Counting tokens

For a detailed guide on counting tokens using the Gemini API, including how images, audio and video are counted, see the Token counting guide and accompanying Cookbook recipe.

Method: models.countTokens

Runs a model's tokenizer on input Content and returns the token count. Refer to the tokens guide to learn more about tokens.

post https://generativelanguage.googleapis.com/v1beta/{model=models/*}:countTokens
model string

Required. The model's resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the models.list method.

Format: models/{model} It takes the form models/{model}.

The request body contains data with the following structure:

Fields
contents[] object (Content)

Optional. The input given to the model as a prompt. This field is ignored when generateContentRequest is set.

generateContentRequest object (GenerateContentRequest)

Optional. The overall input given to the Model. This includes the prompt as well as other model steering information like system instructions, and/or function declarations for function calling. Models/Contents and generateContentRequests are mutually exclusive. You can either send Model + Contents or a generateContentRequest, but never both.

TextChatInline mediaVideoPDFCacheSystem InstructionTools
PythonNode.jsGoShellKotlinSwiftDartJava
from google import genai

client = genai.Client()
prompt = "The quick brown fox jumps over the lazy dog."

# Count tokens using the new client method.
total_tokens = client.models.count_tokens(
    model="gemini-2.0-flash", contents=prompt
)
print("total_tokens: ", total_tokens)
# ( e.g., total_tokens: 10 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=prompt
)

# The usage_metadata provides detailed token counts.
print(response.usage_metadata)
# ( e.g., prompt_token_count: 11, candidates_token_count: 73, total_token_count: 84 )
count_tokens.py
 
// Make sure to include the following import:
// import {GoogleGenAI} from '@google/genai';
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
const prompt = "The quick brown fox jumps over the lazy dog.";
const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: prompt,
});
console.log(countTokensResponse.totalTokens);

const generateResponse = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: prompt,
});
console.log(generateResponse.usageMetadata);
count_tokens.js
 
ctx := context.Background()
client, err := genai.NewClient(ctx, &genai.ClientConfig{
	APIKey:  os.Getenv("GEMINI_API_KEY"),
	Backend: genai.BackendGeminiAPI,
})
if err != nil {
	log.Fatal(err)
}
prompt := "The quick brown fox jumps over the lazy dog."

// Convert prompt to a slice of *genai.Content using the helper.
contents := []*genai.Content{
	genai.NewContentFromText(prompt, "user"),
}
countResp, err := client.Models.CountTokens(ctx, "gemini-2.0-flash", contents, nil)
if err != nil {
	return err
}
fmt.Println("total_tokens:", countResp.TotalTokens)

response, err := client.Models.GenerateContent(ctx, "gemini-2.0-flash", contents, nil)
if err != nil {
	log.Fatal(err)
}
usageMetadata, err := json.MarshalIndent(response.UsageMetadata, "", "  ")
if err != nil {
	log.Fatal(err)
}
fmt.Println(string(usageMetadata))
count_tokens.go
 
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:countTokens?key=$GEMINI_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[{
          "text": "The quick brown fox jumps over the lazy dog."
          }],
        }],
      }'
count_tokens.sh
 
val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

// For text-only input
val (totalTokens) = generativeModel.countTokens("Write a story about a magic backpack.")
print(totalTokens)
count_tokens.kt
 
let generativeModel =
  GenerativeModel(
    // Specify a Gemini model appropriate for your use case
    name: "gemini-1.5-flash",
    // Access your API key from your on-demand resource .plist file (see "Set up your API key"
    // above)
    apiKey: APIKey.default
  )

let prompt = "Write a story about a magic backpack."

let response = try await generativeModel.countTokens(prompt)

print("Total Tokens: \(response.totalTokens)")
CountTokens.swift
 
// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final prompt = 'The quick brown fox jumps over the lazy dog.';
final tokenCount = await model.countTokens([Content.text(prompt)]);
print('Total tokens: ${tokenCount.totalTokens}');
count_tokens.dart
 
// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content inputContent =
    new Content.Builder().addText("Write a story about a magic backpack.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// For text-only input
ListenableFuture<CountTokensResponse> countTokensResponse = model.countTokens(inputContent);

