Tokens and words
How many characters make a token depends on the model and the language. Anthropic's glossary gives about 3.5 English characters per token for its earlier models, and says its newer tokenizer (Claude 4.7 and later) produces about 30% more tokens for the same text. For exact numbers, providers offer token counting for the model you use.
Why you meet them
- Limits: the context window is a number of tokens.
- Prices: API usage is billed per input and output token.
- Speed: longer outputs mean more tokens to generate.