Counting tokens

model = genai.GenerativeModel("models/gemini-1.5-flash")

prompt = "The quick brown fox jumps over the lazy dog."

# Call `count_tokens` to get the input token count (`total_tokens`).
print("total_tokens: ", model.count_tokens(prompt))
# ( total_tokens: 10 )

response = model.generate_content(prompt)

# On the response for `generate_content`, use `usage_metadata`
# to get separate input and output token counts
# (`prompt_token_count` and `candidates_token_count`, respectively),
# as well as the combined token count (`total_token_count`).
print(response.usage_metadata)
# ( prompt_token_count: 11, candidates_token_count: 73, total_token_count: 84 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
});

// Count tokens in a prompt without calling text generation.
const countResult = await model.countTokens(
  "The quick brown fox jumps over the lazy dog.",
);

console.log(countResult.totalTokens); // 11

const generateResult = await model.generateContent(
  "The quick brown fox jumps over the lazy dog.",
);

// On the response for `generateContent`, use `usageMetadata`
// to get separate input and output token counts
// (`promptTokenCount` and `candidatesTokenCount`, respectively),
// as well as the combined token count (`totalTokenCount`).
console.log(generateResult.response.usageMetadata);
// candidatesTokenCount and totalTokenCount depend on response, may vary
// { promptTokenCount: 11, candidatesTokenCount: 124, totalTokenCount: 135 }
count_tokens.js

model := client.GenerativeModel("gemini-1.5-flash")
prompt := "The quick brown fox jumps over the lazy dog"

// Call CountTokens to get the input token count (`total tokens`).
tokResp, err := model.CountTokens(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}

fmt.Println("total_tokens:", tokResp.TotalTokens)
// ( total_tokens: 10 )

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

// On the response for GenerateContent, use UsageMetadata to get
// separate input and output token counts (PromptTokenCount and
// CandidatesTokenCount, respectively), as well as the combined
// token count (TotalTokenCount).
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: 10, candidates_token_count: 38, total_token_count: 48 )
docs-snippets_test.go

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": "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

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

model = genai.GenerativeModel("models/gemini-1.5-flash")

chat = model.start_chat(
    history=[
        {"role": "user", "parts": "Hi my name is Bob"},
        {"role": "model", "parts": "Hi Bob!"},
    ]
)
# Call `count_tokens` to get the input token count (`total_tokens`).
print(model.count_tokens(chat.history))
# ( total_tokens: 10 )

response = chat.send_message(
    "In one sentence, explain how a computer works to a young child."
)

# On the response for `send_message`, use `usage_metadata`
# to get separate input and output token counts
# (`prompt_token_count` and `candidates_token_count`, respectively),
# as well as the combined token count (`total_token_count`).
print(response.usage_metadata)
# ( prompt_token_count: 25, candidates_token_count: 21, total_token_count: 46 )

from google.generativeai.types.content_types import to_contents

# You can call `count_tokens` on the combined history and content of the next turn.
print(model.count_tokens(chat.history + to_contents("What is the meaning of life?")))
# ( total_tokens: 56 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
});

const chat = model.startChat({
  history: [
    {
      role: "user",
      parts: [{ text: "Hi my name is Bob" }],
    },
    {
      role: "model",
      parts: [{ text: "Hi Bob!" }],
    },
  ],
});

const countResult = await model.countTokens({
  generateContentRequest: { contents: await chat.getHistory() },
});
console.log(countResult.totalTokens); // 10

const chatResult = await chat.sendMessage(
  "In one sentence, explain how a computer works to a young child.",
);

// On the response for `sendMessage`, use `usageMetadata`
// to get separate input and output token counts
// (`promptTokenCount` and `candidatesTokenCount`, respectively),
// as well as the combined token count (`totalTokenCount`).
console.log(chatResult.response.usageMetadata);
// candidatesTokenCount and totalTokenCount depend on response, may vary
// { promptTokenCount: 25, candidatesTokenCount: 25, totalTokenCount: 50 }
count_tokens.js

model := client.GenerativeModel("gemini-1.5-flash")
cs := model.StartChat()

cs.History = []*genai.Content{
	{
		Parts: []genai.Part{
			genai.Text("Hi my name is Bob"),
		},
		Role: "user",
	},
	{
		Parts: []genai.Part{
			genai.Text("Hi Bob!"),
		},
		Role: "model",
	},
}

prompt := "Explain how a computer works to a young child."
resp, err := cs.SendMessage(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}

// On the response for SendMessage, use `UsageMetadata` to get
// separate input and output token counts
// (`prompt_token_count` and `candidates_token_count`, respectively),
// as well as the combined token count (`total_token_count`).
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: 25, candidates_token_count: 21, total_token_count: 46 )
docs-snippets_test.go