Futures.addCallback(
    countTokensResponse,
    new FutureCallback<CountTokensResponse>() {
      @Override
      public void onSuccess(CountTokensResponse result) {
        int totalTokens = result.getTotalTokens();
        System.out.println("TotalTokens = " + totalTokens);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
count_tokens.java
PythonNode.jsGoShellKotlinSwiftDartJava
from google import genai
from google.genai import types

client = genai.Client()

chat = client.chats.create(
    model="gemini-2.0-flash",
    history=[
        types.Content(
            role="user", parts=[types.Part(text="Hi my name is Bob")]
        ),
        types.Content(role="model", parts=[types.Part(text="Hi Bob!")]),
    ],
)
# Count tokens for the chat history.
print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=chat.get_history()
    )
)
# ( e.g., total_tokens: 10 )

response = chat.send_message(
    message="In one sentence, explain how a computer works to a young child."
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 25, candidates_token_count: 21, total_token_count: 46 )

# You can count tokens for the combined history and a new message.
extra = types.UserContent(
    parts=[
        types.Part(
            text="What is the meaning of life?",
        )
    ]
)
history = chat.get_history()
history.append(extra)
print(client.models.count_tokens(model="gemini-2.0-flash", contents=history))
# ( e.g., total_tokens: 56 )
count_tokens.py
 
// Make sure to include the following import:
// import {GoogleGenAI} from '@google/genai';
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
// Initial chat history.
const history = [
  { role: "user", parts: [{ text: "Hi my name is Bob" }] },
  { role: "model", parts: [{ text: "Hi Bob!" }] },
];
const chat = ai.chats.create({
  model: "gemini-2.0-flash",
  history: history,
});

// Count tokens for the current chat history.
const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: chat.getHistory(),
});
console.log(countTokensResponse.totalTokens);

const chatResponse = await chat.sendMessage({
  message: "In one sentence, explain how a computer works to a young child.",
});
console.log(chatResponse.usageMetadata);

// Add an extra user message to the history.
const extraMessage = {
  role: "user",
  parts: [{ text: "What is the meaning of life?" }],
};
const combinedHistory = chat.getHistory();
combinedHistory.push(extraMessage);
const combinedCountTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: combinedHistory,
});
console.log(
  "Combined history token count:",
  combinedCountTokensResponse.totalTokens,
);
count_tokens.js
 
ctx := context.Background()
client, err := genai.NewClient(ctx, &genai.ClientConfig{
	APIKey:  os.Getenv("GEMINI_API_KEY"),
	Backend: genai.BackendGeminiAPI,
})
if err != nil {
	log.Fatal(err)
}

// Initialize chat with some history.
history := []*genai.Content{
	{Role: "user", Parts: []*genai.Part{{Text: "Hi my name is Bob"}}},
	{Role: "model", Parts: []*genai.Part{{Text: "Hi Bob!"}}},
}
chat, err := client.Chats.Create(ctx, "gemini-2.0-flash", nil, history)
if err != nil {
	log.Fatal(err)
}

firstTokenResp, err := client.Models.CountTokens(ctx, "gemini-2.0-flash", chat.History(false), nil)
if err != nil {
	log.Fatal(err)
}
fmt.Println(firstTokenResp.TotalTokens)

resp, err := chat.SendMessage(ctx, genai.Part{
	Text: "In one sentence, explain how a computer works to a young child."},
)
if err != nil {
	log.Fatal(err)
}
fmt.Printf("%#v\n", resp.UsageMetadata)

// Append an extra user message and recount.
extra := genai.NewContentFromText("What is the meaning of life?", "user")
hist := chat.History(false)
hist = append(hist, extra)

secondTokenResp, err := client.Models.CountTokens(ctx, "gemini-2.0-flash", hist, nil)
if err != nil {
	log.Fatal(err)
}
fmt.Println(secondTokenResp.TotalTokens)
count_tokens.go
 
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:countTokens?key=$GEMINI_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [
        {"role": "user",
        "parts": [{"text": "Hi, my name is Bob."}],
        },
        {"role": "model",
         "parts":[{"text": "Hi Bob"}],
        },
      ],
      }'
count_tokens.sh
 
val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

val chat =
    generativeModel.startChat(
        history =
            listOf(
                content(role = "user") { text("Hello, I have 2 dogs in my house.") },
                content(role = "model") {
                  text("Great to meet you. What would you like to know?")
                }))

val history = chat.history
val messageContent = content { text("This is the message I intend to send") }
val (totalTokens) = generativeModel.countTokens(*history.toTypedArray(), messageContent)
print(totalTokens)
count_tokens.kt
 
let generativeModel =
  GenerativeModel(
    // Specify a Gemini model appropriate for your use case
    name: "gemini-1.5-flash",
    // Access your API key from your on-demand resource .plist file (see "Set up your API key"
    // above)
    apiKey: APIKey.default
  )

