Skip to main content
← Back to quickstart

platform: 'huggingface' title: 'Hugging Face Inference API' quickStart:

  • 'Create a Hugging Face account'
  • 'Generate an API Token'
  • 'Paste the token into Unimatrix' faq:
  • q: 'Is this different from HuggingChat?' a: 'Yes! This is the Inference API for programmatic access, whereas HuggingChat is the consumer chat interface.' config: | Log into huggingface.co/settings/tokens, generate your API token, and paste it here to access thousands of models.

Hugging Face Inference API Setup

Welcome to the Hugging Face Inference API setup guide.

Hugging Face provides access to thousands of open-source AI models through their Inference API.

Quick Start

  1. Create an account at huggingface.co
  2. Navigate to Settings > Access Tokens
  3. Generate a new API token
  4. Copy the token and paste it into Unimatrix

Configuration

  1. Go to Settings > AI Providers in Unimatrix
  2. Click "Add Provider"
  3. Select "Hugging Face"
  4. Enter your API token: hf_...
  5. Choose your default model (e.g., meta-llama/Meta-Llama-3.1-70B-Instruct)
  6. Save

Features

  • Access to thousands of open-source models
  • Full API capabilities
  • Programmatic memory storage
  • Cross-device sync

Pricing

Hugging Face offers free tier and paid plans. Check huggingface.co/pricing for current pricing.

Troubleshooting

  • Ensure your API token is valid
  • Check your account has sufficient credits
  • Verify network connectivity