Browse the Model Catalog

Open the Model Catalog

In the left sidebar, under Dedicated Inference, click Model Catalog.

The catalog shows available models from Hugging Face in a card grid. Each card displays:

• Model name and Hugging Face repository path (e.g. meta-llama/Llama-3.3-70B-Instruct)
• Capability tags: Chat · Reasoning · Code · Embedding · Vision
• Context window size (e.g. 128K)
• Starting price: FROM $X.XX /GPU-h

Filter Models

Use the filter tabs at the top to narrow by capability type:

All · Chat · Code · Reasoning · Embedding · Vision

Use the search bar (Search: llama, qwen, embedding...) to find a model by name or repository.

Deploy a Model

Click Deploy on a model card to go to My endpoints and open the Deploy Dedicated Endpoint modal. You will need to enter the Hugging Face repository path manually.

See detailed guide: Deploy a Model