// Optionally specify existing chat history
let history = [
  ModelContent(role: "user", parts: "Hello, I have 2 dogs in my house."),
  ModelContent(role: "model", parts: "Great to meet you. What would you like to know?"),
]

// Initialize the chat with optional chat history
let chat = generativeModel.startChat(history: history)

let response = try await generativeModel.countTokens(chat.history + [
  ModelContent(role: "user", parts: "This is the message I intend to send"),
])
print("Total Tokens: \(response.totalTokens)")
CountTokens.swift
 
// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final chat = model.startChat(history: [
  Content.text('Hi my name is Bob'),
  Content.model([TextPart('Hi Bob!')])
]);
var tokenCount = await model.countTokens(chat.history);
print('Total tokens: ${tokenCount.totalTokens}');

final response = await chat.sendMessage(Content.text(
    'In one sentence, explain how a computer works to a young child.'));
if (response.usageMetadata case final usage?) {
  print('Prompt: ${usage.promptTokenCount}, '
      'Candidates: ${usage.candidatesTokenCount}, '
      'Total: ${usage.totalTokenCount}');
}

tokenCount = await model.countTokens(
    [...chat.history, Content.text('What is the meaning of life?')]);
print('Total tokens: ${tokenCount.totalTokens}');
count_tokens.dart
 
// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// (optional) Create previous chat history for context
Content.Builder userContentBuilder = new Content.Builder();
userContentBuilder.setRole("user");
userContentBuilder.addText("Hello, I have 2 dogs in my house.");
Content userContent = userContentBuilder.build();

Content.Builder modelContentBuilder = new Content.Builder();
modelContentBuilder.setRole("model");
modelContentBuilder.addText("Great to meet you. What would you like to know?");
Content modelContent = userContentBuilder.build();

List<Content> history = Arrays.asList(userContent, modelContent);

// Initialize the chat
ChatFutures chat = model.startChat(history);

Content messageContent =
    new Content.Builder().addText("This is the message I intend to send").build();

Collections.addAll(history, messageContent);

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

ListenableFuture<CountTokensResponse> countTokensResponse =
    model.countTokens(history.toArray(new Content[0]));
Futures.addCallback(
    countTokensResponse,
    new FutureCallback<CountTokensResponse>() {
      @Override
      public void onSuccess(CountTokensResponse result) {
        System.out.println(result);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
count_tokens.java
PythonNode.jsGoShellKotlinSwiftDartJava
from google import genai
import PIL.Image

client = genai.Client()
prompt = "Tell me about this image"
your_image_file = PIL.Image.open(media / "organ.jpg")

# Count tokens for combined text and inline image.
print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=[prompt, your_image_file]
    )
)
# ( e.g., total_tokens: 263 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=[prompt, your_image_file]
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 264, candidates_token_count: 80, total_token_count: 345 )
count_tokens.py
 
// Make sure to include the following import:
// import {GoogleGenAI} from '@google/genai';
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
const prompt = "Tell me about this image";
const imageBuffer = fs.readFileSync(path.join(media, "organ.jpg"));

// Convert buffer to base64 string.
const imageBase64 = imageBuffer.toString("base64");

// Build contents using createUserContent and createPartFromBase64.
const contents = createUserContent([
  prompt,
  createPartFromBase64(imageBase64, "image/jpeg"),
]);

const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: contents,
});
console.log(countTokensResponse.totalTokens);

const generateResponse = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: contents,
});
console.log(generateResponse.usageMetadata);
count_tokens.js
 
