---
title: "Fal.ai integration for LuumenAI"
url: "https://www.luumen.ai/integrations/fal-ai/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Fal.ai integration for LuumenAI

Browse fal.ai models, check pricing, and run inference jobs as approved steps

## What LuumenAI can do with Fal.ai

LuumenAI connects to Fal.ai with an API token and exposes 12 tools (7 read-only · 4 write · 1 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 12 tools (7 read-only · 4 write · 1 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Fal.ai with LuumenAI

Connect fal.ai and Luumen can search the model catalog, read unit pricing, estimate what a batch will cost, and follow queued requests to completion. When you want work to actually run, it submits the job, uploads input files, or cancels a stuck request — each change previewed and approved first. Auth is a fal.ai API key.

## Example tools

Read-only (7 in total):

- `FAL_AI_ESTIMATE_PRICING` — Estimate pricing for fal.ai model endpoints.
- `FAL_AI_GET_JWKS` — Retrieve public keys for webhook signature verification.
- `FAL_AI_GET_MODELS` — Discover and search fal.ai model endpoints.
- `FAL_AI_GET_PRICING` — Retrieve unit pricing for model endpoints.
- `FAL_AI_GET_QUEUE_REQUEST_RESULT` — Retrieve the final result of a completed queue request.
- `FAL_AI_QUEUE_GET_STATUS` — Check the status of a queued request in fal.ai.
- `FAL_AI_QUEUE_GET_STATUS_STREAM` — Stream request status updates via SSE.

Write and destructive (5 in total, approval required by default):

- `FAL_AI_CANCEL_QUEUE_REQUEST` — Cancel a queued or in-progress request in fal.ai's queue system.
- `FAL_AI_RUN_MODEL_SYNC` — Invoke a fal.ai model synchronously via fal.run, generating new content (images, audio, video, or other model outputs) hosted at fal.ai CDN URLs in the response.
- `FAL_AI_SUBMIT_ASYNC_JOB` — Submit an asynchronous inference job to fal.ai's queue (queue.fal.run).
- `FAL_AI_SUBSCRIBE_ASYNC_JOB` — Submit a fal.ai inference job to the async queue and block until it completes (or a deadline is reached), returning the model's final result.
- `FAL_AI_UPLOAD_FILE` — Upload an input media file (image, audio, or video) to fal.ai's CDN and return a public access_url that can be passed as a model input.

## Frequently asked questions

### How does LuumenAI connect to Fal.ai?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Fal.ai on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Fal.ai — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/fal-ai/