Spending sensibly
-
Summarising Long PDFs on a Small Budget
A practical walkthrough for extracting PDF text, testing a low-cost workflow, and building a checked summary without repeated full-document requests.
-
Hidden Image and File Costs: A Spending Walkthrough
Follow a practical walkthrough to uncover image and file input costs, trim unnecessary content, and measure spending before scaling.
-
Keep Your Side Project Under a Coffee a Day
A practical walkthrough for setting limits, choosing models, tracking usage, and keeping AI spending predictable with MyRelay.
-
When an AI Pass Beats Paying Per Token
A step-by-step way to compare an AI pass with token billing before you spend more than planned.
-
Understanding a Pass Multiplier on Your Monthly Quota
A practical walkthrough for estimating how a pass multiplier affects your monthly AI budget and planning usage calmly.
-
Track Project Spend with Separate API Keys
A practical way to separate AI spending by project, set limits, and review costs before a small budget becomes a surprise.
-
Cheap First, Expensive Second: A Model Cascade
Build a model cascade that handles routine requests cheaply and escalates difficult work while keeping quality and total spending visible.
-
How to Plan Around Weekly Pass Caps
A practical walkthrough for managing weekly passes, choosing models, and keeping AI spending predictable with MyRelay.
-
How a Small Overdraft Floor Limits Surprise Bills
A practical walkthrough of using a small negative-balance limit, request costs, and a personal budget to keep AI spending predictable.
-
The Real Cost of Long Chat Histories
A practical walkthrough for understanding, measuring, and controlling the cost of long AI chat histories.
-
How Cache Reads Are Billed and Why They Are Cheap
Follow a request from prompt to bill, learn why cached input costs less, and check whether caching is reducing your API spending.