AI and ML
Token consumption doesn't tell the whole tale but it shouldn't be ignored
Claude looks substantially more token-hungry than OpenAI's GPT-5.x, thanks to the new tokenizer that Anthropic shipped with recent releases.Large language models (LLMs) use tokenizers to handle the mapping of text into tokens. There's no set definition of a token, but they're typically a set of three or four characters that are mapped to the integers LLMs actually process. Tokens have become the basic economic unit for billing use of AI models. Because the slicing of words into tokens and the tokens required per task vary across models, it has become rather difficult to predict the final bill for playing the AI slot machine.
Recent changes to Anthropic's tokenizer appear to have further complicated matters by making the same content more costly to process on certain models.
Playcode, an AI app building platform, recently analyzed the impact of Anthropic's latest tokenizer and found that the same TypeScript file processed by Claude can consume up to 73 percent more tokens than OpenAI's GPT-5.x model family.Anthropic acknowledges its new tokenizer – announced at the end of June when Sonnet 5 shipped – may generate more tokens for the same input than prior versions."Sonnet 5 is an upgrade to Sonnet 4.6, but it uses an updated tokenizer that changes how the model processes text to improve performance (this is similar to the tokenizer change we introduced with Claude Opus 4.7)," the company explained. "The tradeoff is that the same input can map to more tokens: roughly 1.0–1.35× depending on the content type."