model := client.GenerativeModel("gemini-1.5-flash")
prompt := "Tell me about this image"
imageFile, err := os.ReadFile(filepath.Join(testDataDir, "personWorkingOnComputer.jpg"))
if err != nil {
	log.Fatal(err)
}
// Call `CountTokens` to get the input token count
// of the combined text and file (`total_tokens`).
// An image's display or file size does not affect its token count.
// Optionally, you can call `count_tokens` for the text and file separately.
tokResp, err := model.CountTokens(ctx, genai.Text(prompt), genai.ImageData("jpeg", imageFile))
if err != nil {
	log.Fatal(err)
}
fmt.Println("total_tokens:", tokResp.TotalTokens)
// ( total_tokens: 264 )

resp, err := model.GenerateContent(ctx, genai.Text(prompt), genai.ImageData("jpeg", imageFile))
if err != nil {
	log.Fatal(err)
}

fmt.Println("prompt_token_count:", resp.UsageMetadata.PromptTokenCount)
fmt.Println("candidates_token_count:", resp.UsageMetadata.CandidatesTokenCount)
fmt.Println("total_token_count:", resp.UsageMetadata.TotalTokenCount)
// ( prompt_token_count: 264, candidates_token_count: 100, total_token_count: 364 )
docs-snippets_test.go
 
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:countTokens?key=$GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
            {"text": "Tell me about this instrument"},
            {
              "inline_data": {
                "mime_type":"image/jpeg",
                "data": "'$(base64 $B64FLAGS $IMG_PATH)'"
              }
            }
        ]
        }]
       }' 2> /dev/null
count_tokens.sh
 
val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

val image1: Bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.image1)
val image2: Bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.image2)

val multiModalContent = content {
  image(image1)
  image(image2)
  text("What's the difference between these pictures?")
}

val (totalTokens) = generativeModel.countTokens(multiModalContent)
print(totalTokens)
count_tokens.kt
 
let generativeModel =
  GenerativeModel(
    // Specify a Gemini model appropriate for your use case
    name: "gemini-1.5-flash",
    // Access your API key from your on-demand resource .plist file (see "Set up your API key"
    // above)
    apiKey: APIKey.default
  )

guard let image1 = UIImage(systemName: "cloud.sun") else { fatalError() }
guard let image2 = UIImage(systemName: "cloud.heavyrain") else { fatalError() }

let prompt = "What's the difference between these pictures?"

let response = try await generativeModel.countTokens(image1, image2, prompt)
print("Total Tokens: \(response.totalTokens)")
CountTokens.swift
 
// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);

Future<DataPart> fileToPart(String mimeType, String path) async {
  return DataPart(mimeType, await File(path).readAsBytes());
}

final prompt = 'Tell me about this image';
final image = await fileToPart('image/jpeg', 'resources/organ.jpg');
final content = Content.multi([TextPart(prompt), image]);

// An image's display size does not affet its token count.
// Optionally, you can call `countTokens` for the prompt and file separately.
final tokenCount = await model.countTokens([content]);
print('Total tokens: ${tokenCount.totalTokens}');

final response = await model.generateContent([content]);
if (response.usageMetadata case final usage?) {
  print('Prompt: ${usage.promptTokenCount}, '
      'Candidates: ${usage.candidatesTokenCount}, '
      'Total: ${usage.totalTokenCount}');
}
count_tokens.dart
 
// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);
Content text = new Content.Builder().addText("Write a story about a magic backpack.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// For text-and-image input
Bitmap image1 = BitmapFactory.decodeResource(context.getResources(), R.drawable.image1);
Bitmap image2 = BitmapFactory.decodeResource(context.getResources(), R.drawable.image2);

Content multiModalContent =
    new Content.Builder()
        .addImage(image1)
        .addImage(image2)
        .addText("What's different between these pictures?")
        .build();

ListenableFuture<CountTokensResponse> countTokensResponse =
    model.countTokens(multiModalContent);

Futures.addCallback(
    countTokensResponse,
    new FutureCallback<CountTokensResponse>() {
      @Override
      public void onSuccess(CountTokensResponse result) {
        int totalTokens = result.getTotalTokens();
        System.out.println("TotalTokens = " + totalTokens);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
count_tokens.java
PythonNode.jsGoShell
from google import genai
import time

client = genai.Client()
prompt = "Tell me about this video"
your_file = client.files.upload(file=media / "Big_Buck_Bunny.mp4")

# Poll until the video file is completely processed (state becomes ACTIVE).
while not your_file.state or your_file.state.name != "ACTIVE":
    print("Processing video...")
    print("File state:", your_file.state)
    time.sleep(5)
    your_file = client.files.get(name=your_file.name)

print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=[prompt, your_file]
    )
)
# ( e.g., total_tokens: 300 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=[prompt, your_file]
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 301, candidates_token_count: 60, total_token_count: 361 )
count_tokens.py
 
// Make sure to include the following import:
// import {GoogleGenAI} from '@google/genai';
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
const prompt = "Tell me about this video";
let videoFile = await ai.files.upload({
  file: path.join(media, "Big_Buck_Bunny.mp4"),
  config: { mimeType: "video/mp4" },
});

// Poll until the video file is completely processed (state becomes ACTIVE).
while (!videoFile.state || videoFile.state.toString() !== "ACTIVE") {
  console.log("Processing video...");
  console.log("File state: ", videoFile.state);
  await sleep(5000);
  videoFile = await ai.files.get({ name: videoFile.name });
}

const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: createUserContent([
    prompt,
    createPartFromUri(videoFile.uri, videoFile.mimeType),
  ]),
});
console.log(countTokensResponse.totalTokens);

const generateResponse = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: createUserContent([
    prompt,
    createPartFromUri(videoFile.uri, videoFile.mimeType),
  ]),
});
console.log(generateResponse.usageMetadata);
count_tokens.js
 
ctx := context.Background()
client, err := genai.NewClient(ctx, &genai.ClientConfig{
	APIKey:  os.Getenv("GEMINI_API_KEY"),
	Backend: genai.BackendGeminiAPI,
})
if err != nil {
	log.Fatal(err)
}

file, err := client.Files.UploadFromPath(
	ctx, 
	filepath.Join(getMedia(), "Big_Buck_Bunny.mp4"), 
	&genai.UploadFileConfig{
		MIMEType : "video/mp4",
	},
)
if err != nil {
	log.Fatal(err)
}

// Poll until the video file is completely processed (state becomes ACTIVE).
for file.State == genai.FileStateUnspecified || file.State != genai.FileStateActive {
	fmt.Println("Processing video...")
	fmt.Println("File state:", file.State)
	time.Sleep(5 * time.Second)

	file, err = client.Files.Get(ctx, file.Name, nil)
	if err != nil {
		log.Fatal(err)
	}
}

parts := []*genai.Part{
	genai.NewPartFromText("Tell me about this video"),
	genai.NewPartFromURI(file.URI, file.MIMEType),
}
contents := []*genai.Content{
	genai.NewContentFromParts(parts, "user"),
}

tokenResp, err := client.Models.CountTokens(ctx, "gemini-2.0-flash", contents, nil)
if err != nil {
	log.Fatal(err)
}
fmt.Println("Multimodal video/audio token count:", tokenResp.TotalTokens)
response, err := client.Models.GenerateContent(ctx, "gemini-2.0-flash", contents, nil)
if err != nil {
	log.Fatal(err)
}
usageMetadata, err := json.MarshalIndent(response.UsageMetadata, "", "  ")
if err != nil {
	log.Fatal(err)
}
fmt.Println(string(usageMetadata))
count_tokens.go
 

MIME_TYPE=$(file -b --mime-type "${VIDEO_PATH}")
NUM_BYTES=$(wc -c < "${VIDEO_PATH}")
DISPLAY_NAME=VIDEO_PATH

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${VIDEO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)

state=$(jq ".file.state" file_info.json)

name=$(jq ".file.name" file_info.json)

while [[ "($state)" = *"PROCESSING"* ]];
do
  echo "Processing video..."
  sleep 5
  # Get the file of interest to check state
  curl https://generativelanguage.googleapis.com/v1beta/files/$name > file_info.json
  state=$(jq ".file.state" file_info.json)
done

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:countTokens?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this video clip"},
          {"file_data":{"mime_type": "video/mp4", "file_uri": '$file_uri'}}]
        }]
       }'
count_tokens.sh
Python
from google import genai

client = genai.Client()
sample_pdf = client.files.upload(file=media / "test.pdf")
token_count = client.models.count_tokens(
    model="gemini-2.0-flash",
    contents=["Give me a summary of this document.", sample_pdf],
)
print(f"{token_count=}")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=["Give me a summary of this document.", sample_pdf],
)
print(response.usage_metadata)
count_tokens.py
PythonNode.jsGo
from google import genai
from google.genai import types
import time

client = genai.Client()
your_file = client.files.upload(file=media / "a11.txt")

cache = client.caches.create(
    model="gemini-1.5-flash-001",
    config={
        "contents": ["Here the Apollo 11 transcript:", your_file],
        "system_instruction": None,
        "tools": None,
    },
)

