Hugging Face website screenshot

Hugging Face

The AI community building the future with open-source machine learning models, datasets, and applications.

6 APIs 7 Features

APIs

Hugging Face Inference API

Run inference on 200,000+ machine learning models with a simple HTTP request.

Hugging Face Hub API

Programmatically interact with the Hugging Face Hub - manage models, datasets, and spaces.

Hugging Face Inference Endpoints API

Deploy and scale machine learning models with dedicated, secure infrastructure.

Hugging Face Inference Providers API

Unified proxy layer providing access to 15+ inference partners through a single OpenAI-compatible endpoint.

Hugging Face Dataset Viewer API

Query and visualize datasets stored on the Hugging Face Hub through a lightweight REST API.

Hugging Face Text Generation Inference API

High-performance toolkit for deploying and serving large language models with optimized inference.

Agent Skills

hf-cli

AGENT SKILL

hf-mcp

AGENT SKILL

huggingface-best

AGENT SKILL

huggingface-datasets

AGENT SKILL

huggingface-gradio

AGENT SKILL

huggingface-papers

AGENT SKILL

huggingface-trackio

AGENT SKILL

huggingface-zerogpu

AGENT SKILL

transformers-js

AGENT SKILL

Collections

Arazzo Workflows

Hugging Face Chat Completion with Model Discovery

Discover an available router model, confirm it exists, then run an OpenAI-compatible chat completion.

ARAZZO

Hugging Face Create Repository and Configure

Identify the authenticated user, create a new repository, then set its visibility and gating.

ARAZZO

Hugging Face Dataset Filter Rows

Confirm a dataset supports filtering, resolve its split, then apply a SQL-like filter.

ARAZZO

Hugging Face Dataset Search and Statistics

Resolve a dataset split, full-text search within it, then pull column statistics.

ARAZZO

Hugging Face Dataset Size and Parquet Files

Confirm a dataset on the Hub, read its size profile, then list its Parquet files.

ARAZZO

Hugging Face Dataset Validate and Preview

Check a dataset is viewer-ready, list its splits, then preview the first rows.

ARAZZO

Hugging Face Deploy Inference Endpoint and Wait

Create a dedicated Inference Endpoint, then poll its status until it is running.

ARAZZO

Hugging Face Discover a Space

Search Hub Spaces by SDK and query, then load the top Space's details.

ARAZZO

Hugging Face Embeddings Pair

Confirm an embedding model is available, then embed a query and a document for comparison.

ARAZZO

Hugging Face Grounded Text Generation

Find a text-generation model on the Hub, confirm it, then run hosted text generation.

ARAZZO

Hugging Face Search and Inspect a Model

Search the Hub for a model, fetch its full record, then inspect a specific revision.

ARAZZO

Hugging Face Summarize Then Translate

Summarize a long document with one model, then translate the summary with another.

ARAZZO

Hugging Face TGI Inspect and Generate

Read a TGI server's info, tokenize a prompt to check its length, then generate text.

ARAZZO

Hugging Face Toggle Inference Endpoint State

Read an endpoint's current state, then pause it if running or resume it if paused.

ARAZZO

GraphQL

Hugging Face GraphQL Schema

This conceptual GraphQL schema models the Hugging Face AI platform, covering the full surface area of its public APIs: the Hub API for managing models, datasets, and spaces; the...

GRAPHQL

Pricing Plans

Rate Limits

Hugging Face Rate Limits

6 limits

RATE LIMITS

FinOps

Features

Model Inference

Run inference on 200,000+ ML models with a simple HTTP request across NLP, vision, audio, and multimodal tasks.

Hub Repository Management

Programmatically manage models, datasets, and spaces including creation, versioning, and access control.

Dedicated Endpoints

Deploy models on dedicated infrastructure with autoscaling, custom hardware, and private networking.

Multi-Provider Routing

Unified OpenAI-compatible API routing to 15+ inference providers with automatic model selection.

Dataset Exploration

Query, search, filter, and visualize datasets without downloading via the Dataset Viewer API.

Text Generation Inference

High-performance LLM serving with streaming, tool calling, structured output, and grammar constraints.

OpenAI Compatibility

Drop-in replacement for OpenAI API with chat completions, embeddings, and image generation endpoints.

Use Cases

ML Model Prototyping

Rapidly prototype AI applications by running inference on pre-trained models without infrastructure setup.

Production ML Deployment

Deploy and scale ML models for production workloads with dedicated endpoints and autoscaling.

Dataset Curation

Explore, validate, and curate ML datasets programmatically for training pipeline automation.

AI Application Development

Build AI-powered applications using unified inference APIs with multi-provider routing.

Model Benchmarking

Compare model performance across providers and hardware configurations for optimization.

