View all systems 
Fal.aiai models
12 available actions
What your AI agent can do in Fal.ai
The generative media platform for developers with 600+ AI models for image, video, voice, and audio generation This page lists every available action. Your agent only receives the actions and permissions required for the role you approve.
Showing all 12 actions.
Common starting points
- Get ModelsTool to discover and search fal.ai model endpoints.
- Get Model PricingTool to retrieve unit pricing for model endpoints.
- Submit Async Inference JobTool to submit an asynchronous inference job to fal.ai's queue (queue.fal.run).
- Upload Input FileTool to 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.
- Run Model (Sync)Tool to 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.
- Cancel Queue RequestTool to cancel a queued or in-progress request in fal.ai's queue system.
Browse all 12 actions by capability
Open a capability to see every supported action and its description.
Find & reviewLook up and review existing recordsView 5 actions
- Get JWKS for Webhook VerificationTool to retrieve public keys for webhook signature verification.
- Get ModelsTool to discover and search fal.ai model endpoints.
- Get Model PricingTool to retrieve unit pricing for model endpoints.
- Get Queue Request ResultTool to retrieve the final result of a completed queue request.
- Check Queue Request StatusTool to check the status of a queued request in fal.ai.
Create & communicateCreate records or send supported messagesView 2 actions
- Submit Async Inference JobTool to submit an asynchronous inference job to fal.ai's queue (queue.fal.run).
- Upload Input FileTool to 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.
Update & manageChange and manage existing recordsView 1 action
- Run Model (Sync)Tool to 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.
Remove & cancelRemove records or cancel supported workView 1 action
- Cancel Queue RequestTool to cancel a queued or in-progress request in fal.ai's queue system.
Other actionsSpecialist and administrative actions.View 3 actions
- Estimate PricingTool to estimate pricing for fal.ai model endpoints.
- Stream Request Status UpdatesTool to stream request status updates via SSE.
- Subscribe to Async Inference JobTool to 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.
Connection record
A connection you can control.
- Sign-in
- Customer-managed key
- Setup
- Use a key you create and control. It is stored securely and limited to the work agreed for the role.
- Boundaries
- Only the approved role and actions.
- Off switch
- Revoke the connection from your account.
FAQ
Before you connect Fal.ai
How does the agent connect to Fal.ai?
With a key you create and control. It is stored securely, permissions are limited to what the agent needs, and you can revoke it at any time.
What can the agent actually do in Fal.ai?
The page above lists the 12 actions currently available through the Fal.ai connection. The role determines which of those actions the agent may use, and write access is only enabled when the workflow needs it.
Is Fal.ai included in my plan?
Connections are priced per tool on top of the base plan. Some are included and some are premium. See pricing for how connection charges work.
How long until Fal.ai is ready?
Timing depends on the sign-in method, permissions and workflow being connected. We confirm the scope and setup plan before enabling the connection.
Bring the workflow together
Ready to put Fal.ai to work?
Start with the responsibility you want off your plate. We’ll map the connection and the boundaries around it.