inference-providers/pr_2713/en/tasks/image-classification.md

## Image Classification

Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image.

> [!TIP]
> For more details about the `image-classification` task, check out its [dedicated page](https://huggingface.co/tasks/image-classification)! You will find examples and related materials.

### Recommended models

- [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224): A strong image classification model.
- [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224): A robust image classification model.
- [facebook/convnext-large-224](https://huggingface.co/facebook/convnext-large-224): A strong image classification model.

Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-classification&sort=trending), or from the terminal with the [`hf` CLI](https://huggingface.co/docs/huggingface_hub/package_reference/cli#hf-models-list):

```bash
hf models ls --warm --pipeline-tag image-classification --sort trending_score
```

### Using the API

<InferenceSnippet
    pipeline=image-classification
    providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"}} }
/>

### API specification

#### Request

| Headers |   |    |
| :--- | :--- | :--- |
| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |

| Payload |  |  |
| :--- | :--- | :--- |
| **inputs*** | _string_ | The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload. |
| **parameters** | _object_ |  |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |

#### Response

| Body |  |
| :--- | :--- | :--- |
| **(array)** | _object[]_ | Output is an array of objects. |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_ | The predicted class label. |
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The corresponding probability. |