T
tokmeter.ai
Operate · Last 30 days

Spend dashboard

This is sample data so you can see the shape of the product. Connect a provider below to replace it with your real spend.

SIMULATED DATA
Routing opportunity
$10.5K
/ month potential savings

About 60% of your traffic looks like it qualifies for a mini-tier model (~70% cheaper). That's $125.8K annualized.

See which calls qualify →Read the playbook
You're looking at sample data — not your spend.

Every number, chart, and engineer on this page is simulated so you can preview the dashboard. Connect a provider (read-only) below and we'll replace it with your real numbers within minutes.

Get started in 5 minutes →Connect a read-only key →
MTD spend
14%
$25K
vs $32K budget
Projected EoM
19.4%
$25.8K
22% under
Budget burn
78%
of monthly cap
Top spender
Jordan
Data · $2,562.00
Spend over time
Stacked by tool, last 30 days
Anomalies & opportunities
Worth a look this week
Platform team spend ↑ 187% week-over-week
Driven by a new background-agent workflow running Claude Opus on full repo context.
Recommended: Cap Opus to ≤10% of Platform requests; route to Sonnet.
5 engineers exceeded daily $50 budget on Tuesday
All on Cursor Business with metered overages. Soft cap not enforced.
Recommended: Promote soft cap to hard cap in /guardrails.
OpenAI Batch API unused
Embedding & classification jobs run synchronously. Batch API offers 50% off.
Recommended: Migrate eligible jobs in /optimize.
By tool
Cursor$7,989.00
Claude Code$6,990.00
Copilot$3,496.00
Anthropic API$2,996.00
By team
Click a bar to filter the table below
By workflow
Multi-file code-gen$8,488.00
Chat Q&A$5,242.00
Inline completion$3,994.00
Agentic loops$4,494.00
Code review$1,747.00
Docs & explanations$999.00
By model
Where token spend lands across providers
Top 10 spenders
Engineers ranked by 30-day cost
#
1Jordan SilvaClaude Code
42.3M
$2,562.00
2Chris ChenChatGPT
38.5M
$2,331.00
3Jordan RossiAnthropic API
34.7M
$2,101.00
4Wes TanakaClaude Code
31.6M
$1,917.00
5Alex RossiOpenAI API
30M
$1,819.00
6Priya CohenCursor
27.9M
$1,688.00
7Priya ChenChatGPT
23.4M
$1,416.00
8Wes ChenClaude Code
21.9M
$1,327.00
9Kai SinghCursor
18.5M
$1,124.00
10Iris TanakaChatGPT
14.3M
$867.00
Replace the sample data

Get your real spend in 5 minutes

Read-only connection. We never see prompts, completions, or your provider keys in plaintext. Pick one provider to start — you can add the rest later.

  1. 1
    Create a read-only key at your provider
    30 sec

    OpenAI → Admin keys (read-only). Anthropic → Org admin → Usage API key. Azure / Bedrock / Vertex use billing exports — pick whichever provider you spend the most on first.

  2. 2
    Paste it into Settings → Providers
    1 min

    Keys are encrypted at rest with per-org envelope encryption. We only call billing & usage endpoints — never the chat/completions endpoints.

    Open connect wizard →
  3. 3
    We backfill the last 30 days
    2 min

    First sync pulls historical usage so this dashboard fills in immediately. Recurring syncs run every 15 minutes after that.

  4. 4
    Set a monthly budget & alert
    1 min

    Pick a soft cap (warn) and a hard cap (block). We notify the owner before you blow through it.

    Set a budget →
  5. 5
    Invite your team
    30 sec

    Add finance + eng leads as viewers. Engineers get attribution; finance gets the chargeback view.

    Invite teammates →
Total time: ~5 minutes. No code change. No proxy. No engineering ticket.
Start now — connect a provider