Run inference on any Hub model
One step with Hugging Face. We can help you get access.
Get something done
Run inference on any Hub model
with Hugging Face · Artificial Intelligence Management
Use Hugging Face: its Hugging Face Inference Natural Language Processing API lets you run inference on any Hub model in a single step (POST /models/{model_id}). capabilities.work can help you get signed up and connected.
- Can I call any model hosted on the Hub with a generic inference request?
- Does the input and output format change depending on a model's pipeline task?
Say it to your AI assistant
- Run inference on model {model_id} with input {inputs}.
- Send {inputs} to {model_id} with task parameters {parameters}.
For your developer
POST /models/{model_id} in Hugging Face Inference Natural Language Processing API. Full spec on APIs.io.