This is a real 30-day Anthropic workload (Claude Code + SDK), semi-anonymized — totals rounded, customer IDs stripped. Connect your own API key to see your numbers in the same shape.

Dashboard

Sample AI spending overview — 30-day window

Total Spend (30D)
$5,060.00

+100.0% vs last period

Total Requests
61,610

Across 2 providers

Top Provider
Anthropic

$4655.20 (92%)

Month Forecast
$7,250.27

Trend: rising ↑

Daily Spend
Usage by Model
Provider
claude-sonnet-4-5Anthropic14.8K$2700.02
53.36%
claude-opus-4-7Anthropic1.2K$1443.11
28.52%
claude-haiku-4-5Anthropic38.1K$512.07
10.12%
gpt-4oOpenAI980$283.36
5.6%
gpt-4o-miniOpenAI6.4K$121.44
2.4%
Savings Opportunity
Optimization
Currentclaude-opus-4-7
Suggestedclaude-sonnet-4-5
Estimated Savings$338/mo
30% OFF

A meaningful slice of Opus traffic looks like routine classification and short-form generation — exactly the workload Sonnet 4.5 handles at ~3.3x lower cost with no measurable quality drop on this owner's benchmark set.

You have 1 more suggestions. Upgrade to Pro to see all optimization opportunities.

Unlock All Suggestions
What you're looking at

30 days of Anthropic-heavy spend with an OpenAI sliver.

Daily chart, model breakdown, and optimization suggestion are the same components the dashboard renders for paying users.

Start Free