Anthropic's extravagant tokenizer complicates AI pricing
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 ...
Copyright of this story solely belongs to theregister.com. To see the full text click HERE