# Create a prompt.
prompt = "Please give a short summary of this file."

# Count tokens for the prompt (the cached content is not passed here).
print(client.models.count_tokens(model="gemini-2.0-flash", contents=prompt))
# ( e.g., total_tokens: 9 )

response = client.models.generate_content(
    model="gemini-1.5-flash-001",
    contents=prompt,
    config=types.GenerateContentConfig(
        cached_content=cache.name,
    ),
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: ..., cached_content_token_count: ..., candidates_token_count: ... )
client.caches.delete(name=cache.name)
count_tokens.py
 
  // Make sure to include the following import:
  // import {GoogleGenAI} from '@google/genai';
  const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
  const textFile = await ai.files.upload({
    file: path.join(media, "a11.txt"),
    config: { mimeType: "text/plain" },
  });

  const cache = await ai.caches.create({
    model: "gemini-1.5-flash-001",
    config: {
      contents: createUserContent([
        "Here the Apollo 11 transcript:",
        createPartFromUri(textFile.uri, textFile.mimeType),
      ]),
      system_instruction: null,
      tools: null,
    },
  });

  const prompt = "Please give a short summary of this file.";
  const countTokensResponse = await ai.models.countTokens({
    model: "gemini-2.0-flash",
    contents: prompt,
  });
  console.log(countTokensResponse.totalTokens);

  const generateResponse = await ai.models.generateContent({
    model: "gemini-1.5-flash-001",
    contents: prompt,
    config: { cachedContent: cache.name },
  });
  console.log(generateResponse.usageMetadata);

  await ai.caches.delete({ name: cache.name });
  return {
    totalTokens: countTokensResponse.totalTokens,
    usage: generateResponse.usageMetadata,
  };
}

count_tokens.js
 
ctx := context.Background()
client, err := genai.NewClient(ctx, &genai.ClientConfig{
	APIKey:  os.Getenv("GEMINI_API_KEY"),
	Backend: genai.BackendGeminiAPI,
})
if err != nil {
	log.Fatal(err)
}

file, err := client.Files.UploadFromPath(
	ctx, 
	filepath.Join(getMedia(), "a11.txt"), 
	&genai.UploadFileConfig{
		MIMEType : "text/plain",
	},
)
if err != nil {
	log.Fatal(err)
}
parts := []*genai.Part{
	genai.NewPartFromText("Here the Apollo 11 transcript:"),
	genai.NewPartFromURI(file.URI, file.MIMEType),
}
contents := []*genai.Content{
	genai.NewContentFromParts(parts, "user"),
}

// Create cached content using a simple slice with text and a file.
cache, err := client.Caches.Create(ctx, "gemini-1.5-flash-001", &genai.CreateCachedContentConfig{
	Contents: contents,
})
if err != nil {
	log.Fatal(err)
}

prompt := "Please give a short summary of this file."
countResp, err := client.Models.CountTokens(ctx, "gemini-2.0-flash", []*genai.Content{
	genai.NewContentFromText(prompt, "user"),
}, nil)
if err != nil {
	log.Fatal(err)
}
fmt.Printf("%d", countResp.TotalTokens)
response, err := client.Models.GenerateContent(ctx, "gemini-1.5-flash-001", []*genai.Content{
	genai.NewContentFromText(prompt, "user"),
}, &genai.GenerateContentConfig{
	CachedContent: cache.Name,
})
if err != nil {
	log.Fatal(err)
}

usageMetadata, err := json.MarshalIndent(response.UsageMetadata, "", "  ")
if err != nil {
	log.Fatal(err)
}
// Returns `nil` for some reason
fmt.Println(string(usageMetadata))
_, err = client.Caches.Delete(ctx, cache.Name, &genai.DeleteCachedContentConfig{})
count_tokens.go
KotlinSwiftDartJava
val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey,
        systemInstruction = content(role = "system") { text("You are a cat. Your name is Neko.")}
    )

