# LLM cost reduction program

Portfolio of client platforms across the advisory engagements.

Cost optimization program · FinOps.

The $200K/year figure is aggregate cloud and LLM spend reduction across advisory engagements. It is not the result of a single sprint, a promised saving, or a measured percentage applicable to every workload.

## Problem

The same integration mistakes repeated across client codebases: context re-injected without caching, token-heavy integrations, and infrastructure patterns that multiplied spend.

## What shipped

- Refactored Anthropic SDK, n8n, and Copilot Studio integrations around token optimization, prompt caching, and low-infrastructure patterns.

## Reported outcomes

- $200K/yr aggregate reduction in cloud and LLM spend across the portfolio.

Anonymized client work, reported by Nick Cerutti. Client identities and raw operational records are not published.

## What to check in your system

The common pattern was integration overhead: repeated context and token-heavy execution paths. The work focused on those paths and their infrastructure requirements. Estimating a new project's savings still requires its traffic mix, model prices and quality constraints.

- How much repeated context is sent on each request?
- Which tasks require the current model and which have alternatives?
- How will you check quality and latency alongside a lower bill?

Stack: Anthropic SDK, n8n, Copilot Studio, AWS Bedrock

[Related engagement](https://nickcerutti.com/services/llm-cost-sprint) · [Free tool](https://nickcerutti.com/tools/llm-routing-estimator)

Canonical page: https://nickcerutti.com/work/cost-program