Inference Providers documentation

Providers

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Providers

Inference Providers sends each request to a provider serving the model. You pay that provider’s price with no markup, and you can turn off the providers listed on this page in your settings.

Language models

Chat, vision and agent requests go through OpenRouter, which routes each one to a provider serving the model, including the ones below. See Routing and Providers to choose how a provider is picked. To send a request to one provider only, append the suffix shown on its card to the model id, for example deepseek-ai/DeepSeek-V4.1-Flash:together.

Baseten

:baseten · On the Hub · Privacy policy

Cerebras

:cerebras · On the Hub · Privacy policy

Cohere

CoreWeave

:coreweave · On the Hub · Privacy policy

DeepInfra

:deepinfra · On the Hub · Privacy policy

DigitalOcean

:digitalocean · On the Hub · Privacy policy

Featherless AI

:featherless · On the Hub · Privacy policy

Fireworks

:fireworks · On the Hub · Privacy policy

Liquid AI

Mistral

:mistral · On the Hub · Privacy policy

Moonshot AI

:moonshotai · On the Hub · Privacy policy

Nebius

Novita

Parasail

:parasail · On the Hub · Privacy policy

Prime Intellect

:primeintellect · On the Hub

Reka

Tencent

:tencent · On the Hub · Privacy policy

Together AI

:together · On the Hub · Privacy policy

Zai

Which providers serve a language model

A model’s page on the Hub lists its providers. To compare their price, speed and context length, use the models page or GET https://router.huggingface.co/v1/models (see Hub API).

Image, video, audio, embeddings and more

Other tasks go to the following providers through the Hugging Face SDKs. Each link lists the models a provider serves on the Hub. To pick a provider, pass the id shown on its card as provider. The list of providers is also available on each model’s page.

HF Inference API

Replicate

WaveSpeed

wavespeed · Image and video · On the Hub
Update on GitHub