Claude Enterprise seat and usage analytics.
What Audon reads. And what it never reads.
Reads
- Per-person daily activity: chat messages and conversations, Cowork sessions, Claude Code sessions, lines, commits and pull requests
- Members and seats (active vs. no activity in the last 30 days)
- Daily cost and token usage by product and model (usage-based plans; usage credits only on seat-based plans)
Never reads
- Prompts, responses, files or code
- Seat fees or invoices (add the plan under Subscriptions)
- Claude Code used through Amazon Bedrock
The key to create. Used read-only, encrypted, never shown again.
- Credential
- Analytics API key (read:analytics scope)
- Where to create it
- claude.ai → Organization settings → API (claude.ai/admin-settings/api-access). Only the primary owner can enable API access and create the key. Claude Console Admin keys can’t call this API.
- Provider documentation
- platform.claude.com/docs/en/manage-claude/analytics-api
- Step by step
- Provider setup in the docs
Savings levers on Claude Enterprise data. Sized on your own spend, each with the exact fix.
Give each person the cheapest plan that covers how they work: remove, downgrade, upgrade or move to a seat.
Default coding agents to a cheaper model or the tool’s own model pool; keep the premium model for hard tasks.
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.
- Only the primary owner can create the Analytics key. Claude Console Admin keys can’t call this API.
- Seat fees aren’t in the API: add the Claude plan under Settings → Subscriptions so idle seats are priced.
- Activity is a daily snapshot with about a day of lag. Data starts on 1 January 2026.
Questions about Claude Enterprise.
What does Audon need to connect Claude Enterprise?
What does Audon read from Claude Enterprise?
Does Audon read prompts, responses or code?
Which savings levers use Claude Enterprise 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 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
xAINew
Daily team spend by model and endpoint, read with a team-scoped management key.
- 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.