Semantic Vocabularies

Hugging Face Context

4 classes · 15 properties

JSON-LD

Hugging Face Dataset Viewer Context

0 classes · 0 properties

JSON-LD

Hugging Face Hub Context

0 classes · 0 properties

JSON-LD

Hugging Face Inference Context

0 classes · 0 properties

JSON-LD

Hugging Face Inference Endpoints Context

0 classes · 0 properties

JSON-LD

Hugging Face Inference Providers Context

0 classes · 0 properties

JSON-LD

Hugging Face Text Generation Inference Context

0 classes · 0 properties

JSON-LD

API Governance Rules

Hugging Face API Rules

7 rules · 7 errors

SPECTRAL

JSON Structure

Hugging Face Dataset Viewer Error Structure

4 properties

JSON STRUCTURE

Hugging Face Hub Dataset Info Structure

0 properties

JSON STRUCTURE

Hugging Face Hub Dataset Summary Structure

13 properties

JSON STRUCTURE

Hugging Face Hub Error Structure

2 properties

JSON STRUCTURE

Hugging Face Hub Model Info Structure

0 properties

JSON STRUCTURE

Hugging Face Hub Model Summary Structure

15 properties

JSON STRUCTURE

Hugging Face Hub Repo Url Structure

1 properties

JSON STRUCTURE

Hugging Face Hub Space Info Structure

0 properties

JSON STRUCTURE

Hugging Face Hub Space Summary Structure

11 properties

JSON STRUCTURE

Hugging Face Hub User Info Structure

11 properties

JSON STRUCTURE

Hugging Face Inference Error Structure

2 properties

JSON STRUCTURE

Hugging Face Structure

0 properties

JSON STRUCTURE

Example Payloads

Hugging Face Getinfo Example

6 fields

EXAMPLE

Hugging Face Getrows Example

6 fields

EXAMPLE

Hugging Face Isvalid Example

6 fields

EXAMPLE

Hugging Face Whoami Example

6 fields

EXAMPLE

Resources

🔗
PostmanWorkspace
PostmanWorkspace
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🔗
Arazzo
Arazzo
🌐
Portal
Portal
🔗
Documentation
Documentation
🚀
GettingStarted
GettingStarted
💰
Pricing
Pricing
📰
Blog
Blog
📄
ChangeLog
ChangeLog
📝
Signup
Signup
🔗
Login
Login
💬
Support
Support
🔗
Contact
Contact
💬
Support
Support
👥
GitHubOrganization
GitHubOrganization
🔗
X
X
🔗
LinkedIn
LinkedIn
💬
Support
Support
👥
YouTube
YouTube
🟢
StatusPage
StatusPage
📜
TermsOfService
TermsOfService
📜
PrivacyPolicy
PrivacyPolicy
📦
SDKs
SDKs
📦
SDKs
SDKs
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONLD
JSONLD
🔗
MCPServer
MCPServer
🔗
AgentSkills
AgentSkills

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Hugging Face Text Generation Inference API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Text Generation
    type: folder
  items:
  - info:
      name: Generate Text
      type: http
    http:
      method: POST
      url: https://api-inference.huggingface.co/generate
      body:
        type: json
        data: '{}'
    docs: Generate text from a prompt using the loaded model. Returns the full generated text in a single response.
  - info:
      name: Generate Text With Streaming
      type: http
    http:
      method: POST
      url: https://api-inference.huggingface.co/generate_stream
      body:
        type: json
        data: '{}'
    docs: Generate text from a prompt using Server-Sent Events (SSE) streaming. Tokens are returned incrementally as they
      are generated.
  - info:
      name: Create Text Completion (openai Compatible)
      type: http
    http:
      method: POST
      url: https://api-inference.huggingface.co/v1/completions
      body:
        type: json
        data: '{}'
    docs: Create a text completion using the OpenAI-compatible completions API format.
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create Chat Completion (openai Compatible)
      type: http
    http:
      method: POST
      url: https://api-inference.huggingface.co/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: Create a chat completion using the OpenAI-compatible Messages API. Supports conversations, tool calling, structured
      output via JSON schema, and multi-modal inputs (text + images). Fully compatible with OpenAI client libraries.
- info:
    name: Info
    type: folder
  items:
  - info:
      name: List Available Models
      type: http
    http:
      method: GET
      url: https://api-inference.huggingface.co/v1/models
    docs: Get information about the model currently loaded on this TGI server.
  - info:
      name: Get Server Information
      type: http
    http:
      method: GET
      url: https://api-inference.huggingface.co/info
    docs: Get metadata about the TGI server including the loaded model, version, SHA, Docker label, and model-specific parameters.
  - info:
      name: Health Check
      type: http
    http:
      method: GET
      url: https://api-inference.huggingface.co/health
    docs: Check the health of the TGI server. Returns 200 if the model is loaded and ready to serve requests.
  - info:
      name: Get Prometheus Metrics
      type: http
    http:
      method: GET
      url: https://api-inference.huggingface.co/metrics
    docs: Get server metrics in Prometheus format including request counts, latencies, queue sizes, and token throughput.
  - info:
      name: Tokenize Text
      type: http
    http:
      method: POST
      url: https://api-inference.huggingface.co/tokenize
      body:
        type: json
        data: '{}'
    docs: Tokenize a string of text using the model's tokenizer. Returns the token IDs and their string representations.
bundled: true