Hugging Face

Popular

Hugging Face hosts the world's largest collection of ML models and provides Inference Endpoints and Serverless Inference API for instant deployment. Access thousands of models including LLMs, image generation, embeddings, and more with a unified API. The free tier allows quick prototyping.

Official Website Documentation

Endpoints

POST

Text Generation

/v1/chat/completions

Generate text using any hosted text generation model.

Streaming

Vision

Function Calling

Models

meta-llama/Llama-3.1-8B-Instructmeta-llama/Llama-3.1-70B-Instructmistralai/Mistral-7B-Instruct-v0.3google/gemma-2-9b-it

Pricing

Model	Input Price	Output Price	Context Window
Llama 3.1 8B (free tier available)	Free	Free	32.0K
Inference Endpoints (dedicated)	Free	Free	32.0K

Capabilities

Streaming

Embeddings

Image Input

Audio Input

Audio Output

Fine-tuning

Try it in Playground

Test Hugging Face APIs directly in our interactive playground with your own API key.

Try it in Playground

Hugging Face

Endpoints

Text Generation

Capabilities

Try it in Playground

Overview

Hugging Face

Endpoints

Text Generation

Capabilities

Try it in Playground

Overview