FREE WHAT-IF SIMULATOR · NO SIGN-UP

See the impact before you make the call.

Six FinOps decision types, one simulator. Edit the inputs → live decision cards rank by impact, risk and reversibility. The math is shown — nothing hidden.

If you take all good moves

+$24K/mo

≈ +$288K/yr

Scenarios simulated

Top recommendation

Swap `summarise` from gpt-5.2 → claude-haiku-4.5

Saves identified

4/4

Scenarios

Edit any field — math recomputes in 350ms.

Swap LLM model

feature slug

monthly calls

current avg cost per call usd

current model

target model

Increase SP/RI coverage

monthly compute spend usd

current coverage pct

target coverage pct

provider

term

Add caching layer

feature slug

current monthly cost usd

cache hit rate pct

Rightsize K8s namespace

cluster id

namespace

current monthly cost usd

rightsize savings pct

Add a scenario

Decision cards · ranked

TOP MOVE

Swap `summarise` from gpt-5.2 → claude-haiku-4.5

High value · low risk

Monthly impact

-$12K/mo

Annual impact

-$148K/yr

low risk·instant rollback·~1h work·next inference call

Saves $12,369/mo ($148,428/yr). Reversible in seconds — flip the model name and roll back if quality drops.

Side effects

· Latency: ~faster (relative 0.18x vs gpt-5.2 baseline)

· Quality: minor quality regression on long-context tasks

Raise AWS 1y coverage 38.9% → 65.0%

High value · low risk

Monthly impact

-$8K/mo

Annual impact

-$99K/yr

low risk·rollback in weeks·~2h work·next billing cycle

Saves ~$99,096/yr in exchange for a $353,916/yr commitment. 28.0% AWS 1Y discount applied to the delta.

Side effects

· Locks in $353,916/yr of additional commitment

· Workload-shift risk: paying for unused capacity if usage drops

Rightsize `data-staging` on cluster `prod-eks` (-35%)

Solid save

Monthly impact

-$2K/mo

Annual impact

-$29K/yr

medium risk·instant rollback·~4h work·next deploy (~hours)

Trims 35% off `data-staging` = ~$2,450/mo ($29,400/yr). Watch p95 latency for 48h post-deploy.

Side effects

· Risk of CPU throttling if requests are aggressive

· Reversible — bump requests back up via kubectl apply

Add caching layer to `search` (hit rate 70%)

Marginal

Monthly impact

-$930/mo

Annual impact

-$11K/yr

low risk·rollback in days·~8h work·1-2 days post-deploy

Cache deflects 70% of inference calls → saves ~$1,030/mo net of infra ($930/mo).

Side effects

· Cache hits skip the LLM = faster (-200ms typical)

· Stale-data risk for queries that need fresh context

· Cache infra cost ~$100/mo (Redis/Memcached)

Run this against your real numbers

Decision Simulator FAQ

Still have questions? Email hello@cartieai.com — replies within 4 business hours.

See full FAQ

Decision cards · ranked

Run this against your real numbers

Decision Simulator FAQ

Install CARTIE AI