Fal-ai Python API Docs | dltHub

Fal AI is a unified generative media model platform exposing 600+ production-ready image, video, audio and text model endpoints via HTTP and WebSocket APIs. The REST API base URL is https://api.fal.ai/v1 and All requests that require elevated rate limits or private actions use an API key presented in the Authorization header (prefixed with "Key ")..

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 Fal-ai data in under 10 minutes.

---

What data can I load from Fal-ai?

Here are some of the endpoints you can load from Fal-ai:

---

How do I authenticate with the Fal-ai API?

Fal uses API keys. Include the key in the request header as: Authorization: Key YOUR_API_KEY (some gateway/proxy examples also accept Bearer in gateway contexts).

1. Get your credentials

1. Sign in to your Fal account at https://fal.ai/ 2) Open the dashboard and navigate to Keys (https://fal.ai/dashboard/keys) 3) Create a new API key and copy it. 4) Use the key in requests: Authorization: Key <your_key> or configure the client with fal.config({credentials: ""}).

2. Add them to .dlt/secrets.toml

Copy
[sources.fal_ai_source]
api_key = "your_fal_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 Fal-ai 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 fal_ai_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline fal_ai_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_details from the Fal-ai 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 fal_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.fal.ai/v1",
            "auth": {
                "type": "api_key",
                "api_key": api_key,
            },
        },
        "resources": [
            {"name": "models", "endpoint": {"path": "v1/models", "data_selector": "models"}},
            {"name": "model_details", "endpoint": {"path": "v1/models?endpoint_id=<endpoint_id>", "data_selector": "models"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="fal_ai_pipeline",
        destination="duckdb",
        dataset_name="fal_ai_data",
    )
    load_info = pipeline.run(fal_ai_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("fal_ai_pipeline").dataset()
sessions_df = data.models.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM fal_ai_data.models LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("fal_ai_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 Fal-ai 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

Fal API requires an API key in the Authorization header. Use: Authorization: Key YOUR_API_KEY. Missing or malformed header returns 401/403; ensure the key is copied from https://fal.ai/dashboard/keys and prefixed with "Key ". When using Cloudflare AI Gateway, the gateway may accept Bearer or Key depending on its configuration.

Rate limits and quotas

Unauthenticated requests or requests without a valid API key have lower rate limits. Authenticated requests receive higher limits. Hitting rate limits returns 429; implement exponential backoff and respect provided retry‑after headers.

Pagination

The /v1/models endpoint is paginated. Responses include "next_cursor" (string|null) and "has_more" (boolean). Use the cursor query parameter to fetch subsequent pages: ?cursor=<next_cursor>&limit=.

Model execution response variability

Model endpoints (https://fal.run/<model_path> or queue) return model‑specific responses (images, audio, text) and do not share a single universal data selector; consult the model's OpenAPI or documentation available via the models API to know the exact response schema.

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