xAI Grok API cost tracking.
What Audon reads. And what it never reads.
Reads
- Daily team spend in USD by usage description (model and endpoint)
Never reads
- Prompts or responses
- Token counts
- Billing details, invoices or payment methods
The key to create. Used read-only, encrypted, never shown again.
- Credential
- Team-scoped management key
- Where to create it
- console.x.ai → Settings → Management keys. Create a dedicated key scoped to the team you want to audit. xAI management keys can also manage API keys; Audon only calls the key-validation and usage endpoints, and you can revoke the key at any time.
- Provider documentation
- docs.x.ai/developers/rest-api-reference/management/billing
- Step by step
- Provider setup in the docs
Savings levers on xAI data. Sized on your own spend, each with the exact fix.
Pay the fast or priority surcharge only where someone waits; run work nobody waits on at flex or batch rates.
Serve repeated prompt prefixes from cache, and stop paying for cache writes that are never read.
A lever writes a potential saving. A change you mark as done is measured from billing; an approved experiment makes it a verified saving.
Good to know.
- xAI management keys can do more than read. Audon only calls the key-validation and billing usage endpoints, and you can revoke the key at any time.
- The endpoint reports cost, not token counts, so levers that need tokens, such as model routing, don’t run on xAI data yet.
Questions about xAI.
What does Audon need to connect xAI?
What does Audon read from xAI?
Does Audon read prompts, responses or code?
Which savings levers use xAI data?
How do I revoke access?
Last updated
Other integrations.
- What we read
OpenAI
Costs and usage by project, model and line item, read with an organization Admin key.
- What we read
Anthropic (Claude API)
Cost and usage reports by workspace and model, plus Claude Code per person, with one Admin key.
- What we read
Claude EnterpriseNew
Per-person activity, idle seats, and daily cost and tokens by product and model.
- What we read
Claude CodeNew
Tokens and cost per person and model, from the Admin report or Claude Code’s own telemetry.
- What we read
CodexNew
Tokens per day and model from Codex’s own OpenTelemetry export, with no key stored.
- What we read
CursorNew
Members, usage per person and model and on-demand spend, or the usage export on individual plans.
- What we read
DevinNew
Daily ACUs by product and per person, priced with your own price per ACU.