Nebius Studio Python API Docs | dltHub

Nebius Studio is a platform that provides access to open-source large language models (LLMs) and inference endpoints for running text generation and embeddings. The REST API base URL is https://api.studio.nebius.ai/v1 and all requests require a Bearer API key in the Authorization header.

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Nebius Studio data in under 10 minutes.

---

What data can I load from Nebius Studio?

Here are some of the endpoints you can load from Nebius Studio:

---

How do I authenticate with the Nebius Studio API?

Nebius Studio uses an API key (Bearer token). Include the key in the HTTP header: Authorization: Bearer <YOUR_API_KEY> for REST calls.

1. Get your credentials

1. Register for an account at Nebius (e.g. https://auth.eu.nebius.com/ui/login). 2) Sign in to Nebius AI Studio (https://studio.nebius.ai). 3) Open Settings → API Keys (https://studio.nebius.ai/settings/api-keys). 4) Create/generate a new API key and copy it to your secure store.

2. Add them to .dlt/secrets.toml

Copy
[sources.nebius_studio_source]
api_key = "your_nebius_api_key_here"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Nebius Studio API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python nebius_studio_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline nebius_studio_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset nebius_studio_data
The duckdb destination used duckdb:/nebius_studio.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline nebius_studio_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads models and model from the Nebius Studio API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def nebius_studio_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.studio.nebius.ai/v1",
            "auth": {
                "type": "bearer",
                "token": api_key,
            },
        },
        "resources": [
            {"name": "models", "endpoint": {"path": "v1/models", "data_selector": "models"}},
            {"name": "model", "endpoint": {"path": "v1/models/{model}"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="nebius_studio_pipeline",
        destination="duckdb",
        dataset_name="nebius_studio_data",
    )
    load_info = pipeline.run(nebius_studio_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("nebius_studio_pipeline").dataset()
sessions_df = data.models.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM nebius_studio_data.models LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("nebius_studio_pipeline").dataset()
data.models.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Nebius Studio data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication failures

If you get 401 Unauthorized: verify your API key is correct, not expired, and present in the Authorization header as "Bearer <API_KEY>". Regenerate the key in Studio → Settings → API Keys if needed.

Rate limits and quota errors

Nebius may enforce rate limits or quota limits; 429 responses indicate rate limiting. Back off with exponential retry and consult your Nebius plan/usage dashboard.

Pagination and large lists

List endpoints (models, usage) may paginate. Check response for pagination fields (cursor/next_page) and use provided query params (page, limit or cursor) where present. If the response contains a top‑level object with an array under a named key (e.g. "models"), use that key as the data selector.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack