Token Intelligence
See what your team's AI
actually costs.
Every token, every model, every tool — read from the usage Claude Code and Codex already record, with no proxy between your tools and the model. Forge turns that raw usage into weighted spend you can compare across tools, attribute to workflows and work items, and trim where it's running hot.
Provider-neutral
Weighted reference tokens put flat-rate plans and per-token API teams on one comparable axis — the same headline for everyone.
Cross-tool
Claude, Codex, and Cursor in a single view, normalized by model — capable tiers where it counts, pennies for the rest.
Attributable
Spend by workflow and by work item, with a cost-per-minute read that surfaces intensity raw totals hide.
Example dashboard with sample data.
Token Intelligence
Premium
Live
Covers only sessions run through Forge workflows — both linked to a work item and unlinked. AI activity outside Forge isn't measured here.
Estimated weighted tokens
167M
—
Estimated cost
$502
—
AI Spend Trend
167M total · 24M/day avgMonTueWedThuFriSatSun
Token Composition
29.3× cache reuseFresh input
1.9M<1%
Cache reads
521M96%
Cache writes
18M3%
Output
2.9M<1%
By AI Tool & Model
| Tool | % | Weighted | Cost | Sessions |
|---|---|---|---|---|
| Claude | 96% | 161M | $483 | 12 |
| Codex | 4% | 6.2M | $18.64 | 7 |
| Model | % | Weighted | Cost | Sessions |
|---|---|---|---|---|
| claude-opus-4-8 | 95% | 159M | $478 | 12 |
| gpt-5.5 | 4% | 6.2M | $18.58 | 7 |
| claude-sonnet-4-6 | <1% | 1.0M | $3.12 | 2 |
| claude-haiku-4-5-20251001 | <1% | 573K | $1.72 | 4 |
| gpt-5.4 | <1% | 14K | $0.04 | 2 |
| gpt-5.4-mini | <1% | 6.0K | $0.02 | 1 |
Tip: Your ad-hoc prompts ran about 1.8× the per-session cost of Forge workflows this period — an estimated $110 you could trim by routing that work through a workflow. See the Ad-hoc row below.
By Workflow
| Workflow | % | Weighted | Cost | Cost / min |
|---|---|---|---|---|
| Implement a Feature | 24% | 40M | $119 | $0.86 |
| Product Discovery | 13% | 22M | $64.83 | $1.66 |
| Fix a Bug | 7% | 11M | $34.34 | $0.65 |
| Update Work Item | 3% | 4.9M | $14.59 | $0.63 |
| Explore Architecture | 1% | 1.9M | $5.72 | $0.14 |
| Review a Pull Request | <1% | 1.4M | $4.24 | $0.28 |
| Check Work Item Status | <1% | 1.2M | $3.54 | $0.15 |
| Create UI Mockups | <1% | 372K | $1.12 | $0.22 |
| Ad-hoc | 51% | 85M | $254 | $0.54 |
Top work items by AI spend
| Work item | Title | AI spend | AI time | Cost / min | Tools | |
|---|---|---|---|---|---|---|
| ENG-412 | User onboarding flow redesign | $12642M weighted | 2h 41m | $0.78 | ||
| Jun 11, 10:34 PM | $5.721.9M weighted | 16m | $0.35 | |||
| Jun 11, 11:36 PM | $2.50833K weighted | 7m | $0.34 | |||
| Jun 13, 11:10 PM | $10435M weighted | 1h 14m | $1.40 | |||
| Jun 14, 01:15 PM | $13.024.3M weighted | 2m | $6.37 | |||
|
Fresh input 817K
Cache reads 137M
Cache writes 4.4M
Output 660K
Cache reuse31.3×
+1h of this item's time — spend booked under other items |
||||||
| ENG-401 | Cross-tool token pricing | $34.3411M weighted | 53m | $0.65 | ||
| ENG-388 | Self-serve billing & plan management | $15.045.0M weighted | 55m | $0.27 | ||
| ENG-339 | API rate limiting & throttling | $9.393.1M weighted | 21m | $0.43 | ||
| ENG-318 | Audit log export to CSV | $2.14712K weighted | 6m | $0.32 | ||
| ENG-356 | Refactor notification service | $1.40468K weighted | 10m | $0.13 | ||
Forge meters every token across the AI tools you already use — read from the usage Claude Code and Codex already record, with no proxy between your tools and the model.