Load Nebius AI Studio data to DuckDB

Nebius Token Factory is an AI platform offering an OpenAI-compatible API for model inference and fine-tuning. Everything needed to build a working Nebius AI Studio → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your Nebius AI Studio to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from Nebius AI Studio to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the Nebius AI Studio API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

Nebius AI Studio API at a glance

These values come from the Nebius AI Studio API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Nebius AI Studio API?

All API requests require an Authorization header with a Bearer token in the format 'Authorization: Bearer '.

1. Get your credentials

1. Navigate to the Nebius AI Studio login page at https://studio.nebius.ai and sign in with your account. 2. Once logged in, click on your profile icon in the top navigation bar to open the account menu. 3. Select Settings from the menu, then navigate to the API Keys section (typically found at https://studio.nebius.ai/settings/api-keys). 4. Click the button to create a new API key, assign it a descriptive name, and copy the generated token immediately, as it cannot be retrieved again after you close the dialog.

2. Add them to .dlt/secrets.toml

Copy
[sources.nebius_ai_studio_source]
api_key = "your_bearer_token_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Nebius AI Studio data can I load into DuckDB?

These are the Nebius AI Studio endpoints dlt can load into DuckDB:

---

How do I load only new Nebius AI Studio records?

Nebius AI Studio exposes after on v1/datasets, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "datasets", "endpoint": {
    "path": "v1/datasets",
    "data_selector": "datasets",
    "incremental": {"cursor_path": "after", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated Nebius AI Studio pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /v1/models and /v1/chat/completions from the Nebius AI Studio API into DuckDB:

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

@dlt.source
def nebius_ai_studio_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.tokenfactory.nebius.com/v1",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "datasets", "endpoint": {"path": "v1/datasets", "data_selector": "datasets"}},
            {"name": "operations", "endpoint": {"path": "v1/operations", "data_selector": "operations"}}
        ],
    }
    yield from rest_api_resources(config)


def load_nebius_ai_studio_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="nebius_ai_studio_pipeline",
        destination="duckdb",
        dataset_name="nebius_ai_studio_data",
    )
    load_info = pipeline.run(nebius_ai_studio_source())
    print(load_info)


if __name__ == "__main__":
    load_nebius_ai_studio_to_duckdb()

Run it with python nebius_ai_studio_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query Nebius AI Studio data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("nebius_ai_studio_pipeline").dataset()
df = data.datasets.df()
print(df.head())

SQL:

Copy
SELECT * FROM nebius_ai_studio_data.datasets LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the Nebius AI Studio to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw Nebius AI Studio loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load Nebius AI Studio data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack