Connect xAI billing
Prepare the reporting access
Create a separate xAI Management API key with access to the intended team billing report. Record that team’s UUID as teamId. Supply both the management key and teamId; an inference API key is a different credential.
Create and confirm your Token Observe account, sign in and create a workspace. In Connect billing, choose the provider, give the connection a useful name and enter its reporting credential. Enter credentials only in the hosted portal’s masked field, never in a chat, worksheet or support message.
Collect and inspect the source
Choose Connect and collect costs. A saved credential can still have a failed or partial collection. Open Coverage details and check source status, reporting window, last successful collection and any reason for incomplete evidence. Use Collect latest 30 days after fixing permissions or configuration.
The connector reads the xAI Management API team usage report in daily USD buckets. It retains the team and description. SuperGrok subscriptions and prepaid balances or top-ups are separate from reported API usage cost.
Keep the evidence usable
Compare usage cost with usage cost. A credit purchase or prepaid top-up is a funding movement, not another copy of the same API usage. Keep its evidence separately when reconciling settlement.
The collectors bound a run to 31 completed UTC days, 20 requests or pages and 10,000 rows. A partial or failed collection keeps previous evidence with its status. Missing evidence remains unknown. One billing connection per provider per workspace prevents overlapping account connections.
To replace a credential, choose Rotate credential and confirm it accesses the same account. Changing accounts requires disconnecting first; disconnecting removes that connection’s retained costs. Scheduled collection stops when the trial expires. Retained authorized reads and exports remain subject to the shared traffic quota.
The texts this guide names
Where the guide above cites a law, a standard, a specification or a paper, this is the text itself, so an article number or a field name can be checked against the original rather than taken from this page. None of it is a source for what Token Observe does; that traces to the product’s own repository. Each read on .
- xAI Management API billing docs.x.ai
Where this argument meets an implementation
AI spend and subscriptions
What you were billed and what you were metered, recorded as two numbers and never added into one.
AI conversation evidence
What the AI was asked and what it returned, redacted before it is stored and bounded before it is kept.
Those pages are one product's implementation of what this guide argues for, each listing what it does not do beside what it does.
How it worksThe questions next to this one
Connect OpenAI billing
How do I connect OpenAI billing to Token Observe?
Connect Anthropic billing
How do I connect Anthropic billing to Token Observe?
Connect Google Cloud billing
How do I connect Google Cloud billing to Token Observe?
Terms this guide uses
Does billing setup give agents a model key?
No. Billing credentials read reports. Optional model calls need a separate inference key plus a workspace-issued agent identity, permissions and gateway credential.
Can I upload an invoice instead?
The workspace has an existing invoice-import path, but the new cloud portal does not provide its own CSV upload or automatic synchronization of those imports. Ask for setup help if your plan does not expose the supported reporting source.
After reading it, the next step is running it on your own hardware.
Create a cloud account and workspace. No card or server installation. Model calls and Google BigQuery scans can incur separate provider charges.