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": [
        {"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

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

import PIL.Image

model = genai.GenerativeModel("models/gemini-1.5-flash")

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

# Call `count_tokens` 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.
print(model.count_tokens([prompt, your_image_file]))
# ( total_tokens: 263 )

response = model.generate_content([prompt, your_image_file])

# On the response for `generate_content`, use `usage_metadata`
# to get separate input and output token counts
# (`prompt_token_count` and `candidates_token_count`, respectively),
# as well as the combined token count (`total_token_count`).
print(response.usage_metadata)
# ( prompt_token_count: 264, candidates_token_count: 80, total_token_count: 345 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
});

function fileToGenerativePart(path, mimeType) {
  return {
    inlineData: {
      data: Buffer.from(fs.readFileSync(path)).toString("base64"),
      mimeType,
    },
  };
}

const imagePart = fileToGenerativePart(
  `${mediaPath}/jetpack.jpg`,
  "image/jpeg",
);

const prompt = "Tell me about this image.";

// Call `countTokens` to get the input token count
// of the combined text and file (`totalTokens`).
// An image's display or file size does not affect its token count.
// Optionally, you can call `countTokens` for the text and file separately.
const countResult = await model.countTokens([prompt, imagePart]);
console.log(countResult.totalTokens); // 265

const generateResult = await model.generateContent([prompt, imagePart]);

// On the response for `generateContent`, use `usageMetadata`
// to get separate input and output token counts
// (`promptTokenCount` and `candidatesTokenCount`, respectively),
// as well as the combined token count (`totalTokenCount`).
console.log(generateResult.response.usageMetadata);
// candidatesTokenCount and totalTokenCount depend on response, may vary
// { promptTokenCount: 265, candidatesTokenCount: 157, totalTokenCount: 422 }
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-1.5-flash:countTokens?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
            {"text": "Tell me about this instrument"},
            {
              "inline_data": {
                "mime_type":"image/jpeg",
                "data": "'$(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

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

import time

model = genai.GenerativeModel("models/gemini-1.5-flash")

prompt = "Tell me about this video"
your_file = genai.upload_file(path=media / "Big_Buck_Bunny.mp4")

# Videos need to be processed before you can use them.
while your_file.state.name == "PROCESSING":
    print("processing video...")
    time.sleep(5)
    your_file = genai.get_file(your_file.name)

# Call `count_tokens` to get the input token count
# of the combined text and video/audio file (`total_tokens`).
# A video or audio file is converted to tokens at a fixed rate of tokens per second.
# Optionally, you can call `count_tokens` for the text and file separately.
print(model.count_tokens([prompt, your_file]))
# ( total_tokens: 300 )

response = model.generate_content([prompt, your_file])

# On the response for `generate_content`, use `usage_metadata`
# to get separate input and output token counts
# (`prompt_token_count` and `candidates_token_count`, respectively),
# as well as the combined token count (`total_token_count`).
print(response.usage_metadata)
# ( prompt_token_count: 301, candidates_token_count: 60, total_token_count: 361 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleAIFileManager, FileState } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadVideoResult = await fileManager.uploadFile(
  `${mediaPath}/Big_Buck_Bunny.mp4`,
  { mimeType: "video/mp4" },
);

let file = await fileManager.getFile(uploadVideoResult.file.name);
process.stdout.write("processing video");
while (file.state === FileState.PROCESSING) {
  process.stdout.write(".");
  // Sleep for 10 seconds
  await new Promise((resolve) => setTimeout(resolve, 10_000));
  // Fetch the file from the API again
  file = await fileManager.getFile(uploadVideoResult.file.name);
}

if (file.state === FileState.FAILED) {
  throw new Error("Video processing failed.");
} else {
  process.stdout.write("\n");
}

const videoPart = {
  fileData: {
    fileUri: uploadVideoResult.file.uri,
    mimeType: uploadVideoResult.file.mimeType,
  },
};

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
});

const prompt = "Tell me about this video.";

// Call `countTokens` to get the input token count
// of the combined text and file (`totalTokens`).
// A video or audio file is converted to tokens at a fixed rate of tokens
// per second.
// Optionally, you can call `countTokens` for the text and file separately.
const countResult = await model.countTokens([prompt, videoPart]);

console.log(countResult.totalTokens); // 302

const generateResult = await model.generateContent([prompt, videoPart]);

// On the response for `generateContent`, use `usageMetadata`
// to get separate input and output token counts
// (`promptTokenCount` and `candidatesTokenCount`, respectively),
// as well as the combined token count (`totalTokenCount`).
console.log(generateResult.response.usageMetadata);
// candidatesTokenCount and totalTokenCount depend on response, may vary
// { promptTokenCount: 302, candidatesTokenCount: 46, totalTokenCount: 348 }
count_tokens.js

model := client.GenerativeModel("gemini-1.5-flash")
prompt := "Tell me about this video"
file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "earth.mp4"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

fd := genai.FileData{URI: file.URI}
// Call `CountTokens` to get the input token count
// of the combined text and file (`total_tokens`).
// A video or audio file is converted to tokens at a fixed rate of tokens per
// second.
// Optionally, you can call `count_tokens` for the text and file separately.
tokResp, err := model.CountTokens(ctx, genai.Text(prompt), fd)
if err != nil {
	log.Fatal(err)
}
fmt.Println("total_tokens:", tokResp.TotalTokens)
// ( total_tokens: 1481 )

resp, err := model.GenerateContent(ctx, genai.Text(prompt), fd)
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: 1481, candidates_token_count: 43, total_token_count: 1524 )
docs-snippets_test.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

model = genai.GenerativeModel("gemini-1.5-flash")
sample_pdf = genai.upload_file(media / "test.pdf")
token_count = model.count_tokens(["Give me a summary of this document.", sample_pdf])
print(f"{token_count=}")

response = model.generate_content(["Give me a summary of this document.", sample_pdf])
print(response.usage_metadata)
count_tokens.py

import time

model = genai.GenerativeModel("models/gemini-1.5-flash")

your_file = genai.upload_file(path=media / "a11.txt")

cache = genai.caching.CachedContent.create(
    model="models/gemini-1.5-flash-001",
    # You can set the system_instruction and tools
    system_instruction=None,
    tools=None,
    contents=["Here the Apollo 11 transcript:", your_file],
)

model = genai.GenerativeModel.from_cached_content(cache)

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

# Call `count_tokens` to get input token count
# of the combined text and file (`total_tokens`).
# A video or audio file is converted to tokens at a fixed rate of tokens per second.
# Optionally, you can call `count_tokens` for the text and file separately.
print(model.count_tokens(prompt))
# ( total_tokens: 9 )

response = model.generate_content(prompt)

# On the response for `generate_content`, use `usage_metadata`
# to get separate input and output token counts
# (`prompt_token_count` and `candidates_token_count`, respectively),
# as well as the cached content token count and the combined total token count.
print(response.usage_metadata)
# ( prompt_token_count: 323393, cached_content_token_count: 323383, candidates_token_count: 64)
# ( total_token_count: 323457 )

cache.delete()
count_tokens.py

// Make sure to include these imports:
// import { GoogleAIFileManager, GoogleAICacheManager } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";

// Upload large text file.
const fileManager = new GoogleAIFileManager(process.env.API_KEY);
const uploadResult = await fileManager.uploadFile(`${mediaPath}/a11.txt`, {
  mimeType: "text/plain",
});

// Create a cache that uses the uploaded file.
const cacheManager = new GoogleAICacheManager(process.env.API_KEY);
const cacheResult = await cacheManager.create({
  ttlSeconds: 600,
  model: "models/gemini-1.5-flash-001",
  contents: [
    {
      role: "user",
      parts: [{ text: "Here's the Apollo 11 transcript:" }],
    },
    {
      role: "user",
      parts: [
        {
          fileData: {
            fileUri: uploadResult.file.uri,
            mimeType: uploadResult.file.mimeType,
          },
        },
      ],
    },
  ],
});

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModelFromCachedContent(cacheResult);

const prompt = "Please give a short summary of this file.";

// Call `countTokens` to get the input token count
// of the combined text and file (`totalTokens`).
const result = await model.countTokens(prompt);

console.log(result.totalTokens); // 10

const generateResult = await model.generateContent(prompt);

// On the response for `generateContent`, use `usageMetadata`
// to get separate input and output token counts
// (`promptTokenCount` and `candidatesTokenCount`, respectively),
// as well as the cached content token count and the combined total
// token count.
console.log(generateResult.response.usageMetadata);
// {
//   promptTokenCount: 323396,
//   candidatesTokenCount: 113, (depends on response, may vary)
//   totalTokenCount: 323509,
//   cachedContentTokenCount: 323386
// }

await cacheManager.delete(cacheResult.name);
count_tokens.js

txt := strings.Repeat("George Washington was the first president of the United States. ", 3000)
argcc := &genai.CachedContent{
	Model:    "gemini-1.5-flash-001",
	Contents: []*genai.Content{genai.NewUserContent(genai.Text(txt))},
}
cc, err := client.CreateCachedContent(ctx, argcc)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteCachedContent(ctx, cc.Name)

