הצגת רשימה של טוקנים וספירתם

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.compute_tokens(
    model="gemini-3.5-flash",
    contents="What's the longest word in the English language?",
)

print(response)
# Example output:
# tokens_info=[TokensInfo(
#    role='user',
#    token_ids=[1841, 235303, 235256, 573, 32514, 2204, 575, 573, 4645, 5255, 235336],
#    tokens=[b'What', b"'", b's', b' the', b' longest', b' word', b' in', b' the', b' English', b' language', b'?']
#  )]

import (
	"context"
	"encoding/json"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// computeWithTxt shows how to compute tokens with text input.
func computeWithTxt(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "What's the longest word in the English language?"},
		},
			Role: genai.RoleUser},
	}

	resp, err := client.Models.ComputeTokens(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	type tokenInfoDisplay struct {
		IDs    []int64  `json:"token_ids"`
		Tokens []string `json:"tokens"`
	}
	// See the documentation: https://pkg.go.dev/google.golang.org/genai#ComputeTokensResponse
	for _, instance := range resp.TokensInfo {
		display := tokenInfoDisplay{
			IDs:    instance.TokenIDs,
			Tokens: make([]string, len(instance.Tokens)),
		}
		for i, t := range instance.Tokens {
			display.Tokens[i] = string(t)
		}

		data, err := json.MarshalIndent(display, "", "  ")
		if err != nil {
			return fmt.Errorf("failed to marshal token info: %w", err)
		}
		fmt.Fprintln(w, string(data))
	}

	// Example response:
	// {
	// 	"ids": [
	// 		1841,
	// 		235303,
	// 		235256,
	//    ...
	// 	],
	// 	"values": [
	// 		"What",
	// 		"'",
	// 		"s",
	//    ...
	// 	]
	// }

	return nil
}

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function countTokens(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
    httpOptions: {apiVersion: 'v1'},
  });

  const response = await client.models.computeTokens({
    model: 'gemini-2.5-flash',
    contents: "What's the longest word in the English language?",
  });

  console.log(response);

  return response.tokensInfo;
}

import com.google.genai.Client;
import com.google.genai.types.ComputeTokensResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.TokensInfo;
import java.nio.charset.StandardCharsets;
import java.util.List;
import java.util.Optional;

public class CountTokensComputeWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    computeTokens(modelId);
  }

  // Computes tokens with text input
  public static Optional<List<TokensInfo>> computeTokens(String modelId) {
    // 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 (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      ComputeTokensResponse response = client.models.computeTokens(
              modelId, "What's the longest word in the English language?", null);

      // Print TokensInfo
      response.tokensInfo().ifPresent(tokensInfoList -> {
        for (TokensInfo info : tokensInfoList) {
          info.role().ifPresent(role -> System.out.println("role: " + role));
          info.tokenIds().ifPresent(tokenIds -> System.out.println("tokenIds: " + tokenIds));
          // print tokens input as strings since they are in a form of byte array
          System.out.println("tokens: ");
          info.tokens().ifPresent(tokens ->
              tokens.forEach(token ->
                  System.out.println(new String(token, StandardCharsets.UTF_8))
              )
          );
        }
      });
      // Example response.tokensInfo()
      // role: user
      // tokenIds: [1841, 235303, 235256, 573, 32514, 2204, 575, 573, 4645, 5255, 235336]
      // tokens:
      // What
      // '
      // s
      // the
      return response.tokensInfo();
    }
  }
}

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))

prompt = "Why is the sky blue?"

# Send text to Gemini
response = client.models.generate_content(
    model="gemini-3.5-flash", contents=prompt
)

# Prompt and response tokens count
print(response.usage_metadata)

# Example output:
#  cached_content_token_count=None
#  candidates_token_count=311
#  prompt_token_count=6
#  total_token_count=317

import (
	"context"
	"encoding/json"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateTextAndCount shows how to generate text and obtain token count metadata from the model response.
func generateTextAndCount(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "Why is the sky blue?"},
		},
			Role: genai.RoleUser},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	usage, err := json.MarshalIndent(resp.UsageMetadata, "", "  ")
	if err != nil {
		return fmt.Errorf("failed to convert usage metadata to JSON: %w", err)
	}
	fmt.Fprintln(w, string(usage))

	// Example response:
	// {
	// 	 "candidatesTokenCount": 339,
	// 	 "promptTokenCount": 6,
	// 	 "totalTokenCount": 345
	// }

	return nil
}

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function countTokens(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
    httpOptions: {apiVersion: 'v1'},
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Why is the sky blue?',
  });

  console.log(response.usageMetadata);

  return response.usageMetadata;
}

import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.GenerateContentResponseUsageMetadata;
import com.google.genai.types.HttpOptions;
import java.util.Optional;

public class CountTokensResponseWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    countTokens(modelId);
  }

  // Generates content response usage metadata that contains prompt and response token counts
  public static Optional<GenerateContentResponseUsageMetadata> countTokens(String modelId) {
    // 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 (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentResponse response =
              client.models.generateContent(modelId, "Why is the sky blue?", null);

      response.usageMetadata().ifPresent(System.out::println);
      // Example response:
      // GenerateContentResponseUsageMetadata{cacheTokensDetails=Optional.empty,
      // cachedContentTokenCount=Optional.empty, candidatesTokenCount=Optional[569],
      // candidatesTokensDetails=Optional[[ModalityTokenCount{modality=Optional[TEXT],
      // tokenCount=Optional[569]}]], promptTokenCount=Optional[6],
      // promptTokensDetails=Optional[[ModalityTokenCount{modality=Optional[TEXT],
      // tokenCount=Optional[6]}]], thoughtsTokenCount=Optional[1132],
      // toolUsePromptTokenCount=Optional.empty, toolUsePromptTokensDetails=Optional.empty,
      // totalTokenCount=Optional[1707], trafficType=Optional[ON_DEMAND]}
      return response.usageMetadata();
    }
  }
}

from google.genai.local_tokenizer import LocalTokenizer

tokenizer = LocalTokenizer(model_name="gemini-3.5-flash")
response = tokenizer.count_tokens("What's the highest mountain in Africa?")
print(response)
# Example output:
#   total_tokens=10

from google.genai.local_tokenizer import LocalTokenizer

tokenizer = LocalTokenizer(model_name="gemini-3.5-flash")
response = tokenizer.compute_tokens("What's the longest word in the English language?")
print(response)
# Example output:
# tokens_info=[TokensInfo(
#     role='user',
#     token_ids=[3689, 236789, 236751, 506,
#               27801, 3658, 528, 506, 5422, 5192, 236881],
#     tokens=[b'What', b"'", b's', b' the', b' longest',
#            b' word', b' in', b' the', b' English', b' language', b'?']
#     )]