AI is cheap to start with and expensive to scale. The gap between a hobby project and a real bill is enormous, and most of it is waste: paying frontier prices for trivial jobs, re-sending the same context on every call, renting compute you could own. This series is a running, practical guide to closing that gap. Real numbers, exact settings, honest trade-offs, no hype.
Every instalment stands alone, but together they stack. Pull two or three of these levers at once and a bill that reads like a mortgage payment starts reading like a phone plan.
The series so far
Prompt Caching: the boring trick that cuts your LLM bill by 90%
Stop paying to re-read the same system prompt on every call. Cache the stable prefix and cache reads drop to roughly a tenth of the price. The single highest-return hour on this list.
LLM Routing: stop paying frontier prices for easy questions
Most of your queries are trivial. A router sends the easy majority to a cheap model and only escalates the hard ones, cutting costs 40 to 85% at near-identical quality.
Running Open Models Locally: kill your API bill in 2026
A used graphics card and a quantised open model can replace a chunk of your API spend outright. The real break-even maths, the setup, and where local still loses.
Coming up in the series
The plan from here, roughly in the order they save you the most for the least effort:
- Batch APIs: hand over any job that can wait 24 hours and take 50% off the top, stackable with caching.
- Semantic caching: reuse answers to questions that mean the same thing even when the wording differs, for another 40 to 70% off repetitive traffic.
- The draft-then-refine pattern: let a cheap model write the first pass and reserve the expensive model for the polish, not the whole job.
- Context discipline: the tokens you never send are the cheapest tokens of all. Trimming, summarising and windowing your history.
- Free tiers and open models worth using: a current map of which budget and open-weight models are genuinely good enough to demote your frontier spend.
- Quantisation, properly explained: GGUF, AWQ and GPTQ, and how to fit a serious model on hardware that costs less than a laptop.
- Structured outputs and prompt hygiene: smaller, tighter prompts and typed responses that stop you paying for waffle.
- RAG and embeddings on a budget: retrieval that answers from cheap storage instead of expensive context.
New instalments land regularly. The fastest way to catch each one is the newsletter below.
Did you know: the cheapest possible API call is the one you never make. Caching, batching and routing all exist for the same reason: computers hate doing the same expensive work twice, and so should your invoice.