// For text-only input
val (totalTokens) = generativeModel.countTokens("What is your name?")
print(totalTokens)
count_tokens.kt
 
let generativeModel =
  GenerativeModel(
    // Specify a model that supports system instructions, like a Gemini 1.5 model
    name: "gemini-1.5-flash",
    // Access your API key from your on-demand resource .plist file (see "Set up your API key"
    // above)
    apiKey: APIKey.default,
    systemInstruction: ModelContent(role: "system", parts: "You are a cat. Your name is Neko.")
  )

let prompt = "What is your name?"

let response = try await generativeModel.countTokens(prompt)
print("Total Tokens: \(response.totalTokens)")
CountTokens.swift
 
// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
var model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final prompt = 'The quick brown fox jumps over the lazy dog.';

// The total token count includes everything sent in the `generateContent`
// request.
var tokenCount = await model.countTokens([Content.text(prompt)]);
print('Total tokens: ${tokenCount.totalTokens}');
model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
  systemInstruction: Content.system('You are a cat. Your name is Neko.'),
);
tokenCount = await model.countTokens([Content.text(prompt)]);
print('Total tokens: ${tokenCount.totalTokens}');
count_tokens.dart
 
// Create your system instructions
Content systemInstruction =
    new Content.Builder().addText("You are a cat. Your name is Neko.").build();

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey,
        /* generationConfig (optional) */ null,
        /* safetySettings (optional) */ null,
        /* requestOptions (optional) */ new RequestOptions(),
        /* tools (optional) */ null,
        /* toolsConfig (optional) */ null,
        /* systemInstruction (optional) */ systemInstruction);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content inputContent = new Content.Builder().addText("What's your name?.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// For text-only input
ListenableFuture<CountTokensResponse> countTokensResponse = model.countTokens(inputContent);

Futures.addCallback(
    countTokensResponse,
    new FutureCallback<CountTokensResponse>() {
      @Override
      public void onSuccess(CountTokensResponse result) {
        int totalTokens = result.getTotalTokens();
        System.out.println("TotalTokens = " + totalTokens);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
count_tokens.java
KotlinSwiftDartJava
val multiplyDefinition = defineFunction(
    name = "multiply",
    description = "returns the product of the provided numbers.",
    parameters = listOf(
        Schema.double("a", "First number"),
        Schema.double("b", "Second number")
    )
)
val usableFunctions = listOf(multiplyDefinition)

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey,
        tools = listOf(Tool(usableFunctions))
    )

// For text-only input
val (totalTokens) = generativeModel.countTokens("What's the product of 9 and 358?")
print(totalTokens)
count_tokens.kt
 
let generativeModel =
  GenerativeModel(
    // Specify a model that supports system instructions, like a Gemini 1.5 model
    name: "gemini-1.5-flash",
    // Access your API key from your on-demand resource .plist file (see "Set up your API key"
    // above)
    apiKey: APIKey.default,
    tools: [Tool(functionDeclarations: [
      FunctionDeclaration(
        name: "controlLight",
        description: "Set the brightness and color temperature of a room light.",
        parameters: [
          "brightness": Schema(
            type: .number,
            format: "double",
            description: "Light level from 0 to 100. Zero is off and 100 is full brightness."
          ),
          "colorTemperature": Schema(
            type: .string,
            format: "enum",
            description: "Color temperature of the light fixture.",
            enumValues: ["daylight", "cool", "warm"]
          ),
        ],
        requiredParameters: ["brightness", "colorTemperature"]
      ),
    ])]
  )

let prompt = "Dim the lights so the room feels cozy and warm."

let response = try await generativeModel.countTokens(prompt)
print("Total Tokens: \(response.totalTokens)")
CountTokens.swift
 
// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
var model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final prompt = 'I have 57 cats, each owns 44 mittens, '
    'how many mittens is that in total?';

// The total token count includes everything sent in the `generateContent`
// request.
var tokenCount = await model.countTokens([Content.text(prompt)]);
print('Total tokens: ${tokenCount.totalTokens}');
final binaryFunction = Schema.object(
  properties: {
    'a': Schema.number(nullable: false),
    'b': Schema.number(nullable: false)
  },
  requiredProperties: ['a', 'b'],
);

model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
  tools: [
    Tool(functionDeclarations: [
      FunctionDeclaration('add', 'returns a + b', binaryFunction),
      FunctionDeclaration('subtract', 'returns a - b', binaryFunction),
      FunctionDeclaration('multipley', 'returns a * b', binaryFunction),
      FunctionDeclaration('divide', 'returns a / b', binaryFunction)
    ])
  ],
);
tokenCount = await model.countTokens([Content.text(prompt)]);
print('Total tokens: ${tokenCount.totalTokens}');
count_tokens.dart
 
