--- title: "Cursor team usage and seat costs · Audon" description: "Track Cursor on-demand spend per person and model with the team Admin API, or a usage export on Pro and Ultra, and find unused seats and Max mode costs." url: https://audon.ai/integrations/cursor last_updated: 2026-11-02 --- # Cursor team usage and seat costs. On team plans with the Admin API, Audon reads members, usage per person and model, and on-demand spend this billing cycle. On individual plans (Pro, Ultra) you upload the usage export from the Cursor dashboard instead. [Start free auditFree](https://audon.ai/sign-up?intent=spend) [About Agent Spend Optimization](https://audon.ai/product/agent-spend-optimization) ## What Audon reads. And what it never reads. Reads - On-demand (usage-based) charges per person and model - Which requests used your own OpenAI or Anthropic key - Team members and their spend this billing cycle - On-demand charges per day and model (usage export) - Included and free requests and tokens per model (usage export) Never reads - Code, prompts or responses - Seat fees (add them under Subscriptions) - Billing details or invoices ## The key to create. Used read-only, encrypted, never shown again. **Credential** Team Admin API key **Where to create it** cursor.com/dashboard → API Keys → New API Key with admin access. Only team admins can create one, on Cursor team plans that include the Admin API (Enterprise). **Without the Admin API** Usage export (CSV) from cursor.com/dashboard → Usage. Individual plans (Pro, Ultra) have no usage API. Export your usage as CSV from the Cursor dashboard and upload it with cursor_import_usage (POST /v1/connections/cursor/import). Upload a newer export at any time; re-uploads replace the days they cover. **Provider documentation** [docs.cursor.com/account/teams/admin-api](https://docs.cursor.com/account/teams/admin-api) **Step by step** [Provider setup in the docs](https://audon.ai/docs/integrations#cursor) ## Savings levers on Cursor data. Sized on your own spend, each with the exact fix. - [Right plan per person](https://audon.ai/glossary/right-plan-per-person) Give each person the cheapest plan that covers how they work: remove, downgrade, upgrade or move to a seat. - [Coding model mix](https://audon.ai/glossary/coding-model-mix) Default coding agents to a cheaper model or the tool’s own model pool; keep the premium model for hard tasks. - [Cursor Max mode](https://audon.ai/glossary/cursor-max-mode) Keep Max mode for large, multi-file work; normal mode costs less per token for the rest. - [Overlapping tools](https://audon.ai/glossary/overlapping-tools) People paying for two tools that do the same job: keep the one they use. 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 on-demand charges count as Cursor spend. Requests included in the plan cost nothing extra. - Requests made with your team’s own OpenAI or Anthropic key are counted once, under that provider. - Seat fees aren’t in Cursor’s API: add your plan under Settings → Subscriptions. ## Questions about Cursor. **What does Audon need to connect Cursor?** Team Admin API key. cursor.com/dashboard → API Keys → New API Key with admin access. Only team admins can create one, on Cursor team plans that include the Admin API (Enterprise). **What does Audon read from Cursor?** On-demand (usage-based) charges per person and model, Which requests used your own OpenAI or Anthropic key and Team members and their spend this billing cycle. **Does Audon read prompts, responses or code?** No. Audon doesn’t read: code, prompts or responses, seat fees (add them under Subscriptions) and billing details or invoices. **Which savings levers use Cursor data?** Right plan per person, coding model mix, cursor Max mode and overlapping tools. Each is sized on your own data with one stated assumption, and comes with the exact fix. **How do I revoke access?** Disconnect in Integrations and the encrypted credential is destroyed immediately. Revoke it at the provider as well, so it stops working there too. Last updated 2 November 2026 ## Other integrations. - [OpenAI Costs and usage by project, model and line item, read with an organization Admin key. What we read](https://audon.ai/integrations/openai) - [Anthropic (Claude API) Cost and usage reports by workspace and model, plus Claude Code per person, with one Admin key. What we read](https://audon.ai/integrations/anthropic) - [Claude EnterpriseNew Per-person activity, idle seats, and daily cost and tokens by product and model. What we read](https://audon.ai/integrations/claude-enterprise) - [Claude CodeNew Tokens and cost per person and model, from the Admin report or Claude Code’s own telemetry. What we read](https://audon.ai/integrations/claude-code) - [CodexNew Tokens per day and model from Codex’s own OpenTelemetry export, with no key stored. What we read](https://audon.ai/integrations/codex) - [xAINew Daily team spend by model and endpoint, read with a team-scoped management key. What we read](https://audon.ai/integrations/xai) - [DevinNew Daily ACUs by product and per person, priced with your own price per ACU. What we read](https://audon.ai/integrations/devin) ## Smaller AI bills. Same results, proven. [Start free auditFree](https://audon.ai/sign-up?intent=spend) [See a sample report](https://audon.ai/sample-report)