Skip to main content
OpenAI bills API usage per model and token bucket, so model spend lands beside your infrastructure cost. CostGraph reads OpenAI as FOCUS 1.2 records at a grain of day x model x token bucket (billed cost + quantity).

​
Choose how the data reaches us

CostGraph pulls it

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

You push it

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

​
Let CostGraph pull

  1. Open Settings -> Integrations and pick OpenAI.
  2. Name the connection and pick the tenant these charges belong to.
  3. Fill in the values the form asks for. It lists exactly the variables OpenAI needs, marks which are optional, and explains the permission each one requires.
  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 OpenAI 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.

​
What CostGraph does with it

Records land as raw billing rows, are normalised into line items, and roll up into daily cost. From there OpenAI spend appears in Cost Overview and in anomaly detection alongside every other provider.