# Hugging Face (/integrations/huggingface)



{/* MANUAL-CONTENT-START:intro */}

Use [Hugging Face](https://huggingface.co/) in Sim to generate text completions with the Hugging Face Inference API. Choose a model and supply the prompt for the workflow step.

{/* MANUAL-CONTENT-END */}

## Use the block [#usage-instructions]

Generate completions with the Hugging Face Inference API.

## Actions [#actions]

### Hugging Face Chat [#hugging-face-chat]

Generate completions using Hugging Face Inference API

#### Input [#input]

| Parameter | Type | Required | Description |
| - | - | - | - |
| `systemPrompt` | string | No | System prompt to guide the model behavior |
| `content` | string | Yes | The user message content to send to the model |
| `provider` | string | Yes | The provider to use for the API request (e.g., novita, cerebras, etc.) |
| `model` | string | Yes | Model to use for chat completions (e.g., "deepseek/deepseek-v3-0324", "meta-llama/Llama-3.3-70B-Instruct") |
| `maxTokens` | number | No | Maximum number of tokens to generate |
| `temperature` | number | No | Sampling temperature (0-2). Higher values make output more random |
| `apiKey` | string | Yes | Hugging Face API token |

#### Output [#output]

| Parameter | Type | Description |
| - | - | - |
| `success` | boolean | Operation success status |
| `output` | object | Chat completion results |
| ↳ `content` | string | Generated text content |
| ↳ `model` | string | Model used for generation |
| ↳ `usage` | object | Token usage information |
| ↳ `prompt_tokens` | number | Number of tokens in the prompt |
| ↳ `completion_tokens` | number | Number of tokens in the completion |
| ↳ `total_tokens` | number | Total number of tokens used |