# GPT-2/GPT-4 Byte-Level BPE + tiktoken Regex: Anatomy of the Modern Standard

> Source: https://sukruyusufkaya.com/en/learn/llm-muhendisligi/gpt-byte-level-bpe-tiktoken-regex
> Updated: 2026-05-13T13:00:26.435Z
> Category: LLM Mühendisliği
> Module: Module 6: Tokenization Microsurgery
**TLDR:** Birth of GPT-2 byte-level BPE (Radford 2019), the secret of the regex pre-tokenizer, GPT-3.5 cl100k, GPT-4o o200k, Llama-3's return to tiktoken. tiktoken Rust performance, token counting for prompt engineering, Turkish cost economics, comparison of encoding regimes.