Cost & token monitoring

Cost and token monitoring in Claude Code is the practice of tracking how many tokens your sessions consume and what those tokens cost, so you can manage spend, stay within plan limits, and optimize model selection. Because Claude Code operates as an agentic system that automatically loads files, conversation history, tool definitions, and subagent outputs into the context window on every turn, token counts can grow quickly and silently. Monitoring gives you visibility into that growth before it becomes a surprise on your bill. The feature spans several layers: a built-in `/cost` command in the CLI that shows a session-level estimate, a `/usage` command that adds plan-limit breakdowns for subscribers, the Usage page in Claude Console for authoritative billing data, an Admin API for programmatic org-wide reporting, and OpenTelemetry integration for exporting metrics to external observability stacks. Each layer serves a different audience, from individual developers checking their burn rate mid-session to platform teams building automated cost governance pipelines. Understanding the distinction between the local cost estimate and your actual bill is fundamental. The CLI computes costs locally from token counts using cached pricing tables; the result is an approximation useful for relative comparisons during a session, not a substitute for the Console's authoritative usage data. Subscription users (Pro, Max, Team, Enterprise) see quota utilization rather than dollar amounts, because their plan includes usage rather than billing per token.