Includes CLI and Cowork (desktop) sessions across every machine
Daily Cost
CLICowork
Token Composition
Daily Tokens (Stacked)
Cache Hit Ratio per Day
Cost by Model
Cost: CLI vs Cowork
Cost by Model & Pricing Tier all-time, this machine
Standard = current API pricing (what you were billed). Batch = same workload via Batch API (50% off all token types, 24h async SLA, not used by Claude Code).
Prompt-caching savings are already baked into Standard — see "Caching saved" column.
This card is a lifetime pricing comparison and does not react to the Date / Machine / Project filters.
Model
Input
Output
Cache Write
Cache Read
Standard $
Batch (50% off) $
No-Cache Hypothetical $
Caching Saved
Cost by Model — Pricing Tier Comparison all-time
Caching Savings vs No-Cache all-time
Sessions
Session
Source
Models
Total Tokens
Hit Ratio
Cost
Daily Breakdown
Date
Models
Input
Output
Cache Create
Cache Read
Total Tokens
Hit Ratio
Cost
Loading…
Headline Insights
Conversations — Context Spend
Each row is one Claude Code session (sessionId). Avg context approximates the running prompt size by summing input + cache_read tokens, divided by turns.
Long conversations with low cache hit ratios are usually the ones burning the most context.
Project / Session
Source
Turns
Total Tokens
Avg Context / Turn
Cache Hit
Duration
Cost
Duration is wall-clock time between first and last assistant message. Long durations on few-turn sessions usually mean the session was left open idle.
Trends Over Time — Where Attribution Is Shifting
Daily attribution mix. Stacked bars show cost composition per day across each dimension. Hover for exact values.
Days where you didn't run Claude show as gaps. Earliest data: starts of your usage history; we only see local + cowork from this machine.
Cost by Project
CLI vs Cowork by Project
Per-Project Detail
Project (cwd)
Cost
CLI / Cowork
Tokens
Cache Hit
Turns
Top Tools
Cache hit ratio = cache_read / (cache_read + cache_create). Low ratios suggest workflows that fetch fresh data each time — optimization targets. Top 10 by cost shown by default; toggle "show all" to expand.
Tool Cost Breakdown
Cost by Category
All Tools — Approximate Cost Attribution
Cost per turn is split evenly across tools used in that turn (rough proxy — a turn with 3 tools attributes 1/3 to each). Top 15 by cost shown by default.
Tool
Category
Invocations
Approx Cost
Approx Tokens
% of Total
MCP Servers
Server
Calls
Cost
Share
Top Tools
Subagents by type
No subagent invocations recorded.
Subagents (Agent tool calls with subagent_type) run as separate API conversations. Costs approximate parent-turn attribution; actual subagent compute is included in totals.
Plugins by server
Plugin tools (mcp__plugin_*) aggregated by plugin server. Skills (Skill tool calls) are grouped generically — individual skill names are not tracked.
Cache ROI by Model
What you actually paid (Standard) vs hypothetical cost without prompt caching. Higher % saved = better ROI from cache reuse.
Model
Cache Read Tokens
Cache Write Tokens
Output Tokens
Standard Cost
No-Cache Cost
Saved
% Saved
Source Coverage
Where your data was found. Multi-machine sync (planned Phase 2) will add per-hostname rows here.
Source
Cost
Turns
Tokens (cache reads)
Note
Methodology: Costs computed from raw JSONL using Anthropic published rates (Opus $5/$25, Sonnet $3/$15, Haiku $1/$5 per 1M; cache writes ×1.25, cache reads ×0.10).
Totals on this page may exceed dashboard.html because every assistant turn (including autocompaction summaries and subagent compute) is counted individually here for attribution.
All numbers are API-equivalent value — you actually pay $100/mo flat under Max 5×.