הסבר על אסימונים וספירתם

from google import genai

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

# Count tokens before sending
total_tokens = client.models.count_tokens(
    model="gemini-3-flash-preview",
    contents=prompt
)
print("total_tokens:", total_tokens)

# Get usage from interaction
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=prompt
)
print(interaction.usage)

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});
const prompt = "The quick brown fox jumps over the lazy dog.";

// Count tokens before sending
const countResponse = await client.models.countTokens({
    model: "gemini-3-flash-preview",
    contents: prompt,
});
console.log(countResponse.totalTokens);

// Get usage from interaction
const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: prompt,
});
console.log(interaction.usage);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-flash-preview:countTokens" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "The quick brown fox."}]}]}'

# First interaction
interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Hi, my name is Bob"
)

# Second interaction continues the conversation
interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What's my name?",
    previous_interaction_id=interaction1.id
)

# Usage includes tokens from both turns
print(f"Input tokens: {interaction2.usage.total_input_tokens}")
print(f"Output tokens: {interaction2.usage.total_output_tokens}")
print(f"Total tokens: {interaction2.usage.total_tokens}")

// First interaction
const interaction1 = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Hi, my name is Bob"
});

// Second interaction continues the conversation
const interaction2 = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: "What's my name?",
    previousInteractionId: interaction1.id
});

console.log(`Input tokens: ${interaction2.usage.totalInputTokens}`);
console.log(`Output tokens: ${interaction2.usage.totalOutputTokens}`);

uploaded_file = client.files.upload(file="path/to/image.jpg")

# Count tokens for image + text
total_tokens = client.models.count_tokens(
    model="gemini-3-flash-preview",
    contents=["Tell me about this image", uploaded_file]
)
print(f"Total tokens: {total_tokens}")

# Generate with image
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Tell me about this image"},
        {"type": "image", "uri": uploaded_file.uri, "mime_type": uploaded_file.mime_type}
    ]
)
print(interaction.usage)

const uploadedFile = await client.files.upload({
    file: "path/to/image.jpg",
    config: { mimeType: "image/jpeg" }
});

// Count tokens
const countResponse = await client.models.countTokens({
    model: "gemini-3-flash-preview",
    contents: [
        { text: "Tell me about this image" },
        { fileData: { fileUri: uploadedFile.uri, mimeType: uploadedFile.mimeType } }
    ]
});
console.log(countResponse.totalTokens);

import base64

with open('image.jpg', 'rb') as f:
    image_bytes = f.read()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Describe this image"},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/jpeg"
        }
    ]
)
print(interaction.usage)

import time

video_file = client.files.upload(file="path/to/video.mp4")

while not video_file.state or video_file.state.name != "ACTIVE":
    print("Processing video...")
    time.sleep(5)
    video_file = client.files.get(name=video_file.name)

# A 60-second video is approximately 263 * 60 = 15,780 tokens
total_tokens = client.models.count_tokens(
    model="gemini-3-flash-preview",
    contents=["Summarize this video", video_file]
)
print(f"Total tokens: {total_tokens}")

# Generate with video
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Summarize this video"},
        {"type": "video", "uri": video_file.uri, "mime_type": video_file.mime_type}
    ]
)
print(interaction.usage)

audio_file = client.files.upload(file="path/to/audio.mp3")

# A 60-second audio clip is approximately 32 * 60 = 1,920 tokens
total_tokens = client.models.count_tokens(
    model="gemini-3-flash-preview",
    contents=["Transcribe this audio", audio_file]
)
print(f"Total tokens: {total_tokens}")

# Generate with audio
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Transcribe this audio"},
        {"type": "audio", "uri": audio_file.uri, "mime_type": audio_file.mime_type}
    ]
)
print(interaction.usage)

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Hello!",
    system_instruction="You are a helpful assistant who speaks like a pirate."
)

# system_instruction tokens included in total_input_tokens
print(f"Input tokens: {interaction.usage.total_input_tokens}")

tools = [
    {
        "type": "function",
        "name": "get_weather",
        "description": "Get current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            }
        }
    }
]

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What's the weather in Tokyo?",
    tools=tools
)

print(f"Input tokens: {interaction.usage.total_input_tokens}")
print(f"Tool use tokens: {interaction.usage.total_tool_use_tokens}")

model_info = client.models.get(model="gemini-3-flash-preview")
print(f"Input token limit: {model_info.input_token_limit}")
print(f"Output token limit: {model_info.output_token_limit}")

const modelInfo = await client.models.get({ model: "gemini-3-flash-preview" });
console.log(`Input token limit: ${modelInfo.inputTokenLimit}`);
console.log(`Output token limit: ${modelInfo.outputTokenLimit}`);