AI and media
AI agents that use fal.ai
UtilitySpaces gives an AI agent scoped access to fal.ai through its own encrypted connection, not your password. The agent can call 3 named fal.ai tools, and the 2 that write wait for a person's approval unless an admin has set the connection to run without asking. Every call is written to a hash-chained audit log with its arguments and its result.
What an agent can do in fal.ai
Run fal.ai hosted models for image, video, and audio generation. A model is called by posting its id as the path, e.g. fal-ai/flux/dev. An agent calls these by name, and matching is exact.
| Tool | What it does | Waits for approval by default |
|---|---|---|
| Run model | Run a fal.ai model synchronously (billed run). Every argument other than model_id/method becomes the model's JSON input. Use it for image models (answers within 90s); for video models use queue_submit + queue_result. | Yes — it writes |
| Queue a model run | Start a fal model run without waiting (use for video models). Every argument other than model_id becomes the model input. Returns request_id; poll queue_result with the same model_id. | Yes — it writes |
| Queued run status / result | Status of a queued run; once COMPLETED, data.output is the model's output (media URLs are public https). Poll every 15-30s. | No — read only |
1 read tool, 2 write tools. Generated from the connector catalogue the product runs on, so it cannot list a tool that does not exist.
What waits for a person
Reads run on their own. These do not — each one waits in Approvals for an owner or admin unless an admin has set this connection to run writes without asking, and every call tofal.ai, approved, rejected or unattended, is logged.
- Run model POST
- Queue a model run
What connecting fal.ai takes
fal.ai uses an API key you create in fal.ai and paste in once. A workspace admin sets the connection up; the fields are:
- API Key
Credentials are encrypted and bound to your workspace, never read back, and every outbound call passes one guarded fetch — the connector security posture sets out exactly how, and the security page covers the platform around it.
Where fal.ai fits
Give an agent fal.ai work by writing a message in the inbox, or put its tools in a scheduled flow. What the run cost is on the cost breakdown.
Other ai and media integrations: AnythingLLM, AssemblyAI, D-ID. Or see every application agents can connect to.
See it doing your actual work
Open a demo workspace, connect one app, and give an agent a real job. No card, no sales call.
We reply to every message within one business day.