List and count tokens

This guide shows you how to list and count tokens for a prompt using the Google Gen AI SDK, covering the following topics:

What are tokens and why is counting them important?

Generative AI models process prompts by breaking down text and other data into units called tokens. A token can be a word, part of a word, or punctuation. The algorithm that converts text into tokens is called a tokenizer.

Listing and counting tokens is useful for the following reasons:

  • Manage context window: Each model has a maximum number of tokens it can accept in a prompt and generate in a response. Counting tokens helps you stay within this limit.
  • Estimate costs: For text prompts, counting tokens also returns the number of billable characters, which helps you understand and predict costs.
  • Troubleshoot and analyze: Listing tokens shows you exactly how your prompt is tokenized and provides token IDs. This is useful for troubleshooting unexpected model behavior and for deeper analysis.

Supported models

The following table shows you the models that support token listing and token counting:

Choose a token utility

The Google Gen AI SDK provides two utilities for working with tokens: listing and counting. The following table helps you decide which one to use.

Utility Description Use Case Supported Prompts
List tokens Returns a list of tokens and their associated token IDs. Troubleshooting and analyzing model behavior. Text-only
Count tokens Returns the total token count and the number of billable characters. Checking model input limits and estimating costs. Text and multimodal

Get a list of tokens and token IDs for a prompt

To get a list of tokens and their corresponding IDs for a prompt, use the following code sample. This operation supports only text prompts; multimodal prompts are not supported.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

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-2.5-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'?']
#  )]

Go

Learn how to install or update the Go.

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

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: "user"},
	}

	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
}

Get the token count and billable characters of a prompt

To get the token count and the number of billable characters for a prompt, use the following code sample. This operation supports both text-only and multimodal prompts.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

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-2.5-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

Go

Learn how to install or update the Go.

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

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: "user"},
	}

	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
}