modelux
$ modelux roi --interactive

Cut 20–50% of your LLM spend without changing your app code.

Modelux routes simple requests to cheaper models, keeps complex requests on premium ones, and shows you the savings before you switch. Start with the typical-team defaults below, then tune the sliders to match your stack.

baseline

Your current LLM bill across OpenAI, Anthropic, Google, and others.

$10,000 / month
$100 $1k $10k $100k $1M+
assumption

Most teams land between 40–80%. Think summarization, classification, formatting, and many retrieval-heavy calls.

60 %
0% 50% 100%
advanced — average savings on each downgraded request

Default: 80%. This assumes a meaningful gap between expensive frontier models and cheaper alternatives like GPT-4o-mini, Claude Haiku, or Gemini Flash. Adjust it if your provider mix is tighter.

80 % cheaper per downgraded request
Estimated cash you keep each month
$4,601 / month
24.1× return on the Team plan after routing savings
Spend removed
$4,800 / mo
from routing simpler work to cheaper models
Modelux cost
$199 / mo
Team tier
Annual cash kept
$55,212 / yr
net of plan cost
Estimated new spend
$5,399 / mo
providers + modelux
What changes
What you pay now $10,000
After routing + modelux $5,399
$ get the business-case PDF

Email yourself a one-page savings summary you can forward to your manager, finance lead, or buyer. Optionally CC them directly now.

Typical payback
First week, not first quarter
Setup risk
Keep your existing providers and SDK flow
Best case
You keep thousands more each month
Worst case
You learn your routing is already efficient
Typical team scenario

A team spending $10,000/mo on LLMs usually has 40–60% of traffic that can move to cheaper models without hurting quality. That alone can create a clear monthly savings story.

How to use this

Adjust only three inputs: what you spend now, how much traffic could downgrade, and how much cheaper those downgraded calls are. The result is the money you keep after Modelux cost.

methodology: Net savings = (monthly spend × downgrade % × per-request cost reduction) − modelux plan cost. Plan is auto-selected from your spend band. Real savings depend on prompt mix, model quality requirements, and provider pricing, so this is best used as a conservative estimate for an internal buying conversation. We do not store the inputs.

If the savings are real, the next step should be easy.

Keep your provider relationships, keep your existing app flow, and validate the routing policy on real traffic before you commit.

Start validating savings