---
title: "CustomVlmApiSettings"
canonical_url: "https://www.nutrient.io/api/python/settings/advanced/vision/custom-vlm-api-settings/"
md_url: "https://www.nutrient.io/api/python/settings/advanced/vision/custom-vlm-api-settings.md"
last_updated: "2026-06-12T15:43:20.744Z"
description: "Settings for CustomVlmApi. Values fall back through three levels: document → SDK → built-in default."
---

Settings for CustomVlmApi. Values fall back through three levels: document → SDK → built-in default. Writes target the document only when set on a document's settings, otherwise the SDK globally when set on SdkSettings.

**Tags:** `Advanced`, `Vision`

```python

from nutrient_sdk import CustomVlmApiSettings

```

## Construction

`CustomVlmApiSettings` is accessed through a [`Document`](/api/python/document/) instance for per-document overrides, or via [`SdkSettings`](/api/python/settings/document/sdk-settings/) for SDK-wide defaults.

```python

# Per-document override

with Document.open("input.pdf") as doc:
    settings = doc.settings.custom_vlm_api_settings
    settings.some_field = new_value          # mutate fields directly

# SDK-wide default (applies to all documents)

SdkSettings.custom_vlm_api_settings.some_field = new_value

```

Settings are configured by writing to fields on the returned object. The settings property itself cannot be reassigned — `doc.settings.custom_vlm_api_settings = other_settings` is rejected.

## Properties

### api_endpoint

```python

@property
def api_endpoint(self) -> str

@api_endpoint.setter
def api_endpoint(self, value: str) -> None

```

API endpoint URL for OpenAI-compatible chat completions.

**Type:** `str`

**Default:** `"http://localhost:1234/v1"`

---

### api_key

```python

@property
def api_key(self) -> str

@api_key.setter
def api_key(self, value: str) -> None

```

API key for authentication with the VLM service.

**Type:** `str`

**Default:** `string.Empty`

---

### batch_size

```python

@property
def batch_size(self) -> int

@batch_size.setter
def batch_size(self, value: int) -> None

```

Number of zone images to include per VLM API call.

**Type:** `int`

**Default:** `8`

---

### classification_strategy

```python

@property
def classification_strategy(self) -> VlmClassificationStrategy

@classification_strategy.setter
def classification_strategy(self, value: VlmClassificationStrategy) -> None

```

Strategy for how zones are sent to the VLM for classification.

**Type:** [`VlmClassificationStrategy`](/api/python/enums/vlm-classification-strategy/)

**Default:** `VlmClassificationStrategy.MultiZone`

---

### max_concurrency

```python

@property
def max_concurrency(self) -> int

@max_concurrency.setter
def max_concurrency(self, value: int) -> None

```

Maximum number of concurrent VLM API calls.

**Type:** `int`

**Default:** `1`

---

### max_tokens

```python

@property
def max_tokens(self) -> int

@max_tokens.setter
def max_tokens(self, value: int) -> None

```

Maximum tokens in response (-1 = unlimited)

**Type:** `int`

**Default:** `-1`

---

### model

```python

@property
def model(self) -> str

@model.setter
def model(self, value: str) -> None

```

Model identifier to use.

**Type:** `str`

**Default:** `"qwen/qwen3-vl-8b"`

---

### send_full_page_reference

```python

@property
def send_full_page_reference(self) -> bool

@send_full_page_reference.setter
def send_full_page_reference(self, value: bool) -> None

```

Whether to send the full page image as reference context alongside cropped zones. Only used when UseZoneCropping is true.

**Type:** `bool`

**Default:** `false`

---

### stream

```python

@property
def stream(self) -> bool

@stream.setter
def stream(self, value: bool) -> None

```

Whether to stream responses from the API

**Type:** `bool`

**Default:** `false`

---

### system_prompt

```python

@property
def system_prompt(self) -> str

@system_prompt.setter
def system_prompt(self, value: str) -> None

```

Optional custom system prompt for zone classification. When empty, the module uses a default prompt based on the ClassificationStrategy.

**Type:** `str`

**Default:** `string.Empty`

---

### temperature

```python

@property
def temperature(self) -> float

@temperature.setter
def temperature(self, value: float) -> None

```

Temperature for response generation (0.0 = deterministic, 1.0 = creative). Defaults to 0.0 because zone classification and verbatim text extraction are deterministic tasks — randomness only adds run-to-run noise.

**Type:** `float`

**Default:** `0.0`

---

---

## Related pages

- [Per-document override](/api/python/settings/advanced/vision/ai-processing-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/form-labeling-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/finalizer-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/form-recognition-settings.md)
- [Vision](/api/python/settings/advanced/vision.md)
- [Per-document override](/api/python/settings/advanced/vision/ocr-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/inference-layout-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/open-ai-languages-detection-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/open-ai-picture-alt-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/reading-order-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/segmenter-settings.md)
- [Per-document override](/api/python/settings/advanced/vision/words-detection-settings.md)