Inference Providers documentation
Nebius
Nebius
All supported Nebius models can be found here
Nebius AI is a technology company specializing in AI-centric cloud platforms, offering scalable GPU clusters, managed services, and developer tools designed for intensive AI workloads. Headquartered in Amsterdam, Nebius provides flexible architecture and high-performance infrastructure to support AI model training and inference at any scale.
Supported tasks
Chat Completion (LLM)
Find out more about Chat Completion (LLM) here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="nebius",
api_key=os.environ["HF_TOKEN"],
)
completion = client.chat.completions.create(
model="deepseek-ai/DeepSeek-R1-0528",
messages=[
{
"role": "user",
"content": "What is the capital of France?"
}
],
)
print(completion.choices[0].message)Chat Completion (VLM)
Find out more about Chat Completion (VLM) here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="nebius",
api_key=os.environ["HF_TOKEN"],
)
completion = client.chat.completions.create(
model="google/gemma-3-27b-it",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
],
)
print(completion.choices[0].message)Feature Extraction
Find out more about Feature Extraction here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="nebius",
api_key=os.environ["HF_TOKEN"],
)
result = client.feature_extraction(
"Today is a sunny day and I will get some ice cream.",
model="Qwen/Qwen3-Embedding-8B",
)Text To Image
Find out more about Text To Image here.
Language
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="nebius",
api_key=os.environ["HF_TOKEN"],
)
# output is a PIL.Image object
image = client.text_to_image(
"Astronaut riding a horse",
model="black-forest-labs/FLUX.1-dev",
)