Tokens, Models and Prices: What an LLM Call Actually Costs
Tokens are the unit you are billed in, and they are not words. This post covers tokenization, counting before you send, model tiers, and how the costs really add up.
Tech Blog · Insights & Experiments
Deep dives into code, design, and system architecture. From frontend to backend, from performance tricks to developer experience — practical notes for building better technology.
Tokens are the unit you are billed in, and they are not words. This post covers tokenization, counting before you send, model tiers, and how the costs really add up.
Most LangChain tutorials online were written before v1 and no longer run. Here is what moved, what landed in langchain-classic, and how to read old code safely.
LangChain is widely used and widely misunderstood. This post explains the problems it actually solves, where it earns its complexity, and what this series will build.
A Svelte 5 component library built for the month your application stops being simple: seventy-plus components, theming you control, and a data grid and scheduler to match.
A slow query in production is a fire. EXPLAIN plans show exactly where the database wastes time — if you know how to read them. This post teaches you how, with real examples.
Bad schema design creates bugs invisible until production. Learn the relational model from first principles, then normalize to 3NF/BCNF with real examples and trade-offs.
Tokens are the unit you are billed in, and they are not words. This post covers tokenization, counting before you send, model tiers, and how the costs really add up.
Most LangChain tutorials online were written before v1 and no longer run. Here is what moved, what landed in langchain-classic, and how to read old code safely.
LangChain is widely used and widely misunderstood. This post explains the problems it actually solves, where it earns its complexity, and what this series will build.
A Svelte 5 component library built for the month your application stops being simple: seventy-plus components, theming you control, and a data grid and scheduler to match.
Cassandra is built for write-heavy workloads at massive scale — but only if you model data for your queries, not your intuition. This post explains the model and the write path.
Redis is not just a cache. Its five core data structures solve problems that would require complex code otherwise. This post covers all of them plus persistence and Pub/Sub.
Eight posts taking LangChain from first principles to a working RAG pipeline — token costs, the raw OpenAI API, messages, prompt templates, structured output and LCEL.
Master the 6 data structures that appear in 80% of technical interviews. Each post goes deep on one structure — how it works under the hood, every interview pattern it unlocks, and the exact templates that win offers.
Learn how to structure routing, master custom hooks, and optimize React builds using Vite and Webpack for production-grade apps.
Build a rock-solid foundation in HTML, CSS, JavaScript, and modern tooling to prepare for a professional full-stack journey using React, NestJS, and PostgreSQL.
Results