At a glance
- Availability: Experimental (how to enable).
- Auth: API key.
- Connection: The key comes from
HF_TOKEN. - Docs: https://huggingface.co/docs/hub/security-tokens
Credentials
Set these per environment. See Connect an integration.| Variable | Required | Description |
|---|---|---|
HF_TOKEN | Yes | Hugging Face access token (starts with hf_) Docs. |
Setup
- Create a Hugging Face account: Go to https://huggingface.co and sign up or sign in. Hub API access and a generous Inference Providers free tier are available without billing.
- Create an access token: Open https://huggingface.co/settings/tokens and create a fine-grained token. Enable ‘Make calls to Inference Providers’ if you want to use the chat completion tool; read access covers the Hub search tools.
- Store the token: Copy the token and add it to your .env file as HF_TOKEN=hf_…
- Verify access: Run the Who Am I tool to confirm the token works and shows the expected permissions.
- Hub search endpoints work with read-scoped tokens; chat completions require the Inference Providers permission
- Inference Providers usage beyond the free tier is billed at provider rates with no markup; PRO accounts include monthly credits
- Some gated models (e.g. meta-llama) require accepting their license on the Hub before access
Tools
| Tool | Access | Description |
|---|---|---|
| Search Models | Read | Search models on the Hugging Face Hub |
| Get Model | Read | Get details about a model repository on the Hub |
| Search Datasets | Read | Search datasets on the Hugging Face Hub |
| Who Am I | Read | Get the account and permissions associated with the access token |
| Create Chat Completion | Write | Generate a chat completion through the Hugging Face Inference Providers router (OpenAI-compatible) |
Example prompts
- Search the Hugging Face Hub for trending models for a task I describe and summarize the top results.
- Use Hugging Face Inference Providers to generate a response from an open model I pick.