Use the Count Tokens API

fromgoogleimport genai
fromgoogle.genai.typesimport HttpOptions
client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.count_tokens(
 model="gemini-2.5-flash",
 contents="What's the highest mountain in Africa?",
)
print(response)
# Example output:
# total_tokens=9
# cached_content_token_count=None

import(
	"context"
	"fmt"
	"io"
	genai "google.golang.org/genai"
)
// countWithTxt shows how to count tokens with text input.
func countWithTxt(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 highest mountain in Africa?"},
		}},
	}
	resp, err := client.Models.CountTokens(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}
	fmt.Fprintf(w, "Total: %d\nCached: %d\n", resp.TotalTokens, resp.CachedContentTokenCount)
	// Example response:
	// Total: 9
	// Cached: 0
	return nil
}

const{GoogleGenAI}=require('@google/genai');
constGOOGLE_CLOUD_PROJECT=process.env.GOOGLE_CLOUD_PROJECT;
constGOOGLE_CLOUD_LOCATION=process.env.GOOGLE_CLOUD_LOCATION||'global';
asyncfunctioncountTokens(
projectId=GOOGLE_CLOUD_PROJECT,
location=GOOGLE_CLOUD_LOCATION
){
constclient=newGoogleGenAI({
vertexai:true,
project:projectId,
location:location,
});
constresponse=awaitclient.models.countTokens({
model:'gemini-2.5-flash',
contents:'What is the highest mountain in Africa?',
});
console.log(response);
returnresponse.totalTokens;
}

importcom.google.genai.Client;
importcom.google.genai.types.CountTokensResponse;
importcom.google.genai.types.HttpOptions;
importjava.util.Optional;
public classCountTokensWithText {
 public static void main(String[] args) {
 // TODO(developer): Replace these variables before running the sample.
 String modelId = "gemini-2.5-flash";
 countTokens(modelId);
 }
 // Counts tokens with text input
 public static Optional<Integer> 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()) {
 CountTokensResponse response =
 client.models.countTokens(modelId, "What's the highest mountain in Africa?", null);
 System.out.print(response);
 // Example response:
 // CountTokensResponse{totalTokens=Optional[9], cachedContentTokenCount=Optional.empty}
 return response.totalTokens();
 }
 }
}

fromgoogleimport genai
fromgoogle.genai.typesimport HttpOptions, Part
client = genai.Client(http_options=HttpOptions(api_version="v1"))
contents = [
 Part.from_uri(
 file_uri="gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
 mime_type="video/mp4",
 ),
 "Provide a description of the video.",
]
response = client.models.count_tokens(
 model="gemini-2.5-flash",
 contents=contents,
)
print(response)
# Example output:
# total_tokens=16252 cached_content_token_count=None

import(
	"context"
	"fmt"
	"io"
	genai "google.golang.org/genai"
)
// countWithTxtAndVid shows how to count tokens with text and video inputs.
func countWithTxtAndVid(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: "Provide a description of the video."},
			{FileData: &genai.FileData{
				FileURI: "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
				MIMEType: "video/mp4",
			}},
		},
			Role: "user"},
	}
	resp, err := client.Models.CountTokens(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}
	fmt.Fprintf(w, "Total: %d\nCached: %d\n", resp.TotalTokens, resp.CachedContentTokenCount)
	// Example response:
	// Total: 16252
	// Cached: 0
	return nil
}

const{GoogleGenAI}=require('@google/genai');
constGOOGLE_CLOUD_PROJECT=process.env.GOOGLE_CLOUD_PROJECT;
constGOOGLE_CLOUD_LOCATION=process.env.GOOGLE_CLOUD_LOCATION||'global';
asyncfunctioncountTokens(
projectId=GOOGLE_CLOUD_PROJECT,
location=GOOGLE_CLOUD_LOCATION
){
constclient=newGoogleGenAI({
vertexai:true,
project:projectId,
location:location,
});
constvideo={
fileData:{
fileUri:'gs://cloud-samples-data/generative-ai/video/pixel8.mp4',
mimeType:'video/mp4',
},
};
constresponse=awaitclient.models.countTokens({
model:'gemini-2.5-flash',
contents:[video,'Provide a description of the video.'],
});
console.log(response);
returnresponse.totalTokens;
}

importcom.google.genai.Client;
importcom.google.genai.types.Content;
importcom.google.genai.types.CountTokensResponse;
importcom.google.genai.types.HttpOptions;
importcom.google.genai.types.Part;
importjava.util.List;
importjava.util.Optional;
public classCountTokensWithTextAndVideo {
 public static void main(String[] args) {
 // TODO(developer): Replace these variables before running the sample.
 String modelId = "gemini-2.5-flash";
 countTokens(modelId);
 }
 // Counts tokens with text and video inputs
 public static Optional<Integer> 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()) {
 Content content =
 Content.fromParts(
 Part.fromText("Provide a description of this video"),
 Part.fromUri("gs://cloud-samples-data/generative-ai/video/pixel8.mp4", "video/mp4"));
 CountTokensResponse response = client.models.countTokens(modelId, List.of(content), null);
 System.out.print(response);
 // Example response:
 // CountTokensResponse{totalTokens=Optional[16707], cachedContentTokenCount=Optional.empty}
 return response.totalTokens();
 }
 }
}