Hugging Face logo

Changelog

Keep track of latest changes on the Hugging Face Hub

Jul 18, 25
Inference Providers now fully support OpenAI-compatible API

Our Inference Providers service now fully supports the OpenAI-compatible API, making it easy to integrate with existing workflows. Plus, you can now specify the provider name directly in the model path for greater flexibility.

This means you can effortlessly switch between different inference providers while using the familiar OpenAI client—just point to router.huggingface.co/v1 and include the provider in the model name.

This update simplifies integration while maintaining full compatibility with OpenAI's SDK. Try it now with supported providers like novita, groq, together, and more!

Using Kimi K2 with Groq Inference Provider via OpenAI client

Jun 20, 25
Organization and User profiles now include repository listing pages

Organization and user profiles on the Hub now feature dedicated pages for exploring their repositories, including models, datasets, and Spaces. This makes it much easier to browse and discover content from individual users and organizations, even those with extensive contributions.

This update makes it easier to browse and find resources on all profiles, including top contributors like https://huggingface.co/Qwen or https://huggingface.co/bartowski.

image/png

Jun 17, 25
Add MCP-Compatible Spaces to Your Tools

It's now possible to quickly add any MCP-compatible Space (already 1,000+ available!) to your list of tools, making it easy to use them in your favorite MCP client (VS Code, Cursor, Claude, ...).

To add a new tool, simply click on the MCP label, then select Add to MCP tools. Check your MCP settings to view which tools are available when using the HF Hub MCP integration.

image/png

Jun 16, 25
New Model Filtering Options on the Hub

You can now filter models directly from the main Models page by Tasks, Parameters Count, Library, Supported Applications and Inference Providers. This update makes it easier to find exactly what you need, whether you're looking for lightweight models, specific frameworks or deployment-ready solutions. Try it out at huggingface.co/models.

image/png