97% AI capacity remaining
Usage velocity -6%
Premium model usage spike: o1-2024-12-17
AI capacity
On pace
$136
of $5,000 MTD
Usage velocity
On pace
-6%
7-day burn vs prior 7
Projected usage
On pace
$2036
projected month-end
Total spend
$2213.26
+18.2%vs prev period
Total tokens
423.73M
+13.1%vs prev period
Active days
30
$73.78 avg/day
Daily spend
Limshift Insights
3 findings on your simulated workloadsSHIFT
Coming v0.2
est. savings
$188/mo
Shift 42% of gpt-4o workloads to gpt-4o-mini
Token-size analysis suggests a meaningful share of gpt-4o-2024-08-06 calls are simple completions that gpt-4o-mini handles within a 0.5% quality delta — intelligent routing reclaims the difference.
Available when this module ships
HISTORY
Coming v0.3
est. savings
$44/mo
claude-opus-4-7 in wrkspc_main: rising usage overhead
Long-running workflows are re-processing ~28% of historical payload per turn. HISTORY reduces the repeated processing while preserving workflow continuity — about 18% of usage on this workload is recoverable.
Available when this module ships
SHIFT
Coming v0.2
est. savings
$76/mo
Premium model usage spike on o1 in proj_Research
A reasoning-tier model is being used for prompts that fail validation 23% of the time, doubling effective usage. Intelligent routing sends validation-prone prompts through a guardrail first and reserves premium tiers for what needs them.
Available when this module ships
Breakdowns · click any row to drill in
By provider
By model