modelWithCache := client.GenerativeModelFromCachedContent(cc)
prompt := "Summarize this statement"
tokResp, err := modelWithCache.CountTokens(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}
fmt.Println("total_tokens:", tokResp.TotalTokens)
// ( total_tokens: 5 )

resp, err := modelWithCache.GenerateContent(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}

fmt.Println("prompt_token_count:", resp.UsageMetadata.PromptTokenCount)
fmt.Println("candidates_token_count:", resp.UsageMetadata.CandidatesTokenCount)
fmt.Println("cached_content_token_count:", resp.UsageMetadata.CachedContentTokenCount)
fmt.Println("total_token_count:", resp.UsageMetadata.TotalTokenCount)
// ( prompt_token_count: 33007,  candidates_token_count: 39, cached_content_token_count: 33002, total_token_count: 33046 )
docs-snippets_test.go

model = genai.GenerativeModel(model_name="gemini-1.5-flash")

prompt = "The quick brown fox jumps over the lazy dog."

print(model.count_tokens(prompt))
# total_tokens: 10

model = genai.GenerativeModel(
    model_name="gemini-1.5-flash", system_instruction="You are a cat. Your name is Neko."
)

# The total token count includes everything sent to the `generate_content` request.
# When you use system instructions, the total token count increases.
print(model.count_tokens(prompt))
# ( total_tokens: 21 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const prompt = "The quick brown fox jumps over the lazy dog.";
const modelNoInstructions = genAI.getGenerativeModel({
  model: "models/gemini-1.5-flash",
});

const resultNoInstructions = await modelNoInstructions.countTokens(prompt);

console.log(resultNoInstructions);
// { totalTokens: 11 }

const modelWithInstructions = genAI.getGenerativeModel({
  model: "models/gemini-1.5-flash",
  systemInstruction: "You are a cat. Your name is Neko.",
});

const resultWithInstructions =
  await modelWithInstructions.countTokens(prompt);

// The total token count includes everything sent to the
// generateContent() request. When you use system instructions, the
// total token count increases.
console.log(resultWithInstructions);
// { totalTokens: 23 }
count_tokens.js

model := client.GenerativeModel("gemini-1.5-flash")
prompt := "The quick brown fox jumps over the lazy dog"

respNoInstruction, err := model.CountTokens(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}
fmt.Println("total_tokens:", respNoInstruction.TotalTokens)
// ( total_tokens: 10 )

// The total token count includes everything sent to the GenerateContent
// request. When you use system instructions, the total token
// count increases.
model.SystemInstruction = genai.NewUserContent(genai.Text("You are a cat. Your name is Neko."))
respWithInstruction, err := model.CountTokens(ctx, genai.Text(prompt))
if err != nil {
	log.Fatal(err)
}
fmt.Println("total_tokens:", respWithInstruction.TotalTokens)
// ( total_tokens: 21 )
docs-snippets_test.go

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

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

model = genai.GenerativeModel(model_name="gemini-1.5-flash")

prompt = "I have 57 cats, each owns 44 mittens, how many mittens is that in total?"

print(model.count_tokens(prompt))
# ( total_tokens: 22 )

def add(a: float, b: float):
    """returns a + b."""
    return a + b

def subtract(a: float, b: float):
    """returns a - b."""
    return a - b

def multiply(a: float, b: float):
    """returns a * b."""
    return a * b

def divide(a: float, b: float):
    """returns a / b."""
    return a / b

model = genai.GenerativeModel(
    "models/gemini-1.5-flash-001", tools=[add, subtract, multiply, divide]
)

# The total token count includes everything sent to the `generate_content` request.
# When you use tools (like function calling), the total token count increases.
print(model.count_tokens(prompt))
# ( total_tokens: 206 )
count_tokens.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const prompt =
  "I have 57 cats, each owns 44 mittens, how many mittens is that in total?";

const modelNoTools = genAI.getGenerativeModel({
  model: "models/gemini-1.5-flash",
});

const resultNoTools = await modelNoTools.countTokens(prompt);

console.log(resultNoTools);
// { totalTokens: 23 }

const functionDeclarations = [
  { name: "add" },
  { name: "subtract" },
  { name: "multiply" },
  { name: "divide" },
];

const modelWithTools = genAI.getGenerativeModel({
  model: "models/gemini-1.5-flash",
  tools: [{ functionDeclarations }],
});

const resultWithTools = await modelWithTools.countTokens(prompt);

// The total token count includes everything sent to the
// generateContent() request. When you use tools (like function calling),
// the total token count increases.
console.log(resultWithTools);
// { totalTokens: 99 }
count_tokens.js

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

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