Usar a API countTokens

import vertexai
from vertexai.generative_models import GenerativeModel

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = "Why is the sky blue?"
# Prompt tokens count
response = model.count_tokens(prompt)
print(f"Prompt Token Count: {response.total_tokens}")
print(f"Prompt Character Count: {response.total_billable_characters}")

# Send text to Gemini
response = model.generate_content(prompt)

# Response tokens count
usage_metadata = response.usage_metadata
print(f"Prompt Token Count: {usage_metadata.prompt_token_count}")
print(f"Candidates Token Count: {usage_metadata.candidates_token_count}")
print(f"Total Token Count: {usage_metadata.total_token_count}")
# Example response:
# Prompt Token Count: 6
# Prompt Character Count: 16
# Prompt Token Count: 6
# Candidates Token Count: 315
# Total Token Count: 321

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.CountTokensResponse;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import java.io.IOException;

public class GetTokenCount {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    getTokenCount(projectId, location, modelName);
  }

  // Gets the number of tokens for the prompt and the model's response.
  public static int getTokenCount(String projectId, String location, String modelName)
      throws IOException {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);

      String textPrompt = "Why is the sky blue?";
      CountTokensResponse response = model.countTokens(textPrompt);

      int promptTokenCount = response.getTotalTokens();
      int promptCharCount = response.getTotalBillableCharacters();

      System.out.println("Prompt token Count: " + promptTokenCount);
      System.out.println("Prompt billable character count: " + promptCharCount);

      GenerateContentResponse contentResponse = model.generateContent(textPrompt);

      int tokenCount = contentResponse.getUsageMetadata().getPromptTokenCount();
      int candidateTokenCount = contentResponse.getUsageMetadata().getCandidatesTokenCount();
      int totalTokenCount = contentResponse.getUsageMetadata().getTotalTokenCount();

      System.out.println("Prompt token Count: " + tokenCount);
      System.out.println("Candidate Token Count: " + candidateTokenCount);
      System.out.println("Total token Count: " + totalTokenCount);

      return promptTokenCount;
    }
  }
}

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class GetTokenCount
{
    public async Task<int> CountTokens(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001"
    )
    {
        var client = new LlmUtilityServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        var request = new CountTokensRequest
        {
            Endpoint = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts = { new Part { Text = "Why is the sky blue?" } }
                }
            }
        };

        var response = await client.CountTokensAsync(request);
        int tokenCount = response.TotalTokens;
        Console.WriteLine($"There are {tokenCount} tokens in the prompt.");
        return tokenCount;
    }
}

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function countTokens(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeModel = vertexAI.getGenerativeModel({
    model: model,
  });

  const req = {
    contents: [{role: 'user', parts: [{text: 'How are you doing today?'}]}],
  };

  // Prompt tokens count
  const countTokensResp = await generativeModel.countTokens(req);
  console.log('Prompt tokens count: ', countTokensResp);

  // Send text to gemini
  const result = await generativeModel.generateContent(req);

  // Response tokens count
  const usageMetadata = result.response.usageMetadata;
  console.log('Response tokens count: ', usageMetadata);
}

import (
	"context"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

// countTokens returns the number of tokens for this prompt.
func countTokens(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()
	prompt := genai.Text("Why is the sky blue?")

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	resp, err := model.CountTokens(ctx, prompt)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "Number of tokens for the prompt: %d\n", resp.TotalTokens)

	resp2, err := model.GenerateContent(ctx, prompt)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Number of tokens for the prompt: %d\n", resp2.UsageMetadata.PromptTokenCount)
	fmt.Fprintf(w, "Number of tokens for the candidates: %d\n", resp2.UsageMetadata.CandidatesTokenCount)
	fmt.Fprintf(w, "Total number of tokens: %d\n", resp2.UsageMetadata.TotalTokenCount)

	return nil
}