Useful notes for building with AI.
Model guides, cost comparisons, and plain-English explanations you can put to work immediately.
Built-in guides are active. Connect Sanity to publish from your own editorial workspace.
A beginner-friendly foundation for token counts, context, and cost.
Essential guideHow tokenization worksWhy GPT, Claude, Gemini, code, and multilingual text produce different counts.
Essential guidePrompt caching costsStructure reusable prompt prefixes and measure real cache savings.
Model guides · 7 minClaude Fable 5 token limits, pricing, and context fit
A plain-English guide to planning prompts for Anthropic's newest flagship family.
Read guide →
Comparisons · 9 minKimi K3 vs Claude Sonnet: which prompt costs less?
A practical comparison for long-context chat, RAG, and production assistants.
Read guide →
Token basics · 5 minWhy the same prompt has different token counts
Tokenizers explained without the textbook: vocabulary, chunks, and hidden request overhead.
Read guide →
Registry · 4 minThe 2026 model registry: what changed this month
A living update log for major model families, context windows, and pricing snapshots.
Read guide →
Optimization · 8 minHow to cut your AI bill without making prompts worse
Five practical ways to reduce tokens while keeping the instructions that matter.
Read guide →Token basics · 6 minA beginner's guide to context windows
The difference between tokens, context, output limits, and what actually gets truncated.
Read guide →