Inference API documentation

More information about the API

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

More information about the API

Rate limits

The current API does not enforce strict rate limitations. Instead we simply balance the loads evenly between all our available resources, and favoring steady flows of requests. If your account suddenly sends 10k requests then you’re likely to receive 503 errors saying models are loading. In order to prevent that, you should instead try to start running queries smoothly from 0 to 10k over the course of a few minutes.

Running private models

You can run private models by default ! If you don’t see them on your Hugging Face page please make sure you are logged in. Within the API make sure you include your token, otherwise your model will be declared as non existent.

Running a public model that I do not own

You can. Please check the model card for any licensing issue that might arise, but most public models are delivered by researchers and are usable within commercial products. But please double check.

Finetuning a public model

We currently don’t provide finetuning automatically for any model on your data, but we announced a product in that sense:

Tracking metrics

This is an area of active improvement. Stay tuned as we release more features to track your API usage!

Running the inference on my infrastructure

Currently we do not provide on premises inference out of the box. If you want to use our Accelerated Inference on your infrastructure please contact us at