> ## Documentation Index
> Fetch the complete documentation index at: https://docs.costgraph.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# xAI

> Bring xAI (Grok) usage cost into CostGraph, pulled by us or pushed by you

xAI bills Grok usage per team, broken down by model and modality, so a chat model
and an image model are attributed separately rather than as one bill total.

CostGraph reads xAI as **FOCUS 1.2** records at a grain of one record per day per
Grok model and modality.

## Choose how the data reaches us

<CardGroup cols={2}>
  <Card title="CostGraph pulls it" icon="cloud-arrow-down">
    You supply read-only credentials and we call xAI once a day. Nothing to run.
  </Card>

  <Card title="You push it" icon="cloud-arrow-up">
    You send us FOCUS records over the API. Credentials never leave your infrastructure.
  </Card>
</CardGroup>

## Let CostGraph pull

1. Open **Settings -> Integrations** and pick **xAI**.
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 xAI 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.

<Note>
  Use an xAI Management key, not the inference API key used to call Grok; only a
  Management key can read billing. Credentials are encrypted at rest and used only
  to read billing data. Revoke them in xAI at any time and the connection stops;
  nothing else is affected.
</Note>

## Push it yourself

Send the charges to CostGraph as FOCUS records instead. [Push FOCUS data](/costgraph/integrations/focus-push) 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 xAI spend appears in Cost Overview and in anomaly detection
alongside every other provider, with spend attributed per Grok model so cost
concentration and spikes are visible.