countMessageTokens method

Future<CountMessageTokensResponse> countMessageTokens(
  1. CountMessageTokensRequest request
)

Runs a model's tokenizer on a string and returns the token count.

Throws a http.ClientException if there were problems communicating with the API service. Throws a ServiceException if the API method failed for any reason.

Implementation

Future<CountMessageTokensResponse> countMessageTokens(
  CountMessageTokensRequest request,
) async {
  final url = Uri.https(_host, '/v1beta/${request.model}:countMessageTokens');
  final response = await _client.post(url, body: request);
  return CountMessageTokensResponse.fromJson(response);
}