> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.agentchat.contrib.img_utils.num_tokens_from_gpt_image

<code class="doc-symbol doc-symbol-heading doc-symbol-function" />

#### num\_tokens\_from\_gpt\_image

```python theme={null}
num_tokens_from_gpt_image(
    image_data: str | ForwardRef('Image'),
    model: str = 'gpt-4-vision',
    low_quality: bool = False
) -> int
```

Calculate the number of tokens required to process an image based on its dimensions
after scaling for different GPT models. Supports "gpt-4-vision", "gpt-4o", and "gpt-4o-mini".<br />This function scales the image so that its longest edge is at most 2048 pixels and its shortest
edge is at most 768 pixels (for "gpt-4-vision"). It then calculates the number of 512x512 tiles
needed to cover the scaled image and computes the total tokens based on the number of these tiles.<br />Reference: [https://openai.com/api/pricing/](https://openai.com/api/pricing/)

<b>Parameters:</b>

| Name          | Description                                                                                                                                                                            |
| ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `image_data`  | Union\[str, Image.Image]: The image data which can either be a base64 encoded string, a URL, a file path, or a PIL Image object.<br /><br />**Type:** str \| ForwardRef('Image.Image') |
| `model`       | str: The model being used for image processing.<br /><br />Can be "gpt-4-vision", "gpt-4o", or "gpt-4o-mini".<br /><br />**Type:** str<br /><br />**Default:** 'gpt-4-vision'          |
| `low_quality` | bool: Whether to use low-quality processing.<br /><br />Defaults to False.<br /><br />**Type:** bool<br /><br />**Default:** False                                                     |

<b>Returns:</b>

| Type | Description                                                        |
| ---- | ------------------------------------------------------------------ |
| int  | int: The total number of tokens required for processing the image. |

<br />