AI & ML Bearer Token

Hugging Face REST API

Open-source AI models and ML infrastructure platform

Hugging Face provides a comprehensive platform for machine learning with access to thousands of pre-trained models, datasets, and inference APIs. Developers use it to deploy state-of-the-art NLP, computer vision, and audio models through a unified REST API. The platform supports model hosting, versioning, and serverless inference for production AI applications.

Base URL https://api-inference.huggingface.co

API Endpoints

Method	Endpoint	Description
POST	`/models/{model_id}`	Run inference on any model from the Hugging Face Hub
GET	`/models/{model_id}`	Get model metadata, architecture, and configuration details
POST	`/models/{model_id}/pipeline`	Execute a specific pipeline task (text-generation, summarization, etc.)
GET	`/api/models`	List and search available models with filters
GET	`/api/datasets`	Browse and search available datasets
GET	`/api/datasets/{dataset_id}`	Get dataset information, splits, and download links
POST	`/models/{model_id}/embeddings`	Generate text embeddings using sentence transformers
POST	`/models/{model_id}/feature-extraction`	Extract features from text, images, or audio inputs
POST	`/models/{model_id}/text-classification`	Classify text into predefined categories
POST	`/models/{model_id}/token-classification`	Perform named entity recognition or part-of-speech tagging
POST	`/models/{model_id}/question-answering`	Answer questions based on provided context
POST	`/models/{model_id}/image-classification`	Classify images using computer vision models
POST	`/models/{model_id}/automatic-speech-recognition`	Transcribe audio to text using speech recognition models
GET	`/api/repos/{repo_id}`	Get repository information including files and commits
POST	`/models/{model_id}/conversational`	Run multi-turn conversational AI with context retention

Code Examples

curl https://api-inference.huggingface.co/models/gpt2 \
  -X POST \
  -H "Authorization: Bearer hf_xxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"inputs": "The future of AI is"}'

const response = await fetch(
  'https://api-inference.huggingface.co/models/gpt2',
  {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer hf_xxxxxxxxxxxxxxxxxxxxx',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      inputs: 'The future of AI is'
    })
  }
);

const result = await response.json();
console.log(result);

import requests

API_URL = "https://api-inference.huggingface.co/models/gpt2"
headers = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxx"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "The future of AI is",
})
print(output)

Connect Hugging Face to AI

Deploy a Hugging Face MCP server on IOX Cloud and connect it to Claude, ChatGPT, Cursor, or any AI client. Your AI assistant gets direct access to Hugging Face through these tools:

search_models Search and filter Hugging Face models by task, language, framework, or tags to find the right model for specific use cases

run_inference Execute inference on any Hugging Face model with automatic task detection and parameter optimization

generate_embeddings Generate vector embeddings for text using sentence transformers for semantic search and similarity tasks

compare_models Compare multiple models side-by-side based on performance metrics, parameters, and use case suitability

dataset_explorer Browse and analyze Hugging Face datasets with automatic schema detection and sample previews

Deploy in 60 seconds

Describe what you need, AI generates the code, and IOX deploys it globally.

Deploy Hugging Face MCP Server →

Hugging Face REST API

API Endpoints

Code Examples

Connect Hugging Face to AI

Deploy in 60 seconds

Related APIs