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

# Hugging Face

> Use Hugging Face Inference endpoints through Prisma AIRS AI Gateway for thousands of open-source models.

## Quick Start

Get started with Hugging Face in under 2 minutes:

```sh cURL icon="square-terminal" theme={"system"}
# 1. Add @huggingface provider in model catalog
# 2. Use it:

curl https://aigw.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PORTKEY_API_KEY" \
  -d '{
    "model": "@huggingface/meta-llama/Llama-3.2-3B-Instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

```python OpenAI Py icon="python" theme={"system"}
from openai import OpenAI

# 1. Install: pip install openai
# 2. Add @huggingface provider in model catalog
# 3. Use it:

client = OpenAI(
    api_key="PORTKEY_API_KEY",  # AI Gateway API key
    base_url="https://aigw.portkey.ai/v1"
)

response = client.chat.completions.create(
    model="@huggingface/meta-llama/Llama-3.2-3B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)
```

```js OpenAI JS icon="square-js" theme={"system"}
import OpenAI from "openai"

// 1. Install: npm install openai
// 2. Add @huggingface provider in model catalog
// 3. Use it:

const client = new OpenAI({
    apiKey: "PORTKEY_API_KEY",  // AI Gateway API key
    baseURL: "https://aigw.portkey.ai/v1"
})

const response = await client.chat.completions.create({
    model: "@huggingface/meta-llama/Llama-3.2-3B-Instruct",
    messages: [{ role: "user", content: "Hello!" }]
})

console.log(response.choices[0].message.content)
```

## Add Provider in Model Catalog

Before making requests, add Hugging Face to your Model Catalog:

1. Go to [**Model Catalog → Add Provider**](https://stratacloudmanager.paloaltonetworks.com/)
2. Select **Hugging Face**
3. Enter your [Hugging Face access token](https://huggingface.co/settings/tokens)
4. (Optional) Add a **Custom Host** if using a dedicated Hugging Face Inference Endpoint (e.g., `https://your-custom-url/v1`)
5. Name your provider (e.g., `huggingface`)

> [!NOTE]
>
> If you have a dedicated server hosted on Hugging Face, enter your dedicated endpoint URL in the **Custom Host** field during provider setup. This allows you to route requests to your private Hugging Face deployment.

> **[Complete Setup Guide](https://docs.portkey.ai/docs/aigw/product/model-catalog.md)**
>
> See all setup options and detailed configuration instructions

***

## Supported Models

Hugging Face provides access to thousands of text generation models through their Inference endpoints, including:

* Meta Llama 3.2, Llama 3.1, Llama 3
* Mistral, Mixtral
* Qwen 2.5
* Phi-3
* Gemma, Gemma 2
* And thousands more!

Browse the complete catalog at [Hugging Face Models](https://huggingface.co/models?pipeline_tag=text-generation).

***

## Next Steps

> **[Gateway Configs](https://docs.portkey.ai/docs/aigw/product/ai-gateway.md)**
>
> Add fallbacks, load balancing, and more

> **[Observability](https://docs.portkey.ai/docs/aigw/product/observability.md)**
>
> Monitor and trace your Hugging Face requests

> **[Metadata](https://docs.portkey.ai/docs/aigw/product/observability/metadata.md)**
>
> Add custom metadata to requests


## Related topics

- [Google Vertex AI](https://docs.portkey.ai/docs/aigw/integrations/llms/vertex-ai.md)
- [Enforcing Saved-Only Resources](https://docs.portkey.ai/docs/aigw/product/administration/enforce-saved-only-config.md)
- [Enterprise Gateway](https://docs.portkey.ai/docs/changelog/enterprise.md)


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