--- title: "Claude Code cost tracking per person and model · Audon" description: "What Claude Code costs per person and model: from your Anthropic Admin key, or on Pro and Max plans from Claude Code’s own OpenTelemetry export." url: https://audon.ai/integrations/claude-code last_updated: 2026-11-02 --- # Claude Code cost tracking per person and model. There are two ways in. On the Claude API, the Anthropic Admin key already includes Claude Code usage per person and model. On Claude Pro or Max, Claude Code sends its own OpenTelemetry metrics to Audon with an ingest token, so no Anthropic key is stored. [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 - Tokens per person, day and model (input, output, cache reads and writes) - Claude Code’s own cost estimate per model, stored as an API-equivalent estimate (not billed spend) - Sessions and active time Never reads - Prompts, responses, code or tool input - Billed spend or the plan fee (add the plan under Subscriptions) - Usage from before the setup ## The key to create. Used read-only, encrypted, never shown again. **Credential** No provider key. Claude Code sends its own OpenTelemetry metrics to Audon with an Audon ingest token (aud_otlp_…). **Where to create it** For Claude Pro or Max (and Claude Code on any plan). Create the connection with connection_create_otlp (tool "claude_code"), then put the returned env block in ~/.claude/settings.json and restart Claude Code. Usage arrives about once a minute while Claude Code runs. **Provider documentation** [code.claude.com/docs/en/monitoring-usage](https://code.claude.com/docs/en/monitoring-usage) **Step by step** [Provider setup in the docs](https://audon.ai/docs/integrations#claude-code) ## Savings levers on Claude Code 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. 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. - The cost Claude Code reports on personal plans is an API-equivalent estimate, not what the plan bills, and is shown as such. - Each person, day and model is counted once: the Admin report wins over the telemetry export. - Usage from before the setup isn’t included. Add the plan fee under Settings → Subscriptions. ## Questions about Claude Code. **What does Audon need to connect Claude Code?** No provider key. Claude Code sends its own OpenTelemetry metrics to Audon with an Audon ingest token (aud_otlp_…).. For Claude Pro or Max (and Claude Code on any plan). Create the connection with connection_create_otlp (tool "claude_code"), then put the returned env block in ~/.claude/settings.json and restart Claude Code. Usage arrives about once a minute while Claude Code runs. **What does Audon read from Claude Code?** Tokens per person, day and model (input, output, cache reads and writes), Claude Code’s own cost estimate per model, stored as an API-equivalent estimate (not billed spend) and Sessions and active time. **Does Audon read prompts, responses or code?** No. Audon doesn’t read: prompts, responses, code or tool input, billed spend or the plan fee (add the plan under Subscriptions) and usage from before the setup. **Which savings levers use Claude Code data?** Right plan per person and coding model mix. Each is sized on your own data with one stated assumption, and comes with the exact fix. **How do I stop it?** Disconnect in Integrations: the ingest token stops working at once. Remove the telemetry settings from the tool as well, so it stops sending. 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) - [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) - [CursorNew Members, usage per person and model and on-demand spend, or the usage export on individual plans. What we read](https://audon.ai/integrations/cursor) - [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)