FunctionDeclaration multiplyDefinition =
    defineFunction(
        /* name  */ "multiply",
        /* description */ "returns a * b.",
        /* parameters */ Arrays.asList(
            Schema.numDouble("a", "First parameter"),
            Schema.numDouble("b", "Second parameter")),
        /* required */ Arrays.asList("a", "b"));

Tool tool = new Tool(Arrays.asList(multiplyDefinition), null);
;

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey,
        /* generationConfig (optional) */ null,
        /* safetySettings (optional) */ null,
        /* requestOptions (optional) */ new RequestOptions(),
        /* tools (optional) */ Arrays.asList(tool));
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content inputContent = new Content.Builder().addText("What's your name?.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// For text-only input
ListenableFuture<CountTokensResponse> countTokensResponse = model.countTokens(inputContent);

Futures.addCallback(
    countTokensResponse,
    new FutureCallback<CountTokensResponse>() {
      @Override
      public void onSuccess(CountTokensResponse result) {
        int totalTokens = result.getTotalTokens();
        System.out.println("TotalTokens = " + totalTokens);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
count_tokens.java

Response body

A response from models.countTokens.

It returns the model's tokenCount for the prompt.

If successful, the response body contains data with the following structure:

Fields
totalTokens integer

The number of tokens that the Model tokenizes the prompt into. Always non-negative.

cachedContentTokenCount integer

Number of tokens in the cached part of the prompt (the cached content).

promptTokensDetails[] object (ModalityTokenCount)

Output only. List of modalities that were processed in the request input.

cacheTokensDetails[] object (ModalityTokenCount)

Output only. List of modalities that were processed in the cached content.

JSON representation 
{
  "totalTokens": integer,
  "cachedContentTokenCount": integer,
  "promptTokensDetails": [
    {
      object (ModalityTokenCount)
    }
  ],
  "cacheTokensDetails": [
    {
      object (ModalityTokenCount)
    }
  ]
}

GenerateContentRequest

Request to generate a completion from the model.

Fields
model string

Required. The name of the Model to use for generating the completion.

Format: models/{model}.

contents[] object (Content)

Required. The content of the current conversation with the model.

For single-turn queries, this is a single instance. For multi-turn queries like chat, this is a repeated field that contains the conversation history and the latest request.

tools[] object (Tool)

Optional. A list of Tools the Model may use to generate the next response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the Model. Supported Tools are Function and codeExecution. Refer to the Function calling and the Code execution guides to learn more.

toolConfig object (ToolConfig)

Optional. Tool configuration for any Tool specified in the request. Refer to the Function calling guide for a usage example.

safetySettings[] object (SafetySetting)

Optional. A list of unique SafetySetting instances for blocking unsafe content.

This will be enforced on the GenerateContentRequest.contents and GenerateContentResponse.candidates. There should not be more than one setting for each SafetyCategory type. The API will block any contents and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each SafetyCategory specified in the safetySettings. If there is no SafetySetting for a given SafetyCategory provided in the list, the API will use the default safety setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_CIVIC_INTEGRITY are supported. Refer to the guide for detailed information on available safety settings. Also refer to the Safety guidance to learn how to incorporate safety considerations in your AI applications.

systemInstruction object (Content)

Optional. Developer set system instruction(s). Currently, text only.

generationConfig object (GenerationConfig)

Optional. Configuration options for model generation and outputs.

cachedContent string

Optional. The name of the content cached to use as context to serve the prediction. Format: cachedContents/{cachedContent}

JSON representation 
{
  "model": string,
  "contents": [
    {
      object (Content)
    }
  ],
  "tools": [
    {
      object (Tool)
    }
  ],
  "toolConfig": {
    object (ToolConfig)
  },
  "safetySettings": [
    {
      object (SafetySetting)
    }
  ],
  "systemInstruction": {
    object (Content)
  },
  "generationConfig": {
    object (GenerationConfig)
  },
  "cachedContent": string
}