Load Chutes data to DuckDB

Chutes is a serverless inference platform that provides APIs for managing account resources and executing open-source AI models. Everything needed to build a working Chutes → 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 Chutes 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 Chutes 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 Chutes 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.

---

Chutes API at a glance

These values come from the Chutes API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Chutes API?

All API requests require an Authorization header using the Bearer scheme with an API key, formatted as 'Authorization: Bearer <api_key>'. Management and inference endpoints consistently use this Bearer token authentication mechanism.

1. Get your credentials

To obtain your Chutes API credentials, perform the following steps: 1. Log in to your account on the Chutes platform. 2. Navigate to your dashboard or account settings. 3. Locate the API Keys or Developer section. 4. Click the button to generate a new API key (or use the CLI command chutes keys create --name to create one via your terminal). 5. Copy the generated API key immediately, as it may not be visible again.

2. Add them to .dlt/secrets.toml

Copy
[sources.chutes_source]
CHUTES_API_KEY = "cpk_xxxxxxxxxxxxxxxx"

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 Chutes data can I load into DuckDB?

These are the Chutes endpoints dlt can load into DuckDB:

---

How do I load only new Chutes records?

The Chutes API reference does not document a timestamp or sequence field for these endpoints, so there is nothing to advertise here as verified. Pick a field from the endpoints table above that increases with every write, then set it as the cursor_path.

Copy
{"name": "chutes", "endpoint": {
    "path": "chutes/",
    # Replace with a field that increases on every write.
    "incremental": {"cursor_path": "REPLACE_ME", "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 Chutes pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading chutes and users from the Chutes API into DuckDB:

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

@dlt.source
def chutes_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.chutes.ai",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "chutes", "endpoint": {"path": "chutes/", "data_selector": "items"}},
            {"name": "images", "endpoint": {"path": "images/"}}
        ],
    }
    yield from rest_api_resources(config)


def load_chutes_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="chutes_pipeline",
        destination="duckdb",
        dataset_name="chutes_data",
    )
    load_info = pipeline.run(chutes_source())
    print(load_info)


if __name__ == "__main__":
    load_chutes_to_duckdb()

Run it with python chutes_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 Chutes 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("chutes_pipeline").dataset()
df = data.chutes.df()
print(df.head())

SQL:

Copy
SELECT * FROM chutes_data.chutes LIMIT 10;

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

---

How do I deploy the Chutes 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 Chutes 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 Chutes 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