Skip to main content
fal.ai hosts generative media models behind API endpoints and bills each endpoint in its own unit, such as images, seconds of video, or GPU time. CostGraph reads fal.ai as FOCUS 1.2 records at a grain of one record per model endpoint per billing unit per API key per day.

​
Choose how the data reaches us

CostGraph pulls it

You supply read-only credentials and we call fal.ai once a day. Nothing to run.

You push it

You send us FOCUS records over the API. Credentials never leave your infrastructure.

​
Before you begin

  • In the fal dashboard, open Keys and create an API key with the Billing permission preset.

​
Let CostGraph pull

  1. Open Settings > Integrations and pick fal.ai.
  2. Name the connection and pick the tenant these charges belong to.
  3. Enter the values you copied. The form lists what fal.ai needs and marks the optional ones.
  4. Select Connect.
CostGraph verifies the credentials with a short fetch before saving, so a wrong value or a missing permission fails while you are still on the form.
Credentials are encrypted at rest and used only to read billing data. Revoke them in fal.ai at any time and the connection stops; nothing else is affected.

​
Push it yourself

Send the charges to CostGraph as FOCUS records instead. Push FOCUS data covers the connection id, the focus:write key, and the request shape.

​
Run the exporter

Rather than build that request yourself, run our exporter. It reads fal.ai on a schedule and pushes the records for you, wherever you want to run it: a container, a Kubernetes CronJob, or a binary on a machine you already have.
Your fal.ai credential stays where you put it, and only the finished FOCUS records reach CostGraph. Run the exporter covers the three ways to run it and the variables it reads.

​
What CostGraph does with it

Records land as raw billing rows, are normalised into line items, and roll up into daily cost. From there fal.ai spend appears in Cost Overview and in anomaly detection alongside every other provider. fal.ai reports usage before it invoices, so the cost is an estimate until fal.ai invoices it. Spend is split per model endpoint and per API key, with any discount applied shown on the line, so you can see which model and which key drive the bill.