Sam Whitaker
Developer & API Cost Writer
Indie developer who reads the API docs before opening the UI and scripts every test he runs more than twice. Tracks cost-per-call and rate limits the way accountants track invoices.
Beat: Local AI · AI Video
- Video & AI APIs, SDKs
- Cost-per-call & rate-limit analysis
- Batch pipeline scripting
- Build-vs-subscribe decisions
How Sam tests
I read the API docs before the landing page, then script the smallest test that proves or breaks the claim. Prices get quoted from invoices, not pricing pages.
Latest from Sam
GuidesAI Tool Reviews: How to Tell Who Paid for the Ranking
Most 'best AI video editor' lists are written by a company on the list. Here is a two-minute check that tells you who paid, plus what the law requires.
GuidesHow to Test Whisper Accuracy on Your Own Audio
Stop borrowing WER numbers from LibriSpeech. A 90-minute protocol to build a test set, score it with jiwer, catch hallucinations, and model local-vs-API cost.
GuidesFree Unlimited AI Video and Voice: The Math Says No
Every 'free unlimited' AI video, TTS and voice cloning page fails the same arithmetic test. Here is the per-second math, and where unlimited is real.
GuidesCloud GPU Pricing: When Renting Beats Buying a Card
H100s span $1.49 to $6.98 an hour across providers. Here's the break-even maths against buying, and the billing details that decide your real bill.
GuidesLuma Ray API Pricing: What a Real Video Batch Actually Costs
Luma's per-second pricing scales with resolution and dynamic range: numbers the landing page buries. We price a real batch and check the rate limits that bite.
GuidesLocal LLMs for Coding: What Actually Works (2026)
Which local coding models are real vs toys, wiring Ollama's OpenAI API into your editor, real latency numbers, and the privacy case for client code.