fal

{/* Generated by scripts/generate-integration-catalog.mjs. Do not edit by hand. */}

At a glance

Credentials

Set these per environment. See Connect an integration.

VariableRequiredDescription
FAL_KEYYesfal API key (sent as 'Authorization: Key <FAL_KEY>') Docs.

Setup

  1. Create a fal account: Sign up at https://fal.ai - new accounts get free credits to try models before adding billing.
  2. Create an API key: Open https://fal.ai/dashboard/keys, create a key, and copy it immediately - it is only shown once.
  3. Store the key: Add it to your .env file as FAL_KEY=.... - requests authenticate with the header 'Authorization: Key <FAL_KEY>'.
  4. Pick a model and verify: Browse https://fal.ai/models and copy a model endpoint ID (e.g. fal-ai/flux/schnell). Pass its segments as app_owner=fal-ai, app_id=flux, app_variant=schnell to the Run Model tool with a small input payload.

Provider notes

  • Each model has its own input schema - check the model's API tab on fal.ai/models for required fields
  • Use the queue tools (submit → status → result) for slow models like video generation; synchronous fal.run requests can time out
  • Queue status/result/cancel URLs use the base app ID without the variant segment (fal returns ready-made status_url and response_url in the submit response)
  • Model runs are billed per inference - check the model page for pricing

Provider API reference.

Tools

ToolAccessDescription
Run Model<br /><code className="reference-identifier">fal__run_model</code>WriteRun model (billed per run)
Submit Queue Request<br /><code className="reference-identifier">fal__queue_submit</code>WriteSubmit queue request (billed per run)
Get Queue Status<br /><code className="reference-identifier">fal__queue_status</code>ReadGet queue status
Get Queue Result<br /><code className="reference-identifier">fal__queue_result</code>ReadGet queue result
Cancel Queue Request<br /><code className="reference-identifier">fal__queue_cancel</code>WriteCancel pending queue request

Verify the connection

Call a read tool such as fal__queue_status with arguments for your account. Confirm that the result comes from the intended account or workspace before enabling write tools.