AI Waste Report
Day 21 of 31 · 6 workflows across OpenAI, Anthropic and Google
Spend to date
$1,384
Forecast this month
$2,043
Estimated monthly waste
$695
34% of spend · recoverable
AI Waste Score
61/100D
Lower is better
Top 3 ways to recover $377/mo
$175/mo
Constrain output length in "Code review bot"
Average output is 2,600 tokens where ~1,900 would satisfy the task. Add an explicit output contract (max length / JSON schema) to cut the excess.
$101/mo
Cache the repeated context in "Code review bot"
~2,500 tokens of identical system prompt / instructions are re-sent on every one of 3,200 calls. Split stable from volatile context and enable Anthropic prompt caching to pay ~10% for the repeated part.
$101/mo
Route "Support ticket triage" from GPT-5 to GPT-5 mini
This is a low-risk, high-volume task on a frontier model. Move ~80% of calls to GPT-5 mini and keep GPT-5 as a fallback for the hardest cases.
Spend by workflow
Spend by model
Spend by provider
All 15 findings
| Recommendation | Type | Difficulty | Savings / mo |
|---|---|---|---|
| Constrain output length in "Code review bot" | Output length | easy | $175 |
| Cache the repeated context in "Code review bot" | Caching | medium | $101 |
| Route "Support ticket triage" from GPT-5 to GPT-5 mini | Model routing | easy | $101 |
| Constrain output length in "Support ticket triage" | Output length | easy | $58 |
| Constrain output length in "Docs Q&A (RAG)" | Output length | easy | $56 |
| Cache the repeated context in "Support ticket triage" | Caching | medium | $44 |
| Cache the repeated context in "Docs Q&A (RAG)" | Caching | medium | $35 |
| Constrain output length in "Invoice data extraction" | Output length | easy | $28 |
| Cut the 14% retry rate in "Invoice data extraction" | Retries | medium | $25 |
| Constrain output length in "Internal agent experiments" | Output length | easy | $20 |
| Cache the repeated context in "Invoice data extraction" | Caching | medium | $18 |
| Route "Marketing copy generation" from GPT-5 to GPT-5 mini | Model routing | easy | $12 |
| Constrain output length in "Marketing copy generation" | Output length | easy | $10 |
| Cut the 12% retry rate in "Internal agent experiments" | Retries | medium | $9 |
| Cache the repeated context in "Internal agent experiments" | Caching | medium | $4 |
This is sample data. See it for your own spend.
Paste or upload a month of usage and get this report for your real workflows in under a minute.
Prices illustrative. Never paste API keys — this report needs usage numbers, not secrets.