span id="regressor-predict-quantiles" /><code className="python-reference-parameter">quantiles</code> | <code className="python-reference-type">Optional\[list]</code> | `None` | Quantile levels to compute when `output_type` is "quantiles". |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type">Union\[<a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a>, list, Dict\[str, <a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a>]]</code> | An array for point predictions; a list with one array per quantile for "quantiles"; a dict of arrays for dict-shaped outputs such as "full" and "main". |
</div>

## Scoring

The classifier and regressor inherit the corresponding scikit-learn `score` method. These adapters do not inherit the main hosted client's `save_model`, `load_model`, or model-version selection methods.


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