AI and agents · by Hugging Face

Hugging Face Inference

Make text, images or video with popular open-source AIs.

text, image → text, data, code · text, image → image · text, image → video
Way in
Official APISign up yourself, api key
To start
$Free users: none (buy credits). PRO ($9/mo): $2/mo credits; Team/Enterprise $2/seat
Runs
In the cloud
Checked
Nov 3, 2026Prices as of that day

What it can do 5

Call hosted LLMs through one OpenAI-compatible endpointrouter.huggingface.co/v1 OpenAI-compatibletext, image → text, data, codepass-through provider price, no HF markup
Generate images from any Hub model a provider servestext, image → imagepass-through (fal, Replicate, Together, Nscale, Novita, WaveSpeed, hf-inference)
Generate video from text or an imagetext, image → videopass-through (fal, Replicate, Novita, WaveSpeed, Together)
Embed text (feature extraction)text → embeddingpass-through; hf-inference billed by compute time
Transcribe speechspeech → textpass-through

Does the same job

Prices and limits as of Nov 3, 2026, from Hugging Face’s own pages. They change; check before you rely on them.Not affiliated with Hugging Face. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.