estimateTokens method

  1. @override
int estimateTokens(
  1. String text
)

Estimates the number of tokens in the given text.

This is an approximation — different providers tokenize differently. Default implementation uses a rough ~kApproxCharsPerToken chars per token estimate.

Implementation

@override
int estimateTokens(String text) {
  // GPT models average ~4 characters per token
  return (text.length / 4).ceil();
}