Skip to main content
LiteLLM is a self-hosted gateway that fronts many LLM providers behind one proxy and tracks the spend of every request it routes. CostGraph reads LiteLLM as FOCUS 1.2 records at a grain of one record per day per model per virtual key.

​
Choose how the data reaches us

CostGraph pulls it

You supply read-only credentials and we call LiteLLM 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

  • Note the base URL of your LiteLLM proxy, for example https://litellm.mycompany.com. Its host becomes the billing account, because the proxy has no organization id.
  • Copy the proxy master key. Only the master key reads spend across every virtual key rather than the caller’s own.

​
Let CostGraph pull

  1. Open Settings > Integrations and pick LiteLLM.
  2. Name the connection and pick the tenant these charges belong to.
  3. Enter the values you copied. The form lists what LiteLLM 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 LiteLLM 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 LiteLLM 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 LiteLLM 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 LiteLLM spend appears in Cost Overview and in anomaly detection alongside every other provider, with spend attributed back to the virtual key or team that incurred it.